Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 107
Encontrada(s) 2 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Strategies in Case-Based Argumentation-Based Negotiation: An Application for the Tourism Domain

  • Bouslama, Rihab
  • Amor, Nahla Ben
  • Jordán, Jaume|||0000-0003-0400-9136
  • Heras, Stella|||0000-0001-6212-9377
[EN] Negotiation is a key solution to find an agreement between conflicting parties especially during the purchase journey. This paper treats the negotiations between a travel agency and its customers in the domain of tourism. Both automated negotiation and argumentation are gathered to create a framework for automated agents, presenting a travel agency and its customers, to negotiate a trip and exchange arguments. Agents take advantage of their past experiences and use Case-Based Reasoning to select the best strategy to follow. We represent agents using two types of profiles, Argumentative profile that represents agents¿ ways of reasoning and Preference profile that embodies customers¿ preferences in the domain of tourism.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

From Simultaneous to Streaming Machine Translation by Leveraging Streaming History

  • Iranzo-Sánchez, Javier
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously translated text. More generally, Streaming MT can be understood as an extension of Simultaneous MT to the incremental translation of a continuous input text stream. In this work, a state-of-the-art simultaneous sentencelevel MT system is extended to the streaming setup by leveraging the streaming history. Extensive empirical results are reported on IWSLT Translation Tasks, showing that leveraging the streaming history leads to significant quality gains. In particular, the proposed system proves to compare favorably to the best performing systems., The research leading to these results has received funding from the European Union¿s Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5Gon) and 952215 (TAILOR), and Erasmus+ Education programme under grant agreement no. 20-226-093604-SCH (EXPERT); the Government of Spain¿s grant RTI2018-094879-B-I00 (Multisub) funded by MCIN/AEI/10.13039/501100011033 & ¿ERDF A way of making Europe¿, and FPU scholarships FPU18/04135; and the Generalitat Valenciana¿s research project Classroom Activity Recognition (ref. PROMETEO/2019/111). The authors gratefully acknowledge the computer resources at Artemisa, funded by the European Union ERDF and Comunitat Valenciana as well as the technical support provided by the Instituto de Física Corpuscular, IFIC (CSIC-UV).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Deep Embedded Framework for Spitzoid Neoplasm Classification Using DNA Methylation Data

  • del Amor, Rocío
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Monteagudo, Carlos
  • Garzón, María José
  • García-Giménez, José Luis
[EN] Spitzoid melanocytic tumors (SMT) are a group of neoplasms that represent a formidable diagnostic challenge for dermatopathologists. DNA methylation (DNAm) is a welldefined epigenetic factor that has an important role in the development of these lesions. In this work, we propose different deep-learning-based approaches to address the Spitzoid neoplasms detection from DNAm. We use an autoencoder and a variational autoencoder for dimensionality reduction with a subsequently supervised classification. Additionally, we present a deep embedded refined clustering algorithm able to optimize the latent space at the same time that the non-supervised classification task is performed. This novel approach in DNAm supposes a step forward in the SMT detection as suggest the obtained results (acc = 0.9). Additionally, making use of the resulting model, we present a subspace-prototypical-based approach for the prognostic prediction of uncertain malignant potential samples, which is nowadays the hottest open area in SMT detection., This work has received funding from Horizon 2020, the European Union¿s Framework Programme for Research and Innovation, under grant agreement No. 860627 (CLARIFY), the Spanish Ministry of Economy and Competitiveness through project PID2019-105142RB-C21 (AI4SKIN) and SICAP (DPI2016-77869-C2-1-R) and GVA through project PROMETEO/2019/109
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Comparación de los umbrales de fractura biomecánica de los tejidos de la cabeza humana mediante un modelo de elementos finitos

  • Lozano-Mínguez, Estívaliz|||0000-0003-4576-826X
  • Rupérez Moreno, María José|||0000-0001-8457-7963
  • Giner Maravilla, Eugenio|||0000-0003-1903-6495
  • Palomar-Toledano, Marta
[ES] Anualmente se producen un gran número de muertes y discapacidades permanentes a consecuencia de traumatismos craneoencefálicos. Al no poderse realizar ensayos in vivo para conocer los mecanismos de desarrollo de estas lesiones, las simulaciones numéricas son una herramienta clave en el estudio de éstas. La precisión de los modelos numéricos depende en gran medida de la correcta definición de las ecuaciones constitutivas y de los modelos de daño. Sin embargo, en la literatura se encuentra gran dispersión en los modelos empleados, así como en los valores de las propiedades biomecánicas. Por tanto, el objetivo principal de esta investigación era realizar una revisión y comparación de los modelos y las propiedades empleadas en la literatura, mediante un nuevo modelo de elementos finitos (EF) calibrado con ensayos experimentales de cadáveres, para discernir aquellos que proporcionan una respuesta más cercana a los resultados empíricos. Los valores umbral del cráneo y del cuero cabelludo que conducen a la fractura han sido estudiados y seleccionados. Se ha observado que el hueso compacto es crítico en la fractura del cráneo pero que no es el único parámetro que influye en ésta., Los autores agradecen el apoyo financiero recibido del Ministerio de Economía y Competitividad y los Fondos FEDER a través del proyecto RTC-2015-3887-8. También se reconoce el apoyo de la Generalitat Valenciana a través del programa PROMETEO 2016/007
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

An SMT-Based Concolic Testing Tool for Logic Programs

  • Fortz, Sophie
  • Mesnard, Fred
  • Payet, Etienne
  • Perrouin, Gilles
  • Vanhoof, Wim
  • Vidal, Germán|||0000-0002-1857-6951
[EN] Concolic testing combines symbolic and concrete execution to generate test cases that achieve a good program coverage. Its benefits have been demonstrated for more than 15 years in the case of imperative programs. In this work, we present a concolic-based test generation tool for logic programs which exploits SMT-solving for constraint resolution, Third author is a research associate at FNRS that also supports this work (O05518FRG03). The last author is partially supported by the EU (FEDER) and the Spanish MCI/AEI under grants TIN2016-76843-C4-1-R/PID2019-104735RB-C41 and by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Recommending Learning Videos for MOOCs and Flipped Classrooms

  • Jordán, Jaume|||0000-0003-0400-9136
  • Valero Cubas, Soledad|||0000-0003-4565-326X
  • Turró Ribalta, Carlos|||0000-0002-3840-9405
  • Botti V.|||0000-0002-6507-2756
[EN] New teaching approaches are emerging in higher education, such as flipped classrooms. In addition, academic institutions are offering new types of training like Massive Online Open Courses. Both of these new ways of education require high-quality learning objects for their success, with learning videos being the most common to provide theoretical concepts. This paper describes a hybrid learning recommender system based on content-based techniques, which is able to recommend useful videos to learners and teachers from a learning video repository. This hybrid technique has been successfully applied to a real scenario such as the central video repository of the Universitat Politècnica de València., This work was partially supported by MINECO/FEDER RTI2018-095390-B-C31 and TIN2017-89156-R projects of the Spanish government, and PROMETEO/2018/002 project of Generalitat Valenciana. J. Jordán and V. Botti are funded by UPV PAID-06-18 project. J. Jordán is also funded by grant APOSTD/2018/010 of Generalitat Valenciana - Fondo Social Europeo.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Protocol Analysis with Time

  • Aparicio-Sánchez, Damián
  • Meadows, Catherine
  • Meseguer, José
  • Escobar Román, Santiago|||0000-0002-3550-4781
  • Sapiña-Sanchis, Julia|||0000-0003-2994-6986
[EN] We present a framework suited to the analysis of cryptographic protocols that make use of time in their execution. We provide a process algebra syntax that makes time information available to processes, and a transition semantics that takes account of fundamental properties of time. Additional properties can be added by the user if desirable. This timed protocol framework can be implemented either as a simulation tool or as a symbolic analysis tool in which time references are represented by logical variables, and in which the properties of time are implemented as constraints on those time logical variables. These constraints are carried along the symbolic execution of the protocol. The satisfiability of these constraints can be evaluated as the analysis proceeds, so attacks that violate the laws of physics can be rejected as impossible. We demonstrate the feasibility of our approach by using the Maude-NPA protocol analyzer together with an SMT solver that is used to evaluate the satisfiability of timing constraints. We provide a sound and complete protocol transformation from our timed process algebra to the Maude-NPA syntax and semantics, and we prove its soundness and completeness. We then use the tool to analyze Mafia fraud and distance hijacking attacks on a suite of distance-bounding protocols., This paper was partially supported by the EU (FEDER) and the Spanish MCIU under grant RTI2018-094403-B-C32, by the Spanish Generalitat Valenciana under grant PROMETEO/2019/098 and APOSTD/2019/127, by the US Air Force Office of Scientific Research under award number FA9550-17-1-0286, and by ONR Code 311.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Mapping Study about Usability Requirements Elicitation

  • Ormeño Ayala, Yeshica Isela
  • Panach Navarrete, Jose Ignacio
[EN] The HCI community has developed guidelines and recommendations for improving the usability system that are usually applied at the last stages of the software development process. On the other hand, the SE community has developed sound methods to elicit functional requirements in the early stages, but usability has been relegated to the last stages together with other nonfunctional requirements. Therefore, there are no methods of usability requirements elicitation to develop software within both communities. An example of this problem arises if we focus on the Model-Driven Development paradigm, where the methods and tools that are used to develop software do not support usability requirements elicitation. In order to study the existing publications that deal with usability requirements from the first steps of the software development process, this work presents a mapping study. Our aim is to compare usability requirements methods and to identify the strong points of each one, This work has been developed with the support of MICINN (PROS-Req TIN2010-19130-C02-02), UV (UV-INV-PRECOMP12-80627), GVA (ORCA PROMETEO/2009/015), and co-financed with ERDF. We acknowledge the support of the ITEA2 Call 3 UsiXML (20080026) and funding by the MITYC (TSI-020400-2011-20)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Integrating technical debt into MDE

  • Giraldo Velásquez, Faber Danilo
  • España Cubillo, Sergio
  • Pineda, Manuel A.
  • Giraldo, William J.
  • Pastor López, Oscar|||0000-0002-1320-8471
The main goal of this work is to evaluate the feasibility to calculate the technical debt (a traditional software quality approach) in a model-driven context through the same tools used by software deve- lopers at work. The SonarQube tool was used, so that the quality check was performed directly on projects created with Eclipse Modeling Frame- work (EMF) instead of traditionals source code projects. In this work, XML was used as the model speci cation language to verify in Sonar- Qube due to the creation of EMF metamodels in XMI (XML Metadata Interchange) and that SonarQube o ers a plugin to assess the XML lan- guage. After this, our work focused on the de nition of model rules as an XSD schema (XML Schema De nition) and the integration between EMF-SonarQube in order that these metrics were directly validated by SonarQube; and subsequently, this tool determined the technical debt that the analyzed EMF models could contain, F. G, thanks to Colciencias (Colombia) for funding this work through the Colciencias Grant call 512-2010. This work has been supported by the Spanish MICINN PROS-Req (TIN2010-19130-C02-02), the Generalitat Valenciana Project ORCA (PROMETEO/2009/015), the European Commission FP7 Project CaaS (611351), and ERDF structural funds.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Overview of PAN 2021: Authorship Verification, Profiling Hate Speech Spreaders on Twitter, and Style Change Detection.

  • Bevendorff, Janek
  • Chulvi-Ferriols, María Alberta
  • Peña-Sarracén, Gretel Liz de la
  • Kestemont, Mike
  • Manjavacas, Enrique
  • Markov, Ilia
  • Mayerl, Maximilian
  • Potthast, Martin
  • Rangel, Francisco
  • Stamatatos, Efstathios
  • Stein, Benno
  • Wiegmann, Matti
  • Wolska, Magdalena
  • Zangerle, Eva
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The paper gives a brief overview of the three shared tasks to be organized at the PAN 2021 lab on digital text forensics and stylometry hosted at the CLEF conference. The tasks include authorship verification across domains, author profiling for hate speech spreaders, and style change detection for multi-author documents. In part the tasks are new and in part they continue and advance past shared tasks, with the overall goal of advancing the state of the art, providing for an objective evaluation on newly developed benchmark datasets., The work of the researchers from Universitat Politecnica de Valencia was partially funded by the Spanish MICINN under the project MISMISFAKEnHATE on MISinformation and MIScommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31), and by the Generalitat Valenciana under the project DeepPattern (PROMETEO/2019/121).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ReverCSP: Time-Travelling in CSP Computations

  • Galindo, Carlos|||0000-0002-3569-6218
  • Silva, Josep|||0000-0001-5096-0008
  • Nishida, Naoki
  • Tamarit, Salvador
[EN] This paper presents reverCSP, a tool to animate both forward and backward CSP computations. This ability to reverse computations can be done step by step or backtracking to a given desired state of interest. reverCSP allows us to reverse computations exactly in the same order in which they happened, or also in a causally-consistent way. Therefore, reverCSP is a tool that can be especially useful to comprehend, analyze, and debug computations. reverCSP is an open-source project publicly available for the community. We describe the tool and its functionality, and we provide implementation details so that it can be reimplemented for other languages., This work has been partially supported by the EU (FEDER) and the Spanish MCI/AEI under grants TIN2016-76843-C4-1-R and PID2019- 104735RB-C41, and by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Automating Data Integration in Adaptive and Data-Intensive Information Systems

  • Galvão, João
  • Costa, Carlos
  • Santos, Maribel Yasmina
  • León-Palacio, Ana|||0000-0003-3516-8893
  • Pastor López, Oscar|||0000-0002-1320-8471
[EN] Data acquisition is no longer a problem for organizations, as many efforts have been performed in automating data collection and storage, providing access to a wide amount of heterogeneous data sources that can be used to support the decision-making process. Nevertheless, those efforts were not extended to the context of data integration, as many data transformation and integration tasks such as entity and attribute matching remain highly manual. This is not suitable for complex and dynamic contexts where Information Systems must be adaptative enough to mitigate the difficulties derived from the frequent addition and removal of sources. This work proposes a method for the automatic inference of the appropriate data mapping of heterogeneous sources, supporting the data integration process by providing a semantic overview of the data sources, with quantitative measures of the confidence level. The proposed method includes both technical and domain knowledge and has been evaluated through the implementation of a prototype and its application in a particularly dynamic and complex domain where data integration remains an open problem, i.e., genomics., This work has been supported by FCT Fundação para a Ciência e Tecnologia within the Project Scope: UID/CEC/00319/2019, the Doctoral scholarship PD/BDE/135100/2017 and European Structural and Investment Funds in the FEDER component, through the Operational Competitiveness and Internationalization Programme (COMPETE 2020) [Project nº 039479; Funding Reference: POCI-01-0247-FEDER-039479]. We also thank both the Spanish State Research Agency and the Generalitat Valenciana under the projects DataME TIN2016-80811-P, ACIF/2018/171, and PROMETEO/2018/176. Icons made by Freepik, from www.flaticon.com.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Parallel CT Reconstruction for Multiple Slices Studies with SuiteSparseQR Factorization Package

  • CHILLARÓN-PÉREZ, MÓNICA|||0000-0002-7611-8908
  • Vidal-Gimeno, Vicente-Emilio|||0000-0002-2384-7015
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
[EN] Algebraic factorization methods applied to the discipline of Computerized Tomography (CT) Medical Imaging Reconstruction involve a high computational cost. Since these techniques are significantly slower than the traditional analytical ones and time is critical in this field, we need to employ parallel implementations in order to exploit the machine resources and obtain efficient reconstructions. In this paper, we analyze the performance of the sparse QR decomposition implemented on SuiteSparseQR factorization package applied to the CT reconstruction problem. We explore both the parallelism provided by BLAS threads and the use of the Householder reflections to reconstruct multiple slices at once efficiently. Combining both strategies, we can boost the performance of the reconstructions and implement a reliable and competitive method that gets high-quality CT images., This research has been supported by Universitat Politècnica de València, Generalitat Valenciana under PROMETEO/2018/035 co-financed by FEDER funds, as well as ACIF/2017/075 predoctoral grant, and the Spanish Ministry of Economy and Competitiveness under Grant TIN2015-66972-C5-4-R and TIAMHA co-financed by FEDER funds.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Real-time functionalization and biosensing in subwavelength grating bimodal waveguides

  • Torrijos-Morán, Luis
  • Martinez-Perez, Paula
  • García-Rupérez, Jaime|||0000-0002-2036-0084
[EN] In this paper, we present for the first time experimental results of biosensing processes by using subwavelength grating bimodal waveguides as a refractive index sensors. We demonstrate the detection of 10ppm concentration of Bovine Serum Albumin (BSA) with a 190pm wavelength shift after a functionalization of the sensor surface with a layer of protein A/G in a continuous flowing system. Real-time data of each step is obtained, validating these kind of novel and highly sensitive SWG sensors for biosensing purposes., The authors acknowledge the funding from the Generalitat Valencia through project AVANTI/2019/123 and grant ACIF/2019/009.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Computational simulations of the effects of the V17M missense mutation on atrial electrical activity

  • Belletti, Rebecca
  • Martínez Mateu, L.
  • Romero Pérez, Lucia|||0000-0003-4605-8630
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
[EN] Atrial fibrillation is a cardiac arrhythmia responsible for disorganized electrical activity of the upper chambers of the heart. Recently genetic mutations have been associated to episodes of atrial fibrillation in asymptomatic patients, a condition called Lone AF. Indeed, genetic defects in ion channel protein structures can alter the flowing of the current through the pore. The aim of this work is to model and simulate the gain of function missense mutation V17M affecting the accessory subunit KCNE3 of the rapid delayed rectifier potassium channel, Kv11.1, found in a 46-years-old man affected by Lone AF. To accomplish this, the ventricular IKr Markov model proposed by Martin Fink and colleagues has been refitted to reproduce the behavior of the atrial IKr using an optimization procedure. Then, it was introduced into the atrial cellular model developed by Courtemanche Ramirez Nattel (CRN). Additionally, this model has been adjusted to fit experiments in literature in order to accurately reproduce the effects of the V17M mutation. The resulting wild-type IKr formulation mimics the CRN IKr time course at 0.5, 1 and 2 Hz, the activation time constants and the steady-state activation and inactivation curves. In addition, the V17M mutation formulation reproduces the experimentally reported electrophysiological alterations, which are approximately 3-fold increment of the current at high voltages and an almost 2-fold prolongation of the deactivation time constant. Simulation of the V17M mutation at the cellular level showed a 300% increase of the IKr peak, which shortened the action potential duration in 118.30 ms., Generalitat Valenciana, Prometeo programme 2016/088 and grant agreement 766082 European Union's Horizon 2020
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ICFHR2016 Handwritten Keyword Spotting Competition (H-KWS 2016)

  • Pratikakis, Ioannis
  • Zagoris, Konstantinos
  • Gatos, Basilis
  • Puigcerver, Joan
  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
[EN] The H-KWS 2016, organized in the context of the ICFHR 2016 conference aims at setting up an evaluation framework for benchmarking handwritten keyword spotting (KWS) examining both the Query by Example (QbE) and the Query by String (QbS) approaches. Both KWS approaches were hosted into two different tracks, which in turn were split into two distinct challenges, namely, a segmentation-based and a segmentation-free to accommodate different perspectives adopted by researchers in the KWS field. In addition, the competition aims to evaluate the submitted training-based methods under different amounts of training data. Four participants submitted at least one solution to one of the challenges, according to the capabilities and/or restrictions of their systems. The data used in the competition consisted of historical German and English documents with their own characteristics and complexities. This paper presents the details of the competition, including the data, evaluation metrics and results of the best run of each participating methods., This work was partially supported by the Spanish MEC under FPU grant FPU13/06281, by the Generalitat Valenciana under the Prometeo/2009/014 project grant ALMA-MATER, and through the EU projects: HIMANIS (JPICH programme, Spanish grant Ref. PCIN-2015-068) and READ (Horizon-2020 programme, grant Ref. 674943).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Setting up of a radon measurement system from an exhalation simulation device, Puesta a punto de un sistema de medida de radón a partir de un dispositivo de simulación de exhalación

  • Noverques-Medina, Aina|||0000-0002-7810-0381
  • Juste-Vidal, Belen-Jeanne|||0000-0003-1978-3765
  • Sancho, M.|||0000-0002-9566-1949
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
  • Arnal Arnal, José Miguel
  • García-Fayos, Beatriz|||0000-0002-7941-4243
[EN] Radon is a radioactive gas from the uranium decay which is being considered as a carcinogenic element by the World Health Organization (WHO) since 2010. In 2013, it was published the Directive 59/2013/EURATOM which establishes new radon limit values, more restrictive, and action plans against radon in air. Since then, and due to the great concern about radon hazardous, several research centers, as well as laboratories and collaborating entities, are joining their efforts in order to develop different methodologies and protocols that allow the control and mitigation of radon gas, with the aim of reducing its concentration in air, and thus preserving population health. Within this context, this works performs the setting up of a RadonScout detector (SARAD GmbH), portable equipment that lets to know in situ and continuously the concentration of radon in air in any location. Measurements have been taken with experimental equipment designed to keep constant environmental conditions. To check the repeatability of the measurements, the results have been compared with RAD7 (Durridge) detector which has been previously used in several intercomparison and calibration procedures., [ES] El radón es un gas radiactivo procedente de la desintegración del uranio, considerado como un elemento cancerígeno por la Organización Mundial de la Salud (OMS) desde 2010. En 2013, se publicó la Directiva 59/2013/EURATOM que establecía unos nuevos valores límite, más restrictivos, y planes de acción frente al radón en aire. Desde entonces, y dada la gran preocupación por la peligrosidad de este gas, diversos centros de investigación, así como laboratorios y entidades colaboradoras, aúnan sus esfuerzos para disponer de metodologías y protocolos que permitan el control y la mitigación del gas radón, con el fin de disminuir su concentración en el aire, y así preservar la salud de la población. Dentro de este contexto, en este trabajo se realiza la puesta a punto del detector RadonScout (SARAD GmbH), un equipo portátil que permite conocer in situ y en continuo la concentración de radón en aire en cualquier emplazamiento. Las medidas se han llevado a cabo a partir de un equipo experimental diseñado para mantener las diferentes variables ambientales estables. Para comprobar la repetibilidad de las medidas, los resultados han sido comparados con los del detector RAD7 (Durridge), con el que se ha participado en diferentes intercomparaciones y calibraciones., Este trabajo ha sido financiado por el Proyecto Prometeo/2018/035 de la Generalitat Valenciana
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks

  • Álvaro Muñoz, Francisco
  • Benedí Ruiz, José Miguel
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate., This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Optimal Teaching Curricula with Compositional Simplicity Priors

  • García-Piqueras, Manuel
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] Machine teaching under strong simplicity priors can teach any concept in universal languages. Remarkably, recent experiments suggest that the teaching sets are shorter than the concept description itself. This raises many important questions about the complexity of concepts and their teaching size, especially when concepts are taught incrementally. In this paper we put a bound to these surprising experimental findings and reconnect teaching size and concept complexity: complex concepts do require large teaching sets. Also, we analyse teaching curricula, and find a new interposition phenomenon: the teaching size of a concept can increase because examples are captured by simpler concepts built on previously acquired knowledge. We provide a procedure that not only avoids interposition but builds an optimal curriculum. These results indicate novel curriculum design strategies for humans and machines., This work was funded by the EU (FEDER) and Spanish MINECO under RTI2018-094403-B-C32, G. Valenciana under PROMETEO/2019/098 and EU's Horizon 2020 research and innovation programme under grant 952215 (TAILOR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Restauración de Imágenes Médicas con Diferentes Tipos de Ruido

  • Sanchez, Guadalupe
  • Vidal-Gimeno, Vicente-Emilio|||0000-0002-2384-7015
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
  • Mayo, Patricia|||0000-0002-8403-5221
  • Ródenas Escribá, Francisco De Asís|||0000-0003-4564-5171
Las imágenes obtenidas por rayos X o computarizada tomografía computarizada (CT) en condiciones adversas, pueden estar contaminadas con ruido que puede afectar a la detección de enfermedades. Un gran número de técnicas de procesamiento de imágenes han sido propuestas para eliminar el ruido. Estas técnicas dependen del tipo de ruido presente en la imagen. En este trabajo, se propone un método para reducir el ruido gaussiano, impulsivo y speckle. Este filtro, llamado PGMFDNL combina un filtro de difusión no lineal con peer group y fuzzy. El filtro propuesto es capaz de reducir eficazmente el ruido de la imagen sin ningún tipo de información acerca del ruido presente en la imagen. Como resultado, el método propuesto obtiene un buen rendimiento en los diferentes tipos de ruido., Este trabajo fue financiado por el ministerio español de ciencia e innovación: Proyecto TIN2011-26254), ANITRAN PROMETEO/2010/039, Proyecto TIN2008-06570-C04-04, y DGEST ITCG a través del programa PROMEP (México).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

1D Periodic Corrugated Waveguides for Real-Time Detection of Increasing Concentrations of Thrombin

  • Martinez-Perez, Paula
  • Torrijos-Morán, Luis
  • Gómez-Gómez, María Isabel|||0000-0001-7548-209X
  • Ivanova-Angelova, Todora|||0000-0002-8150-4133
  • Griol Barres, Amadeu
  • Hurtado Montañés, Juan|||0000-0002-4870-7641
  • Bellieres, Laurent Christophe
  • García-Rupérez, Jaime|||0000-0002-2036-0084
[EN] An aptasensor based on periodic 1D corrugated waveguides is demonstrated to be suitable for the specific and continuous detection of thrombin at nM concentrations in real time with an estimated detection limit of 33.5 pM., This research was supported by a co-financed action by the European Union through the operational program of the European Regional Development Fund (FEDER) of the Valencian Community 2014-2020, the Generalitat Valenciana through the PROMETEO project AVANTI/2019/123 and the grant ACIF/2019/009, and by Universitat Politècnica de València through grants PAID-01-17 and the project OCUSENSOR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

When AI Difficulty is Easy: The Explanatory Power of Predicting IRT Difficulty

  • Martínez-Plumed, Fernando|||0000-0003-2902-6477
  • C. Monserrat|||0000-0003-1790-8085
  • Hernández-Orallo, José|||0000-0001-9746-7632
  • Castellano, David
[EN] One of challenges of artificial intelligence as a whole is robustness. Many issues such as adversarial examples, out of distribution performance, Clever Hans phenomena, and the wider areas of AI evaluation and explainable AI, have to do with the following question: Did the system fail because it is a hard instance or because something else? In this paper we address this question with a generic method for estimating IRT-based instance difficulty for a wide range of AI domains covering several areas, from supervised feature-based clas- sification to automated reasoning. We show how to estimate difficulty systematically using off-the-shelf machine learning regression models. We illustrate the usefulness of this estima- tion for a range of applications., This work has been partially supported by the EU (FEDER) and Spanish MINECO grant RTI2018-094403-B-C32 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe , Generalitat Valenciana under grant PROMETEO/2019/098, EU s Horizon 2020 research and innovation programme under grant agreement No. 952215 (TAILOR), the Future of Life Institute, FLI, under grant RFP2-152, US DARPA HR00112120007 (RECoG-AI), the AI-Watch and HUMAINT projects by DG CONNECT and DG JRC of the European Commission, and INNEST/2021/317 (Project cofunded by the European Union with the Programa Operativo del Fondo Europeo de Desarrollo Regional (FEDER) de la Comunitat Valenciana 2014-2020).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Variant-based Equational Unification under Constructor Symbols

  • Aparicio-Sánchez, Damián
  • Escobar Román, Santiago|||0000-0002-3550-4781
  • Sapiña-Sanchis, Julia|||0000-0003-2994-6986
[EN] Equational unification of two terms consists of finding a substitution that, when applied to both terms, makes them equal modulo some equational properties. A narrowing-based equational unification algorithm relying on the concept of the variants of a term is available in the most recent version of Maude, version 3.0, which provides quite sophisticated unification features. A variant of a term t is a pair consisting of a substitution sigma and the canonical form of tsigma. Variant-based unification is decidable when the equational theory satisfies the finite variant property. However, this unification procedure does not take into account constructor symbols and, thus, may compute many more unifiers than the necessary or may not be able to stop immediately. In this paper, we integrate the notion of constructor symbol into the variant-based unification algorithm. Our experiments on positive and negative unification problems show an impressive speedup.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ICDAR 2021 competition on mathematical formula detection

  • Anitei, Dan|||0000-0001-8288-6009
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Paredes Palacios, Roberto
  • Fuentes-López, José Manuel
  • Benedí Ruiz, José Miguel
[EN] This paper introduces the Competition on Mathematical Formula Detection that was organized for the ICDAR 2021. The main goal of this competition was to provide the researchers and practitioners a common framework to research on this topic. A large dataset was prepared for this contest where the GT was automatically generated and manually reviewed. Fourteen participants submitted their results for this competition and these results show that there is still room for improvement especially for the detection of embedded mathematical expressions., This work has been partially supported by the Ministerio de Ciencia y Tecnologia under the grant TIN2017-91452-EXP (IBEM) and by the Generalitat Valenciana under the grant PROMETEO/2019/121 (DeepPattern).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Overview of the Track on Author Profiling and Deception Detection in Arabic

  • Rangel, Francisco
  • Charfi, Anis
  • Zaghouani, Wajdi
  • Ghanem, Bilal
  • Sánchez-Junquera, Javier
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This overview presents the Author Profiling and Deception Detection in Arabic (APDA) shared task at PAN@FIRE 2019. Two have been the main aims of this years task: i) to profile the age, gender and native language of a Twitter user; ii) to determine whether an Arabic text is deceptive or not in two different genres: Twitter and news headlines. For this purpose we have created three corpora in Arabic. Altogether, the approaches of 13 participants are evaluated., This publication was made possible by NPRP 9-175-1-033 from the Qatar National Research Fund (a member of Qatar Foundation). The findings achieved herein are solely the responsibility of the authors. The work of Paolo Rosso was also partially funded by Generalitat Valenciana under grant PROMETEO/2019/121.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Influencia de la morfometría y las propiedades aparentes en la integridad estructural del hueso trabecular humano enfermo y sano

  • Megías-Díaz, Raquel|||0000-0002-1698-7108
  • Belda Ricardo|||0000-0003-3913-5773
  • Vercher Martínez, Ana|||0000-0003-3695-6461
  • Giner Maravilla, Eugenio|||0000-0003-1903-6495
[ES] En este trabajo, se han estudiado las relaciones entre la morfometría y la respuesta mecánica de hueso trabecular humano. Las muestras analizadas proceden de cabezas femorales humanas y están divididas en tres grupos: grupo sano (GS), grupo artrósico (GA) y grupo osteoporótico (GO). Las muestras se han escaneado mediante micro-CT para disponer de la geometría y poder realizar el estudio morfométrico de la microarquitectura trabecular. Se han llevado a cabo ensayos de compresión cuasiestática en la dirección más rígida de las muestras hasta producir su fractura. La influencia entre los parámetros se ha estudiado mediante correlaciones lineales por grupos de forma independiente, ya que el comportamiento aparente es tan diferente entre las muestras que las relaciones obtenidas analizando todas las muestras en conjunto no son relevantes y presentan unos coeficientes de correlación muy bajos. El grupo sano (GS) es el que presenta relaciones relevantes (con un p-valor < 0.05) con la densidad de conectividad Conn.D, el número de trabéculas Tb.N, el área superficial de hueso BS y la dimensión fractal D. Además, también se han relacionado los parámetros aparentes obtenidos de los ensayos experimentales entre sí. Para el caso de GS, presenta correlación entre la tensión de fallo final ¿¿ y el módulo de Young aparente ¿¿¿¿. Respecto al grupo osteoporótico, tanto ¿¿ como ¿¿¿¿ presentan correlaciones con la separación trabecular Tb.Sp y el número de trabéculas Tb.N. Además, también presentan correlación ¿¿¿¿ y la deformación asociada a la que se da la tensión de fallo final ¿¿. El grupo artrósico (GA) es el que menos correlaciones presenta, únicamente entre ¿¿ y el volumen total de las muestras TV y entre ¿¿ y ¿¿¿¿. Las correlaciones lineales obtenidas indican que se podría determinar el módulo de Young aparente o la tensión máxima que soportan las muestras sin realizar los ensayos experimentales mediante la evaluación de imágenes micro-CT., Los autores desean agradecer la financiación recibidadesde la GVA por el programa PROMETEO 2021/046, y por los proyectos PID2020-118920RB-I00 y PID2020-118480RB-C21 y C22, financiado por MCIN/AEI/10.13039/5011000110 33 y por FEDER Una manera de hacer Europa y el proyecto PDC2021- 121368-C21 y C22 financiado por MCIN/AEI/10.13039/501100011033 y por la Unión Europea NextGenerationEU/PRTR .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Online learning for interactive statistical machine translation

  • Ortiz-Martínez, Daniel
  • García-Varea, Ismael
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] State-of-the-art Machine Translation (MT) systems are still far from being perfect. An alternative is the so-called Interactive Machine Translation (IMT) framework. In this framework, the knowledge of a human translator is combined with a MT system. The vast majority of the existing work on IMT makes use of the well-known batch learning paradigm. In the batch learning paradigm, the training of the IMT system and the interactive translation process are carried out in separate stages. This paradigm is not able to take advantage of the new knowledge produced by the user of the IMT system. In this paper, we present an application of the online learning paradigm to the IMT framework. In the online learning paradigm, the training and prediction stages are no longer separated. This feature is particularly useful in IMT since it allows the user feedback to be taken into account. The online learning techniques proposed here incrementally update the statistical models involved in the translation process. Empirical results show the great potential of online learning in the IMT framework., Work supported by the EC (FEDER/FSE), the Spanish Government (MEC, MICINN, MITyC, MAEC, ¿Plan E¿, under grants MIPRCV ¿Consolider Ingenio 2010¿ CSD2007-00018, iTrans2 TIN2009-14511, erudito.com TSI-020110-2009-439), the Generalitat Valenciana (grant Prometeo/2009/014), the Univ. Politecnica de Valencia (grant 20091027) and the Spanish JCCM (grant PBI08-0210-7127).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Automatically Proving and Disproving Feasibility Conditions

  • Gutiérrez Gil, Raúl|||0000-0002-3984-2868
  • Lucas Alba, Salvador|||0000-0001-9923-2108
[EN] In the realm of term rewriting, given terms s and t, a reachability condition s>>t is called feasible if there is a substitution O such that O(s) rewrites into O(t) in zero or more steps; otherwise, it is called infeasible. Checking infeasibility of (sequences of) reachability conditions is important in the analysis of computational properties of rewrite systems like confluence or (operational) termination. In this paper, we generalize this notion of feasibility to arbitrary n-ary relations on terms defined by first-order theories. In this way, properties of computational systems whose operational semantics can be given as a first-order theory can be investigated. We introduce a framework for proving feasibility/infeasibility, and a new tool, infChecker, which implements it., Supported by EU (FEDER), and projects RTI2018-094403-B-C32, PROMETEO/2019/098, and SP20180225. Also by INCIBE program "Ayudas para la excelencia de los equipos de investigación avanzada en ciberseguridad" (Raul Gutiérrez).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Influence of Fibrotic Tissue Arrangement on Intracardiac Electrograms During Persistent Atrial Fibrillation

  • Sánchez-Arciniegas, Jorge Patricio
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
  • Trenor Gomis, Beatriz Ana|||0000-0001-9166-6112
  • Nothstein Mark
  • Unger, Laura
  • Dossel, Olaf
  • Loewe, Axel
[EN] Under persistent atrial fibrillation (peAF), cardiac tissue experiences electrophysiological and structural remodeling. Fibrosis in the atrial tissue has an important impact on the myocyte action potential and its propagation. The objective of this work is to explore the effect of heterogeneities present in the fibrotic tissue and their impact on the intracardiac electrogram (EGM). Human atrial myocyte and fibroblast electrophysiology was simulated using mathematical models proposed by Koivumäki et al. to represent electrical remodeling under peAF and the paracrine effect of the transforming grow factor ¿1 (TGF-¿1). 2D tissue simulations were computed varying the density of fibrosis (10%, 20% and 40%), myofibroblasts and collagen were randomly distributed with different ratios (0%-100%, 50%-50% and 100%- 0%). Results show that increasing the fibrosis density changes the re-entry dynamics from functional to anatomical due to a block in conduction in regions with high fibrosis density (40%). EGM morphology was affected by different ratios of myofibroblasts-collagen. For low myofibroblast densities (below 50%) the duration of active segments was shorter compared to higher myofibroblasts densities (above 50%). Our results show that fibrosis heterogeneities can alter the dynamics of the re-entry and the morphology of the EGM., We gratefully acknowledge financial support by Deutsche Forschungsgemeinschaft (DFG) under grant LO 2093/1-1.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Caracterización de lentes multifocales mediante un laboratorio virtual basado en la óptica de Fourier

  • Ferrando, Vicente|||0000-0002-7434-7109
  • Monsoriu Serra, Juan Antonio|||0000-0003-3350-7951
  • Montagud-Martínez, Diego
  • Remón, Laura
  • Furlan, Walter D.
[ES] En este trabajo presentamos un nuevo laboratorio virtual, desarrollado en Python, que permite la caracterización óptica de una serie de lentes multifocales bajo diferentes parámetros de configuración (esfera, cilindro, eje, diámetro de pupila, aberración esférica, ¿) mediante diferentes métricas basadas en la óptica de Fourier, tales como la Función de Transferencia de Modulación (MTF), la Función de Dispersión del Punto (PSF) y la simulación de formación de imágenes de diferentes optotipos., [EN] In this paper we present a new Python developed virtual laboratory that allows the optical characterization of a series of multifocal lenses under different setup parameters (sphere, cylinder, axis, pupil diameter, spherical aberration, ...) by using different metrics based on the Fourier optics, such as the Modulation Transfer Function (MTF), the Point Spread Function (PSF) and the image forming simulation of different optotypes., Este trabajo ha sido financiado por el Ministerio de Ciencia e Innovación de España [PID2019- 107391RB-I00] y por la Generalitat Valenciana (España) [PROMETEO/2019/048]. D. M.-M. también agradece la financiación otorgada por la beca Margarita Salas del Ministerio de Universidades de España financiado por the European Union-Next Generation EU.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Traceability-based Method to Support Conceptual Model Evolution

  • Ruiz Carmona, Luz Marcela
Renewing software systems is one of the most cost-effective ways to protect software investment, which saves time, money and ensures uninter- rupted access to technical support and product upgrades. There are several mo- tivations to promote investment and scientific effort for specifying systems by means of conceptual models and supporting its evolution. As an example, the software engineering community is addressing solutions for supporting model traceability, continuous improvement of business process, organisational reen- gineering, information system maintenance, etc. Model-driven techniques have been developed in order to analyse systems raising the abstraction level of its specification. However, a support for conceptual model evolution by means of model-driven techniques is still needed. This thesis proposes a traceability- based method that involves model-driven capabilities for designing and provid- ing guidelines, techniques, and tools to support conceptual model evolution. The main idea is to support information system analysts in the tasks related to: justify why the conceptual models have evolved, report and specify what ele- ments have evolved, and guide how to carry out evolution in certain predefined organisational contexts. We plan to apply our method to guide the evolution of an E-shopping software. This way, we also provide mechanism to facilitate in- dustrial adoption., This PhD project has been supported by the Spanish Generalitat Valenciana ORCA (PROMETEO/2009/015); the FPI grant of the Universitat Politècnica de València (3146); the European Commission FP7 Project CaaS (611351); and the ERDF structural funds.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Experimental Study of Hierarchical Clustering for Unmixing of Hyperspectral Images

  • Prades Nebot, José|||0000-0003-4489-3704
  • Salazar Afanador, Addisson|||0000-0001-5849-5104
  • Vergara Domínguez, Luís|||0000-0001-6803-4774
  • Safont, Gonzalo
[EN] Estimation of the number of materials that are present in a hyperspectral image is a necessary step in many hyperspectral image processing algorithms, including classification and unmixing. Previously, we presented an algorithm that estimated the number of materials in the image using clustering principles. This algorithm is an iterative approach with two input parameters: the initial number of materials (P0) and the number of materials added in each iteration (¿). Since the choice of P0 and ¿ can have a large impact on the estimation accuracy. In this paper, we made an experimental study of the effect of these parameters on the algorithm performance. Thus, we show that the choice of a large ¿ can significantly reduce the estimation accuracy. These results can help to make an appropriate choice of these two parameters., This research has been supported by Generalitat Valenciana, grant PROMETEO 2019/109.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

High performance photonic biosensors based on periodic configurations

  • García-Rupérez, Jaime|||0000-0002-2036-0084
  • Gómez-Gómez, María Isabel|||0000-0001-7548-209X
  • Ponce-Alcántara, Salvador|||0000-0002-7479-8129
  • Torrijos-Morán, Luis
  • Martinez-Perez, Paula
[EN] Periodic photonic configurations as photonic crystals (PhCs) and subwavelength grating (SWG) waveguides are gaining a renewed interest for the development of biosensing structures. By performing a proper design, these periodic configurations allow a significant sensitivity increase while keeping a compact footprint, what is achieved by exploiting concepts such as the slow-wave effect, the increase of the light-matter overlap or the interference of dispersion engineered modes., These results were achieved thanks to the funding received from the European Union (ICT-644242-SAPHELY, PHC634013-PHOCNOSIS and the operational program of the European Regional Development Fund (FEDER) of the Valencia Regional Government 2014¿2020), the Spanish Government (TEC2015-63838-C3-1-R-OPTONANOSENS and PID2019-106965RB-C21-PHOLOW), the Generalitat Valenciana (AVANTI/2019/123, ACIF/2019/009 and PPC/2020/037), the Universitat Politècnica de València (PAID-01-17, PAID-01-18 and OCUSENSOR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Interactive Machine Translation using Hierarchical Translation Model

  • González-Rubio, Jesús
  • Ortiz-Martínez, Daniel
  • Benedí Ruiz, José Miguel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] Current automatic machine translation systems are not able to generate error-free translations and human intervention is often required to correct their output. Alternatively, an interactive framework that integrates the human knowledge into the translation process has been presented in previous works. Here, we describe a new interactive machine translation approach that is able to work with phrase-based and hierarchical translation models, and integrates error-correction all in a unified statistical framework. In our experiments, our approach outperforms previous interactive translation systems, and achieves estimated effort reductions of as much as 48% relative over a traditional post-edition system., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grans agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Towards Designing Conceptual Data Models for Big Data Warehouses: The Genomics Case

  • Galvão, João
  • Costa, Carlos
  • Santos, Maribel Yasmina
  • León-Palacio, Ana|||0000-0003-3516-8893
  • Pastor López, Oscar|||0000-0002-1320-8471
[EN] Data Warehousing applied in Big Data contexts has been an emergent topic of research, as traditional Data Warehousing technologies are unable to deal with Big Data characteristics and challenges. The methods used in this field are already well systematized and adopted by practitioners, while research in Big Data Warehousing is only starting to provide some guidance on how to model such complex systems. This work contributes to the process of designing conceptual data models for Big Data Warehouses proposing a method based on rules and design patterns, which aims to gather the information of a certain application domain mapped in a relational conceptual model. A complex domain that can benefit from this work is Genomics, characterized by an increasing heterogeneity, both in terms of content and data structure. Moreover, the challenges for collecting and analyzing genome data under a unified perspective have become a bottleneck for the scientific community, reason why standardized analytical repositories such as a Big Genome Warehouse can be of high value to the community. In the demonstration case presented here, a genomics relational model is merged with the proposed Big Data Warehouse Conceptual Metamodel to obtain the Big Genome Warehouse Conceptual Model, showing that the design rules and patterns can be applied having a relational conceptual model as starting point., This work has been supported by FCT - Fundação para a Ciên-cia e Tecnologia within the Project Scope: UID/CEC/00319/2019, the Doctoral scholarship PD/BDE/135100/2017 and European Structural and Investment Funds in the FEDER component, through the Operational Competitiveness and Internationalization Programme (COMPETE 2020) [Project nº 039479; Funding Reference: POCI-01-0247-FEDER-039479]. We also thank both the Spanish State Research Agency and the Generalitat Valenciana under the projects DataME TIN2016-80811-P, ACIF/2018/171, and PROMETEO/2018/176. Icons made by Freepik, from www.flaticon.com.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Estudio de estabilidad de técnicas de filtrado en imágenes de la base de datos mini-MIAS

  • PARCERO IGLESIAS, ESTIBALIZ|||0000-0002-5155-2900
  • Vidal-Gimeno, Vicente-Emilio|||0000-0002-2384-7015
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
  • Mayo, Patricia|||0000-0002-8403-5221
Durante los últimos años se han realizado una gran cantidad de estudios a fin de establecer filtros de calidad que reconstruyan imágenes con todo tipo de ruido (impulsivo, gausiano o speckle). Esto es especialmente importante en el área de la imagen médica, donde un diagnóstico puede depender de la calidad de dicha imagen. En estudios anteriores se ha comprobado la eficacia de filtros fuzzy en una imagen mamográfica de la base de datos mini-MIAS. La base de datos mini-MIAS consiste en una colección normalizada de 322 imágenes de mamografías (en blanco y negro), 161 derechas y 161 izquierdas. Cada una de las imágenes está clasificada según el tipo de tejido dominante (graso, graso-glandular o glandular denso) y el diagnóstico: a) calcificación, b) masa bien definida o circunscrita, c) masa espigada, d) otras, masas mal definidas, e) distorsión estructural, f) asimetría, o g) normal. Ahora bien, se desconoce si existe una correlación entre el tipo de mama, o el diagnóstico y la eficacia del filtro aplicado. El objetivo del presente estudio es establecer si existe o no dicha relación, y si es así, cuantificarla. Para ello, se realizará una reconstrucción de cada una de las imágenes de la base de datos a la que habremos introducido ruido. Para cuantificar la eficacia de la reconstrucción se tomarán las medidas MSE, MAE y PSNR para cada una de las reconstrucciones y se compararán los resultados., Este trabajo ha sido parcialmente financiado por el proyecto ANITRAN PROMETEO/2010/039 de la Generalitat Valenciana, por el proyecto del Ministerio de Ciencia e Innovación (TIN2008-06570-C04-04) y por la spin-off Titania (Grupo Dominguis).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Proving Operational Termination of Declarative Programs in General Logics

  • Lucas Alba, Salvador|||0000-0001-9923-2108
  • Meseguer, José
A declarative program P is a *theory* in a given computational logic L, so that *computation* with such a program is efficiently implemented as *deduction* in L. That is why *inference systems* are crucial: they both (i) *define* the logical semantics of a language in its underlying logic L, and (ii) *specify* the *execution* of programs in a correct implementation. The notion of *operational termination* (OT) of a declarative program P identifies termination with *absence of infinite inference* with P. We further develop the OT notion for declarative programs in general logics with schematic inference systems and characterize OT in terms of *chains of proof jumps*. We also generalize the dependency pair framework to an arbitrary schematic logic L, so that methods for proving declarative programs OT become available for a very wide range of declarative languages. We illustrate the usefulness of the general OT methods we propose by three case studies in three logics: that of Conditional Term Rewriting Systems, the Typed Lambda Calculus, and Membership Rewriting Logic. In particular, we show how various programs that could not be proved terminating with existing methods can be proved OT with the methods presented here., Partially supported by NSF grant CNS 13-19109. Salvador Lucas’ research was developed during a sabbatical year at the UIUC and was also supported by the EU (FEDER), Spanish MINECO projects TIN2010-21062-C02-02 and TIN 2013-45732-C4-1-P, and GV grant BEST/2014/026 and project PROMETEO/2011/052.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ELiRF-UPV at TASS 2020: TWilBERT for Sentiment Analysis and Emotion Detection in Spanish Tweets

  • González-Barba, José Ángel
  • Arias-Moncho, José
  • Pla Santamaría, Ferran
  • Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
[EN] This paper describes the participation of the ELiRF research group of the Universitat Politècnica de València in the TASS 2020 Workshop, framed within the XXXVI edition of the International Conference of the Spanish Society for the Processing of Natural Language (SEPLN). We present the approach used for the Monolingual Sentiment Analysis and Emotion Detection tasks of the workshop, as well as the results obtained. Our participation has focused mainly on employing an adaptation of BERT for text classification on the Twitter domain and the Spanish language. This system, that we have called TWilBERT, shown systematic improvements of the state of the art in almost all the tasks framed in the SEPLN conference of previous years, and also obtains the most competitive performance in the tasks addressed in this work., This work has been partially supported by the Spanish MINECO and FEDER founds under project AMIC (TIN2017-85854-C4-2-R) and by the GiSPRO project (PROMETEU/2018/176). Work of José-Ángel González is financed by Universitat Politècnica de València under grant PAID-01-17.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Mean ergodic operators and reflexive Fréchet lattices

  • Bonet Solves, José Antonio|||0000-0002-9096-6380
  • de Pagter, Ben
  • Ricker, Werner Joseph
Connections between (positive) mean ergodic operators acting in Banach lattices and properties of the underlying lattice itself are well understood (see the works of Emel'yanov, Wolff and Zaharopol). For Frechet lattices (or more general locally convex solid Riesz spaces) there is virtually no information available. For a Frechet lattice E, it is shown here that (amongst other things) every power-bounded linear operator on E is mean ergodic if and only if E is reflexive if and only if E. is Dedekind sigma-complete and every positive power-bounded operator on E is mean ergodic if and only if every positive power-bounded operator in the strong dual E'(beta) (no longer a Frechet lattice) is mean ergodic. An important technique is to develop criteria that detect when E admits a (positively) complemented lattice copy of c(0) l(1) or l(infinity). © Copyright © Royal Society of Edinburgh 2011., J.B. was partly supported by MEC and FEDER Project MTM 2007-62643, GV Project Prometeo 2008/101 and the net MTM 2007-30904-E (Spain). B.D.P. gratefully acknowledges the support of the Alexander von Humboldt Foundation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

infChecker. A Tool for Checking Infeasibility

  • Gutiérrez Gil, Raúl|||0000-0002-3984-2868
  • Lucas Alba, Salvador|||0000-0001-9923-2108
[EN] Given a Conditional Term Rewriting System (CTRS) R and terms s and t, we say that the reachability condition s ->* t is *feasible* if there is a substitution \sigma instantiating the variables in s and t such that the *reachability test* \sigma(s)->* \sigma(t) succeeds; otherwise, we call it *infeasible*. Checking infeasibility of such (sequences of) reachability conditions is important in the analysis of computational properties of CTRSs, like confluence or operational termination. Recently, a logic-based approach to prove and disprove infeasibility has been introduced. In this paper we present infChecker, a new tool for checking infeasibility which is based on such an approach., Partially supported by the EU (FEDER), and projects RTI2018-094403-B-C32, PROMETEO/2019/098, and SP20180225. Raul Gutierrez was also supported by INCIBE program Ayudas para la excelencia de los equipos de investigacion avanzada en ciberseguridad.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

MU-TERM: Verify Termination Properties Automatically (System Description)

  • Gutiérrez Gil, Raúl|||0000-0002-3984-2868
  • Lucas Alba, Salvador|||0000-0001-9923-2108
[EN] We report on the new version of mu-term, a tool for proving termination properties of variants of rewrite systems, including conditional, context-sensitive, equational, and order-sorted rewrite systems. We follow a unified logic-based approach to describe rewriting computations. The automatic generation of logical models for suitable first-order theories and formulas provide a common basis to implement the proofs., Supported by EU (FEDER), and projects RTI2018-094403-B-C32,PROMETEO/ 2019/098, and SP20180225. Also by INCIBE program "Ayudas para la excelencia de los equipos de investigación avanzada en ciberseguridad" (Raul Gutiérrez).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Sub-cm Temperature Monitoring of 500 Weak Gratings Array Through Chirped Ultra-Short Light Pulses

  • Sartiano, Demetrio
  • Madrigal-Madrigal, Javier|||0000-0003-3156-1321
  • Sales Maicas, Salvador|||0000-0001-9457-976X
[EN] We developed a temperature quasi-distributed sensing system interrogating a 500 weak fiber Bragg gratings (FBGs) array of 5 meters. It was possible to sense temperature changes down to 1°C with sub-centimeter spatial resolution., This research was supported by FINESSE project, funded by the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska -Curie Action grant agreement n° 722509. It was also supported by the Ministry of Economy and Competitiveness project DIMENSION TEC2017 and by the Generalitat Valenciana project PROMETEO 2017/017.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

RoMa at HAHA-2021: Deep Reinforcement Learning to Improve a Transformed-based Model for Humor Detection

  • Rodriguez, Mariano
  • Ortega-Bueno, Reynier
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this paper, we describe our system we participated in the shared task ¿Humor Analysis based on Human Annotation (HAHA) at IberLEF-2021 with. Our system relies on data representations learned through fine-tuned neural language models. The representations are used to train a Siamese Neural Network (SNN) which learns to verify whether or not a pair of tweets belong to the same or distinct classes. A key point in our model is the heuristic used to create the pair of messages in the training and test phases. For that, we used a Deep Reinforcement Learning (DRL) strategy that aims at identifying a set of optimal prototypes in each class. In general, the results achieved are encouraging and give us a starting point for further improvements., The work of the second and third authors was in the framework of the research project MISMIS-FAKEnHATE on MISinformation and MIScommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31), funded by Spanish Ministry of Science and Innovation, and DeepPattern (PROMETEO/2019/121), funded by the Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Aplicación para usuarios intolerantes a la fructosa

  • Gimeno Tébar, M.
  • Ortigosa, Nuria|||0000-0002-5272-7661
[EN] La intolerancia a la fructosa, a diferencia de la intolerancia a lactosa o al gluten, no dispone del etiquetado adecuado y específico en los productos comerciales. Por ello, el presente trabajo pretende solventar este problema mediante el desarrollo de una aplicación capaz de, analizando una fotografía de los ingredientes de un producto, indicar si el mismo es adecuado o no para los diferentes niveles de intolerancia a fructosa. Por otra parte, también incluirá un listado de alimentos ordenados por cantidad de fructosa por cada 100 gramos de alimento en el que el usuario pueda buscar directamente un producto (natural o procesado) y comprobar si su composición hace que sea adecuado para la intolerancia a la fructosa o no, indicándose mediante un código de colores tipo semáforo. La aplicación final es capaz de proporcionar una ayuda a usuarios que padezcan este tipo de intolerancia alimentaria, facilitándoles el reconocimiento de aquellos productos que contengan fructosa en alguno de sus ingredientes o edulcorantes, y funcionando con todo tipo de productos, incluso aquellos nuevos que se lancen al mercado., N. Ortigosa agradece el apoyo de la Generalitat Valenciana con el proyecto Prometeo/2017/102 y del MINECO con el proyecto MTM2016-76647-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Exotic nanophotonics with subwavelength high-index disks

  • Díaz-Escobar, Evelyn
  • Pinilla-Cienfuegos, Elena|||0000-0002-3734-0821
  • Mercadé, Laura|||0000-0002-4994-7727
  • Griol Barres, Amadeu
  • Martínez, Alejandro|||0000-0001-5448-0140
  • Barreda, Ángela I.
[EN] High-index dielectric disks with subwavelength dimensions seem relatively simple electromagnetic structures. However, they can give rise to exotic phenomena in nanophotonics. Here we show recent findings that show that high-index disks can be used to manipulate light in subwavelength dimensions as a result of Mie and Fabry-Perot resonances. We also propose that such disks can be used for new applications in photonic integrated circuits (PICs) using silicon technology., A. M. acknowledges funding from Generalitat Valenciana (BEST/2020/178, IDIFEDER/2018/033, PPC/2018/002, PROMETEO/2019/123, IDIFEDER/2020/041); Ministerio de Ciencia e Innovación (PGC2018-094490-B-C21, ICTS-2017- 28-UPV-9); European Commission, H2020 Future and Emerging Technologies (713450, 829067).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Comparación de los resultados de quemado para reactores BWR con CASMO y SCALE 6.2 (TRITON/NEWT), Secciones eficaces obtenidas de un modelado BWR con el código de quemado SCALE 6.2 y comparación con CASMO

  • Mesado Melia, Carles
  • Soler, A.
  • Concejal, A.
  • Miró Herrero, Rafael|||0000-0003-1012-0869
  • Barrachina, Teresa|||0000-0001-8794-4204
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
En este trabajo se comparan los resultados a partir de dos códigos de quemado CASMO y SCALE 6.2 (TRITON). Para ello, se simulan todos los segmentos correspondientes a un reactor de agua en ebullición (BWR) usando ambos códigos. Además, para tener en cuenta los diferentes puntos de trabajo, se repiten las simulaciones variando las variables instantáneas, estas son: fracción de huecos (6 puntos), temperatura del fuel (6 puntos) y barras de control (dos puntos), con un total de 72 posibles combinaciones de variables instantáneas distintas para cada segmento. Una vez todas las simulaciones para cada segmento han finalizado, se puede reordenar las secciones eficaces obtenidas, tanto de CASMO como SCALE, para crear una librería de composiciones en formato nemtab. Dicho formato es aceptado por el código neutrónico de difusión nodal PARCS v2.7. Finalmente se puede comparar los resultados obtenidos con PARCS y con la metodología SIMULATE3/SIMTAB a nivel del reactor completo. Por último, se ha hecho uso de los módulos KENOVI y MCDANCOFF pertenecientes a SCALE. El primero de ellos es un código Monte Carlo de transporte con el que se puede validar el valor del factor de multiplicación, el segundo se ha usado para obtener valores del factor Dancoff y aumentar la precisión del modelo de SCALE., Este trabajo ha sido parcialmente financiado por el Ministerio Español de Ciencia e Innovación mediante el proyecto ENE2011-22823, la Generalitat Valenciana mediante el proyecto PROMETEO/2010/039 y ACOMP/2013/237, y la Universitat Politècnica de València mediante el proyecto UPPTE/2012/118.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Distance and Similarity Measurements of P Waves Before and After Pulmonary Vein Isolation in Patients with Atrial Fibrillation

  • Ortigosa, Nuria|||0000-0002-5272-7661
  • Cano, Óscar
  • Mainardi, Luca
[EN] This study aimed to assess electric markers obtained from the surface electrocardiogram in order to analyse significant differences before and after pulmonary vein isolation in patients who suffered from paroxysmal atrial fibrillation. 30 patients who underwent catheter ablation (in order to permanently restore sinus rhythm and stop atrial fibrillation episodes) were included in the study. Both surface electrocardiogram and intracavitary recordings were simultaneously acquired starting some minutes before catheter ablation began until the whole procedure successfully ended. P-waves have been delineated on V1 lead, and measurements of distances and similarities between them have been obtained to compare the recordings. It has been found that distances between Pwaves significatively decrease (about 14%) whereas similarities significatively increase (about 3%) after catheter ablation. The use of these features would help to identify the success of the catheter ablation procedure, which is the main objective of this preliminary study: the non-invasive identification of spontaneous reconnection of pulmonary veins, the main cause of the arrhythmia recurrences., N. Ortigosa acknowledges the support from Generalitat Valenciana under grant Prometeo/2017/102; from Spanish Ministerio de Educacion, Cultura y Deporte en el marco del Programa Estatal de Promocion del Talento y su Empleabilidad en I+D+i -Subprograma Estatal de Movilidad- under grant Jose Castillejo CAS18/00396; from Spanish MINECO under grant MTM2016-76647-P, and from VLC-BIOMED 2017 (Universitat de Valencia and Hospital La Fe / IIS La Fe) under grant 10-ARVEAP-GALBIS-CANO2017-A.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A novel ICT tool to prevent bullying in schools

  • González, C.
  • Monfort, G.
  • Molines, S.
  • Soto, M.D.
  • Díaz, S.
  • Alberola Oltra, Juan Miguel|||0000-0002-5486-5638
  • Sanchez-Anguix, Víctor|||0000-0003-4851-0037
[EN] In the last few years, bullying and has emerged as one of the main issues to be addressed by the Educational community. The problem of bullying in primary and secondary schools is particularly important, as students are in a sensitive age and consequences may negatively affect their adult lives too. This problem has become an active are for researchers of different disciplines. Specifically, different studies have focused this problem by means of ICT tools in order to fight against bullying in schools. According to this, in the literature we can find a wide range of ICT-based tools such as e-learning systems, intelligent tutoring systems, gamified applications, analytics, or even artificial intelligence have been proposed as technological assets against bullying. Most of these proposals focus on bullying prevention by means of educational applications. However, there is a need of ICT tools that support teachers and other educational staff in the fight against bullying, both at the detection and mitigation stage. In this paper, we propose a novel ICT tool focused on bullying mitigation and detection. This tool is currently composed by two different components. One the one hand, this tool integrates several validated tests in order to determine the potential risk of an individual for becoming a victim or a bully. On the other hand, it also provides a notification mechanism for anonymously reporting situations related to bullying. By considering both components, the tool is able to determine those actions that should be considered by teachers and educational staff in order to mitigate potential problems and prevent future situations related to bullying., This work has been partially funded by the Generalitat Valenciana (GV/2019/012).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Enhanced Pockels effect in strained silicon by means of a SiGe/Si/SiGe slot structure

  • Olivares-Sánchez-Mellado, Irene
  • Sanchis Kilders, Pablo|||0000-0003-2984-4218
[EN] A slot waveguide structure made of a SiGe/Si/SiGe heterojunction is proposed to enhance Pockels effect in strained silicon. The strain is applied via lattice mismatch between layers, while the slot configuration optimizes the overlap between the optical and electric field inside the strained silicon., Funding from projects TEC2016-76849 (MINECO/FEDER, UE) and PROMETEO/2019/123 (Generalitat Valenciana) is acknowledged. Irene Olivares acknowledges the UPV for funding her research staff training (FPI) grant.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ICT tools for tackling bullying in schools: an analysis and opportunities

  • Alberola Oltra, Juan Miguel|||0000-0002-5486-5638
  • Sanchez-Anguix, Víctor|||0000-0003-4851-0037
  • Soto-González, María D.
  • Molines Borrás, Sandra
  • Monfort Torres, Gonzalo
  • Díaz Novillo, Susana
[EN] Bullying is defined as the act of repeatedly and intentionally causing harm to another person who feels helpless (i.e., the victim) against the perpetrator or group of perpetrators. These series of acts of physical and/or psychological violence have been reported to cause a negative impact on the victim on several aspects of his/her well-being and daily life. Recently, multidisciplinary research teams have noticed the potential of ICT tools as catalysts for fighting bullying in schools. A range of ICT-based tools such as elearning systems, intelligent tutoring systems, gamified applications, analytics, or even artificial intelligence have been proposed as technological assets against bullying. In this paper, we identify, categorize, and analyse the use of these ICT tools against bullying under a wide range of criteria such as their role (e.g., prevention, mitigation, detection, etc.), the potential investment that is required, the target age of users, and strengths and weaknesses of each tool. Then, we discuss on potential areas of expansion for the use of ICT tools in the fight bullying, and we identify new potential areas of research., This work has been partially funded by the Generalitat Valenciana (GV/2019/012).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Reduced Myofilament Contraction in Human Heart Failure. Insights From Electromechanical Simulations

  • Mora-Fenoll, María Teresa|||0000-0002-8069-2486
  • Trenor Gomis, Beatriz Ana|||0000-0001-9166-6112
  • Gutiérrez, Sofía
  • Dasi, Albert
  • Gómez García, Juan Francisco
[EN] Intracellular Ca2+ is the main activator of myofilament contraction and the altered Ca2+ handling observed in failing cells has been established as the leading cause of reduced inotropy in heart failure. Electrophysiological studies usually quantify Ca2+ transients to estimate contractile effects. However, heart failure remodeling of myofilaments also occurs, modifying the correlation between Ca2+ and force. The aim of this study was to analyze myofilament tension generated by action potentials in human heart failure. In a ventricular electromechanical model we investigated cellular contraction force associated with intracellular Ca2+ in heart failure by implementing the characteristic electrophysiological, beta-adrenergic, and mechanical changes. Despite the inotropic myofilament remodeling induced by heartfailure, the maximal active tension in failing cells was one third of the force generated in normal cells. With isoproterenol, beta-adrenergic stimulation increased systolic Ca2+, which enhanced myofilament tension by up to 150%, but failing cells also showed a smaller contraction force compared to normal. We observed that contractility was very sensitive to changes in intracellular Ca2+, confirming that increasing Ca2+ peak would improve contraction in heart failure., This work was partially supported by the "Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020" from the Ministerio de Ciencia e Innovación y Universidades (PID2019-104356RB-C41/AEI/10.13039/501100011033) and by the Dirección general de PolíticaCientífica de la Generalitat Valenciana (PROMETEO/2020/043). MTM is being funded by "Programa de Ayudas de Investigación y Desarrollo (PAID-01-17)" from the Universitat Politècnica de València
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Exploring AI Safety in Degrees: Generality, Capability and Control

  • Burden, John
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] The landscape of AI safety is frequently explored differently by contrasting specialised AI versus general AI (or AGI), by analysing the short-term hazards of systems with limited capabilities against those more long-term risks posed by `superintelligence¿, and by conceptualising sophisticated ways of bounding control an AI system has over its environment and itself (impact, harm to humans, self-harm, containment, etc.). In this position paper we reconsider these three aspects of AI safety as quantitative factors ¿generality, capability and control¿, suggesting that by defining metrics for these dimensions, AI risks can be characterised and analysed more precisely. As an example, we illustrate how to define these metrics and their values for some simple agents in a toy scenario within a reinforcement learning setting., We thank the anonymous reviewers for their comments. This work was funded by the Future of Life Institute, FLI, under grant RFP2-152, and also supported by the EU (FEDER) and Spanish MINECO under RTI2018-094403-B-C32, and Generalitat Valenciana under PROMETEO/2019/098.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Low Complexity Near-ML Sphere Decoding based on a MMSE ordering for Generalized Spatial Modulation

  • Simarro, M. Angeles|||0000-0001-6238-2532
  • García Mollá, Víctor Manuel|||0000-0003-4768-7367
  • Martínez Zaldívar, Francisco José|||0000-0002-7845-6273
  • Gonzalez, Alberto|||0000-0002-6984-3212
[EN] Generalized Spatial Modulation (GSM) is a trans-mission technique used in wireless communications in which only part of the transmitter antennas are activated during each time signaling period. A low complexity Sphere Decoding (SD) algorithm to achieve maximum likelihood (ML) detection has recently been proposed by using subproblem partitions, sorting preprocessing and radius updating. However, the ordering method has a serious limitation when the number of activated antennas is equal to the number of received antennas. Therefore, alternative sorting methods are studied in the present paper. In addition, the computational cost of the ML algorithm can be high when the system sizes increases. In this paper a suboptimal version is proposed where only the first L SD subproblems are carried out. The results show that the proposed algorithm achieves near optimal performance at lower computational cost than ML algorithms., This work has been partially supported by Spanish Ministry of Science, Innovation and Universities and by European Union through grant RTI2018-098085- BC41 (MCUI/AEI/FEDER), by GVA through PROMETEO/2019/109 and by Catedra Telefonica-UPV through SSENCE project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Pulmonary Vein Isolation Induces Changes in Vectorcardiogram P-wave Loops

  • Ortigosa, Nuria|||0000-0002-5272-7661
  • Cano, Óscar
  • Sandberg, Frida
[EN] Pulmonary vein isolation (PVI) is considered a standard treatment of paroxysmal atrial fibrillation aiming to restore and maintain sinus rhythm. The purpose of this study is to analyse how the PVI treatment affects the electrical conduction pattern in the atria. We have compared the morphology of P wave loops extracted from the vectorcardiogram (VCG) before and after PVI. Ten patients suffering from paroxysmal atrial fibrillation who underwent PVI were included in the study. All patients were in sinus rhythm before as well as after the procedure. Vectorcardiogram was obtained using the Kors matrix and the resulting P-waves were automatically delineated. Using these marks, P-wave loops were constructed from the three orthogonal leads of the VCG. The first and second eigenvalues of the P-wave loops increased after the PVI procedure was completed, whereas the ratio of the second to the first eigenvalue, quantifying the roundness of the Pwave loop, decreased significantly after PVI. These results show that PVI induces morphological changes of the Pwave loops., N. Ortigosa acknowledges the support from Spanish Ministerio de Ciencia, Innovacion y Universidades en el marco del Programa Estatal de Promocion del Talento y su Empleabilidad en I+D+i -Subprograma Estatal de Movilidad- under grant CAS19/00168; from Generalitat Valenciana under grant Prometeo/2017/102, and from Spanish MINECO under grant MTM2016-76647-P. F.Sandberg acknowledges the support from The Swedish Research Council (VR2019-04272).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Changes in QRS and T-wave Loops Subsequent to an Increase in Left Ventricle Globularity as in Intrauterine Growth Restriction: a Simulation Study

  • Bueno-Palomeque, Freddy L
  • Mountris, Konstantinos A
  • Mincholé, Ana
  • Bailón, Raquel
  • Pueyo, Esther
  • Laguna, Pablo
  • Ortigosa, Nuria|||0000-0002-5272-7661
[EN] Cardiovascular remodeling induced by intrauterine growth restriction manifests in adulthood by more globular ventricles, as evidenced by in vivo measurements. The angle between the dominant vectors of the QRS and T-wave loops has been reported to be significantly altered as a result of the induced remodeling. To investigate whether the more globular ventricular shape was a major factor contributing to such alteration, we performed electrophysiological simulations in a human biventricular model for control and in a model obtained by deforming the control one to represent a more spherical left ventricle (SLV). Transmural ventricular heterogeneities and a Purkinje network were included. 12-lead ECGs were calculated, from which spatial QRS and T-wave angles were computed. The angle between the T-wave and the XZ-plane was found to increase in the SLV model, showing a variation similar to that reported in in vivo studies. However, the angle between the dominant vectors of the QRS and T-wave loops projected onto the XY-plane was lower for control, contrary to clinical observations in IUGR adults. Other clinical results could not be reproduced in our simulations either. Our findings suggest that a more globular left ventricular shape leads to changes in the angles of QRS and T-wave loops, but further research is needed to fully understand these changes and the underlying mechanisms, I would like to acknowledge support by Fundaci ' on Carolina, Universidad de Zaragoza and Universidad Polit ' ecnica Salesiana through its doctoral scholar-ship. This work was supported by projects ERC-StG 638284 (ERC), PID2019-105674RB-I00 and PID2019104881RB-I00 (MICINN) and LMP124-18 and reference group T39-20R (Arag ' on Government cofunded by FEDER 2014-2020 "Building Europe from Aragon"). Computations were performed using ICTS NANBIOSIS (HPC unit at U. Zaragoza). N. Ortigosa acknowledges support from Generalitat Valenciana under grant Prometeo/2017/102 and Spanish MINECO under grant MTM2016-76647-P
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Modelo integral de interacción vehículo-vía que contempla la dinámica de baja y alta frecuencia para circulación en vía recta, transición y curva

  • Martínez Casas, José|||0000-0001-5706-4951
  • Carballeira, Javier|||0000-0002-4179-8499
  • F. D. Denia|||0000-0003-4536-8610
  • Baeza González, Luis Miguel|||0000-0002-3815-8706
[ES] Actualmente hay un elevado interés en analizar ciertos fenómenos ferroviarios que surgen de la interacción dinámica vehículo-vía cuando se negocia una curva, como son el ruido de rodadura, los chirridos y la corrugación de los carriles en curva. En la literatura se detallan, por un lado, modelos de baja frecuencia (hasta 20 Hz) que formulan la dinámica de todo el vehículo completo, y por otro lado, modelos de interacción de alta frecuencia que describen la dinámica de las masas no suspendidas. Sin embargo, para estudiar con precisión los fenómenos citados anteriormente, no sólo debe incluirse la dinámica de alta frecuencia asociada a la flexibilidad de las masas no suspendidas, sino que también deben adoptarse las hipótesis más avanzadas de los modelos de baja frecuencia, fundamentalmente en lo que respecta a la geometría del contacto y a la dinámica del vehículo completo. El presente trabajo pretende ser una contribución para resolver los problemas anteriormente indicados a través del modelado de la interacción dinámica vehículo-vía en curva. Para ello, el modelo contempla tanto la dinámica de alta frecuencia asociada a la flexibilidad de los ejes montados y la vía como la componente de baja frecuencia referente a las masas suspendidas, considerando que el vehículo circula por vía recta, transición y curva. Se llevan a cabo simulaciones con el modelo de interacción vehículo-vía propuesto para diferentes condiciones de circulación en curva y diferentes casos propuestos en el Benchmark de Manchester. Finalmente, los resultados se presentan, discuten y comparan con programas comerciales basados en dinámica de sistemas multicuerpo., Los autores desean agradecer el apoyo recibido del Ministerio de Economía y Competitividad y del Fondo Europeo de Desarrollo Regional mediante el proyecto TRA2013-45596-C2-1-R, así como a la Generalitat Valenciana mediante los proyectos Prometeo/2016/007 y GV/2016/011 de la Conselleria d'Educació, Investigació, Cultura i Esport.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Estudio de la fractura a compresión de hueso trabecular sano, osteoporótico y artrósico procedente de cabezas femorales humanas

  • Megías-Díaz, Raquel|||0000-0002-1698-7108
  • Belda Ricardo|||0000-0003-3913-5773
  • Vercher Martínez, Ana|||0000-0003-3695-6461
  • Giner Maravilla, Eugenio|||0000-0003-1903-6495
[ES] En este trabajo se ha estudiado el comportamiento mecánico del hueso trabecular mediante ensayos experimentales de compresión y el desarrollo de modelos numéricos de elementos finitos. Las muestras proceden de cabezas femorales humanas y se agruparon en tres cohortes: grupo sano (GS), grupo osteoporótico (GO) y grupo artrósico (GA). Los especímenes se ensayaron en la dirección estimada de máxima rigidez y se sometieron a cargas de compresión cuasiestática hasta la fractura. La respuesta experimental permitió calibrar los modelos numéricos, estimando el módulo de Young del tejido óseo y las propiedades de fallo de las muestras. Los resultados muestran que el hueso sano soporta un 52% más de carga que el hueso osteoporótico, y que la deformación correspondiente a la tensión máxima es un 33% mayor en el GS que en el GO. Las muestras artrósicas presentan un comportamiento intermedio, más próximo al grupo osteoporótico que al sano, lo que indica que las patologías analizadas se asocian a menores niveles de carga y deformación frente al hueso sano. La calibración de los modelos numéricos proporciona valores similares de deformación de inicio de fallo y de fallo completo para las muestras patológicas, mientras que en las muestras sanas estos valores difieren. En consecuencia, la simulación de la fractura en hueso osteoporótico requiere considerar propiedades de fallo específicas, coherentes con un comportamiento más frágil que el del hueso sano. Finalmente, este trabajo permite cuantificar dichos parámetros e identifica como principal origen de las diferencias las características morfométricas propias de la microestructura del hueso trabecular no sano., Los autores desean agradecer la financiación recibida desde la GVA por el Plan FDEGENT 2018 GVA y por el programa PROMETEO 2021/046, y por los proyectos PID2020-118920RB-I00 y PID2020-118480RB-C21 y C22, financiado por MCIN/AEI/10.13039/501100011033 y por FEDER Una manera de hacer Europa y el proyecto PDC2021-121368-C21 y C22 financiado por MCIN/AEI/10.13039/501100011033 y por la Unión Europea NextGenerationEU/PRTR .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks

  • Iranzo-Sánchez, Javier
  • Pérez-González de Martos, Alejandro
  • Baquero-Arnal, Pau
  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Giménez Pastor, Adrián
  • Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
[EN] This work describes the participation of the MLLP-VRAIN research group in the two shared tasks of the IWSLT 2022 conference: Simultaneous Speech Translation and Speech-to-Speech Translation. We present our streaming-ready ASR, MT and TTS systems for Speech Translation and Synthesis from English into German. Our submission combines these systems by means of a cascade approach paying special attention to data preparation and decoding for streaming inference., The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5Gon) and 952215 (TAILOR), and Erasmus+ Education programme under grant agreement no. 20- 226-093604-SCH (EXPERT); the Government of Spain¿s grant RTI2018-094879-B-I00 (Multisub) funded by MCIN/AEI/10.13039/501100011033 & ERDF A way of making Europe, and FPU scholarships FPU18/04135; and the Generalitat Valenciana¿s research project Classroom Activity Recognition (ref. PROMETEO/2019/111).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Towards an Incremental and Modular Termination Analysis of Context-Sensitive Rewriting Systems (Work in Progress)

  • Gutiérrez Gil, Raúl|||0000-0002-3984-2868
  • Lucas Alba, Salvador|||0000-0001-9923-2108
Modularity is essential in software development, where a piece of software is often designed and implemented as a composition of simpler modules. So, if we want to prove that a program satisfies a given property, a modular approach becomes natural. With the development and successful use of the Dependency Pair Framework, which rather focuses on the decomposition of termination problems, less attention has been payed to modularity issues (which rather require the opposite approach). But the modular analysis of termination is still paramount for software developers. In this paper, we analyze modularity of context-sensitive rewrite systems. A modularity analysis was carried out by Gramlich and Lucas in 2002, but a correct notion of context-sensitive dependency pair (CS-DP) was not obtained until 2006. In this paper, we analyze modularity using CS-DPs., Partially supported by the EU (FEDER), MINECO projects TIN2010-21062-C02-02 and TIN 2013-45732-C4-1-P, and project PROMETEO/2011/052. Salvador Lucas’ research was developed during a sabbatical year at the CS Dept. of the UIUC and was also partially supported by NSF grant CNS 13-19109, Spanish MECD grant PRX12/00214, and GV grant BEST/2014/026. Raúl Gutiérrez is also partially supported by a Juan de la Cierva Fellowship from the Spanish MINECO, ref. JCI-2012-13528.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Intelligent Project Management Tools, Herramientas inteligentes para la gestión de proyectos

  • Palomares Chust, Alberto|||0000-0002-4583-467X
  • Heras, Stella|||0000-0001-6212-9377
  • Gil Pérez, Aída
[EN] The application of Artificial Intelligence (AI) in Project Management (PM) is a current research field with a growing demand from companies and organizations, interested in applying these technologies to get the most out of their data and expertise. Many organizations use software tools that allow automating the status of projects (situation analysis). These tools also provide predictions on the evolution of projects, using classic techniques such as Earned Value Management (EVM). However, the standard tools do not have many advanced functionalities, based on AI, which would allow to take much better advantage of the knowledge acquired by the organization. This fact is especially important in Risk Management (RM), which is one of the most complex aspects of PM. The objective of this work is to propose a methodology for research and development of tools based on AI technologies that allow organizations to analyze information from projects already developed (historical information) and to use it to improve RM in the planning of future projects., [ES] La aplicación de la Inteligencia Artificial (IA) en la Gestión de Proyectos (GP) es un campo de investigación actual y además existe una demanda creciente por parte de empresas y organizaciones para aplicar estas tecnologías. Muchas organizaciones utilizan herramientas de software que permiten automatizar el estado de los proyectos (análisis de situación). Estas herramientas también proporcionan predicciones sobre la evolución de los proyectos, utilizando técnicas clásicas como la Gestión del Valor Ganado (EVM). Sin embargo, estas herramientas, en general, no disponen de muchas funcionalidades avanzadas, basadas en la IA, que permitirían aprovechar mucho mejor los conocimientos adquiridos por la organización. Este hecho es especialmente importante en la Gestión de Riesgos (GR), que es uno de los aspectos más complejos de la GP. El objetivo de este trabajo es proponer una metodología para la investigación y el desarrollo de herramientas basadas en las tecnologías de la IA que permitan a las organizaciones analizar la información histórica de los proyectos ya ejecutados (información histórica) y utilizarla para poder mejorar la GR en la planificación de los proyectos futuros.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Cálculo 3D de la potencia acústica radiada por una rueda ferroviaria a partir de la respuesta temporal con efectos giroscópicos y comportamiento no lineal

  • García-Andrés, Francesc Xavier
  • F. D. Denia|||0000-0003-4536-8610
  • Martínez Casas, José|||0000-0001-5706-4951
  • Baeza González, Luis Miguel|||0000-0002-3815-8706
[ES] El objetivo de este trabajo es el desarrollo de un modelo de radiación acústica para una rueda de tren a partir de su respuesta temporal, calculada con un modelo dinámico que considera la rotación y sus efectos giroscópicos, la dinámica de alta frecuencia asociada a la flexibilidad de los sólidos y las no linealidades del contacto rueda-carril. Además, se realiza una comparación con los resultados proporcionados por el programa comercial TWINS. La implementación acústica se ha realizado sobre un modelo 3D de elementos finitos (EF) de una rueda ferroviaria excitada por una rugosidad pseudoaleatoria en la superficie del carril, cuyo espectro máximo viene determinado por la norma ISO 3095. A diferencia de los métodos lineales de cálculo de la radiación acústica, basados en funciones de respuesta en frecuencia, el modelo utilizado en este trabajo permite tener en cuenta las no linealidades presentes en el sistema. En la metodología propuesta, inicialmente se divide la superficie de la rueda estudiada en diversos elementos de superficie y se calcula la velocidad normal de cada uno de ellos para cada modo de vibración. En segundo lugar se calculan las eficiencias acústicas correspondientes a cada modo de vibración a partir de una formulación semianalítica [1]. Para ello se requiere conocer el número de diámetros nodales por modo. Con vistas a reducir el coste computacional, el problema de autovalores se resuelve a partir de una sección transversal de la rueda estudiada con un planteamiento 2D de EF capaz de tener en cuenta las propiedades de axisimetría [2]. Seguidamente se determina el contenido en frecuencia del campo temporal de velocidades para calcular a continuación la potencia acústica radiada mediante la integración de las velocidades normales para toda el área de la rueda, teniendo en cuenta la eficiencia acústica correspondiente a cada modo. Finalmente, los resultados obtenidos con el modelo propuesto se comparan con otras metodologías de tipo lineal, tales como la implementada en TWINS [3]. REFERENCIAS [1] D.J. Thompson and C.J.C. Jones, Sound radiation from a vibrating railway wheel , Journal of Sound and Vibration, 253, 401-419 (2002). [2] M. Petyt, Introduction to finite element vibration analysis, second edition, Cambridge University Press, (2010). [3] D.J. Thompson, Railway noise and vibration, Elsevier Ltd, (2009)., Los autores desean agradecer el apoyo recibido del Ministerio de Economía y Competitividad y del Fondo Europeo de Desarrollo Regional (proyecto TRA2013-45596-C2-1-R), así como de la Generalitat Valenciana (proyecto Prometeo/2016/007 y GV/2016/2011 de la Conselleria d¿Educacio, Investigació, Cultura i Esport)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Does AI Qualify for the Job?: A Bidirectional Model Mapping Labour and AI Intensities

  • Martínez-Plumed, Fernando|||0000-0003-2902-6477
  • Hernández-Orallo, José|||0000-0001-9746-7632
  • Tolan, Songül
  • Pesole, Annarosa
  • Fernández-Macías, Enrique
  • Gómez, Emilia
[EN] In this paper we present a setting for examining the relation between the distribution of research intensity in AI research and the relevance for a range of work tasks (and occupations) in current and simulated scenarios. We perform a mapping between labour and AI using a set of cognitive abilities as an intermediate layer. This setting favours a two-way interpretation to analyse (1) what impact current or simulated AI research activity has or would have on labour-related tasks and occupations, and (2) what areas of AI research activity would be responsible for a desired or undesired effect on specific labour tasks and occupations. Concretely, in our analysis we map 59 generic labour-related tasks from several worker surveys and databases to 14 cognitive abilities from the cognitive science literature, and these to a comprehensive list of 328 AI benchmarks used to evaluate progress in AI techniques. We provide this model and its implementation as a tool for simulations. We also show the effectiveness of our setting with some illustrative examples., This material is based upon work supported by the EU (FEDER), and the Spanish MINECO under grant RTI2018-094403-B-C3, the Generalitat Valenciana PROMETEO/2019/098. F. Martínez-Plumed was also supported by INCIBE (Ayudas para la excelencia de los equipos de investigación avanzada en ciberseguridad), the European Commission (JRC) HUMAINT project (CT-EX2018D335821-101), and UPV (PAID-06-18). J. H-Orallo is also funded by an FLI grant RFP2-152.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Comparison of carrier suppressed and quadrature bias point external modulation for 40 GHz millimeter-wave photonic generation using a 16-QAM signal with directly modulated laser

  • Vallejo-Castro, Luis
  • Nguyen, Dong-Nhat
  • Bohata, Jan
  • Zvanovec, Stanislav
  • Ortega Tamarit, Beatriz|||0000-0003-1196-4756
  • Almenar Terre, Vicenç|||0000-0002-8742-2315
[EN] A directly modulated laser usage is proposed for 16-QAM signal transmission over hybrid optical links using two optical frequency multiplication schemes based on external modulation for 40 GHz millimeter-wave (mmW) signal generation. We provide an experimental comparison of two possible approaches: quadrature bias point external modulation system using additional optical filter and null transmission point with suppressed carrier. The systems are discussed in terms of cost and complexity of mmW photonic transmission. High error vector magnitude performance of mmW transmission over fiber and free space optics links is demonstrated and an estimation of the sensitivity of the systems is provided, This work was also supported by the Research Excellence Award Programme GVA PROMETEO 2017/103, the Spanish Ministerio de Ciencia, Innovación y Universidades RTI2018-101658-B-I00 FOCAL project, Ministry of Industry and Trade project MPO TRIO FV40089 and within COST CA16220.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

New applications of late fusion methods for EEG signal processing

  • Safont, Gonzalo
  • Salazar Afanador, Addisson|||0000-0001-5849-5104
  • Vergara Domínguez, Luís|||0000-0001-6803-4774
[EN] Decision fusion consists in the combination of the outputs of multiple classifiers into a common decision that is more precise or stable. In most cases, however, only classical fusion techniques are considered. This work compares the performance of several state-of-the-art fusion methods on new applications of automatic stage classification of several neuropsychological tests. The tests were staged into three classes: stimulus display, retention interval, and subject response. The considered late fusion methods were: alpha integration; copulas; Dempster-Shafer combination; independent component analysis mixture models; and behavior knowledge space. Late fusion was able to improve the performance for the task, with alpha integration yielding the most stable result., This work was supported by Generalitat Valenciana under grant PROMETEO/2019/109 and Spanish Administration and European Union grant TEC2017-84743-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A new method for fraud detection in credit cards based on transaction dynamics in subspaces

  • Salazar Afanador, Addisson|||0000-0001-5849-5104
  • Vergara Domínguez, Luís|||0000-0001-6803-4774
  • Safont, Gonzalo
[EN] This paper presents a new method for fraud detection in credit cards based on exploiting the dynamics of the card transactions. We hypothesize different behavior models in the use of the card between legitimate clients and fraudsters that are registered in the sequential pattern that follows the transactions. The method considers analyses in subspaces defined by two or three variables recorded in the transactions. From these subspaces, several dynamic features, such as transaction velocity and acceleration, are estimated as input vectors for a classification process. Linear and quadratic discriminant analysis and random forest are implemented as single classifiers. All the single classification results obtained for each of the subspaces are late fused to obtain an overall result using alpha integration algorithm. The proposed method was evaluated using a subset of real data with a very low fraud to legitimate transaction ratio. We demonstrated that the temporal dependence of card transactions exploited in different subspaces and fused to give an overall result improves the detection accuracy of fraud detection in credit cards., This work was supported by Generalitat Valenciana under grant PROMETEO/2019/109, and Spanish Administration and European Union grant TEC2017-84743-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Towards a Classifier to Recognize Emotions Using Voice to Improve Recommendations

  • Fuentes-López, José Manuel
  • Rincón Arango, Jaime Andrés
  • Taverner-Aparicio, Joaquín José|||0000-0002-5163-5335
  • Botti V.|||0000-0002-6507-2756
[EN] The recognition of emotions in tone voice is currently a tool with a high potential when it comes to making recommendations, since it allows to personalize recommendations using the mood of the users as information. However, recognizing emotions using tone of voice is a complex task since it is necessary to pre-process the signal and subsequently recognize the emotion. Most of the current proposals use recurrent networks based on sequences with a temporal relationship. The disadvantage of these networks is that they have a high runtime, which makes it difficult to use in real-time applications. On the other hand, when defining this type of classifier, culture and language must be taken into account, since the tone of voice for the same emotion can vary depending on these cultural factors. In this work we propose a culturally adapted model for recognizing emotions from the voice tone using convolutional neural networks. This type of network has a relatively short execution time allowing its use in real time applications. The results we have obtained improve the current state of the art, reaching 93.6% success over the validation set., This work is partially supported by the Spanish Government project TIN2017-89156-R, GVA-CEICE project PROMETEO/2018/002, Generalitat Valenciana and European Social Fund FPI grant ACIF/2017/085, Universitat Politecnica de Valencia research grant (PAID-10-19), and by the Spanish Government (RTI2018-095390-B-C31).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Design and convergence of new iterative methods with memory for solving nonlinear problems

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization

  • Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Giménez Pastor, Adrián
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
  • Iranzo-Sánchez, Javier
  • Baquero-Arnal, Pau
  • Roselló, Nahuel
  • Pérez-González de Martos, Alejandro Manuel
[EN] We introduce Europarl-ASR, a large speech and text corpus of parliamentary debates including 1300 hours of transcribed speeches and 70 million tokens of text in English extracted from European Parliament sessions. The training set is labelled with the Parliament¿s non-fully-verbatim official transcripts, time-aligned. As verbatimness is critical for acoustic model training, we also provide automatically noise-filtered and automatically verbatimized transcripts of all speeches based on speech data filtering and verbatimization techniques. Additionally, 18 hours of transcribed speeches were manually verbatimized to build reliable speaker-dependent and speaker-independent development/test sets for streaming ASR benchmarking. The availability of manual non-verbatim and verbatim transcripts for dev/test speeches makes this corpus useful for the assessment of automatic filtering and verbatimization techniques. This paper describes the corpus and its creation, and provides off-line and streaming ASR baselines for both the speaker-dependent and speaker-independent tasks using the three training transcription sets. The corpus is publicly released under an open licence., [CA] "Europarl-ASR: Un extens corpus parlamentari de referència per a reconeixement de la parla i filtratge/literalització de transcripcions": Presentem Europarl-ASR, un extens corpus de veu i text de debats parlamentaris amb 1300 hores d'intervencions transcrites i 70 milions de paraules de text en anglés extrets de sessions del Parlament Europeu. Les transcripcions oficials del Parlament Europeu, no literals, s'han sincronitzat per a tot el conjunt d'entrenament. Com que l'entrenament de models acústics requereix transcripcions com més literals millor, també s'han inclòs transcripcions filtrades i transcripcions literalitzades de totes les intervencions, basades en tècniques de filtratge i literalització automàtics. A més, s'han inclòs 18 hores de transcripcions literals revisades manualment per definir dos conjunts de validació i avaluació de referència per a reconeixement automàtic de la parla en temps real, amb oradors coneguts i amb oradors desconeguts. Pel fet de disposar de transcripcions literals i no literals, aquest corpus és també ideal per a l'anàlisi de tècniques de filtratge i de literalització. En aquest article, es descriu la creació del corpus i es proporcionen mesures de referència de reconeixement automàtic de la parla en temps real i en diferit, amb oradors coneguts i amb oradors desconeguts, usant els tres conjunts de transcripcions d'entrenament. El corpus es fa públic amb una llicència oberta., This work has received funding from the EU's H2020 research and innovation programme under grant agreements 761758 (X5gon) and 952215 (TAILOR); the Government of Spain's research project Multisub (RTI2018-094879-B-I00, MCIU/AEI/FEDER,EU) and FPU scholarships FPU14/03981 and FPU18/04135; the Generalitat Valenciana's research project Classroom Activity Recognition (PROMETEO/2019/111) and predoctoral research scholarship ACIF/2017/055; and the Universitat Politecnica de València's ` PAID-01-17 R&D support programme.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Program slicing with exception handling

  • Galindo, Carlos|||0000-0002-3569-6218
  • Silva, Josep|||0000-0001-5096-0008
  • Pérez-Rubio, Sergio
[EN] Program slicing is a technique for program analysis and transformation with many different applications such as program debugging, program specialization, and parallelization. The system dependence graph (SDG) is the most commonly used data structure for program slicing. In this paper, we show that the presence of exception-handling constructs can make the SDG produce incorrect and sometimes even incomplete slices. We showcase the instances of incorrectness and incompleteness and we propose a framework for correctly handling exception-related instructions, which includes representation of all possible exception throwing and catching mechanisms, and a new kind of control dependence: conditional control dependence; which produces more precise slices in the presence of catch statements., This work is partially supported by the EU (FEDER) and the Spanish MCI/AEI under Grant No.: TIN2016-76843-C4-1-R and PID2019-104735RB-C41, and by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust). Sergio Pérez was partially supported by Universitat Politècnica de València under FPI grant PAID-01-18.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Multisensor System for Road Surface Identification

  • Safont, Gonzalo
  • Rodríguez, Alberto
  • Salazar Afanador, Addisson|||0000-0001-5849-5104
  • Vergara Domínguez, Luís|||0000-0001-6803-4774
[EN] This work introduces a multisensor road surface identification system that considers features from four different kind of sensors: microphones, accelerometers, speed signals, and handwheel signals. Features are extracted separately from each sensor, joined together, and then filtered using feature selection before classification. The proposed system was tested on a set of signals extracted from a specially-converted passenger car driving on a closed course. Three types of road surfaces were considered: smooth flat asphalt, cobblestones, and stripes. Three classifiers were considered: linear discriminant analysis, support vector machines, and random forests. All the considered classifiers reached over 90% accuracy, with a maximum accuracy of 96.52% for RDF. These results show the potential of the proposed system for road surface identification., This work was supported by Spanish Administration and European Union grant TEC2017-84743-P, and Generalitat Valenciana under grant PROMETEO/2019/109.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Experimental Characterization of a MMW Signal Generation Approach Based on Optical Phase Modulation and Optical Filtering for Data Transmission over a Directly Modulated Laser

  • Botella-Campos, Marta|||0000-0002-1317-286X
  • Mora Almerich, José|||0000-0002-2877-4118
  • Ortega Tamarit, Beatriz|||0000-0003-1196-4756
[EN] In this paper, we present a detailed characterization of a phase modulation (PM)–based approach employing optical filtering for photonic millimeter-wave (mmW) signal generation. Simulations and experimental results exhibit very good agreement, showing that both the bandwidth and the notch peak of the optical filter lead to the overall system response, with up to 15 dB electrical gain in the mmW band, also due to the combination of laser chirp and 10 km fiber dispersion. The system error-vector-magnitude (EVM) performance for a 25 MHz bandwidth QPSK signal is characterized over a wide range of electrical mmW power values and frequencies, while intermodulation distortion appears at high power levels. Accordingly, in the linear regime, it is observed that the 10 km SSMF link yields improved EVM values compared to OB2B in terms of RoP, while measurements for different ReP values show the transparency of this approach with no further degradation with respect to EB2B tests. Therefore, this method is confirmed as very promising for future deployment of mmW-based communication networks using photonic technologies for signal generation and transmission., The research leading to these results has received funding from Generalitat Valenciana (PROMETEO 2021/015) and MCIN/AEI/10.13039/501100011033 and ERDF A way of making Europe by Grant PID2021-126514OBI00 OPTIMISE.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Stream-level Latency Evaluation for Simultaneous Machine Translation

  • Iranzo-Sánchez, Javier
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream-level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task., The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 761758 (X5Gon) and 952215 (TAILOR) and Erasmus+ Education program under grant agreement no. 20-226-093604-SCH; the Government of Spain's research project Multisub, ref. RTI2018-094879-B-I00 (MCIU/AEI/FEDER,EU) and FPU scholarships FPU18/04135; and the Generalitat Valenciana's research project Classroom Activity Recognition, ref. PROMETEO/2019/111.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

IDAT@FIRE2019: Overview of the Track on Irony Detection in Arabic Tweets

  • Ghanem, Bilal
  • Karoui, Jihen
  • Benamara, Farah
  • Moriceau, Véronique
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This overview paper describes the first shared task on irony detection for the Arabic language. The task consists of a binary classification of tweets as ironic or not using a dataset composed of 5,030 Arabic tweets about different political issues and events related to the Middle East and the Maghreb. Tweets in our dataset are written in Modern Standard Arabic but also in different Arabic language varieties including Egypt, Gulf, Levantine and Maghrebi dialects. Eighteen teams registered to the task among which ten submitted their runs. The methods of participants ranged from feature-based to neural networks using either classical machine learning techniques or ensemble methods. The best performing system achieved F-score value of 0.844, showing that classical feature-based models outperform the neural ones., This publication was made possible by NPRP grant 9-175-1-033 from the Qatar National Research Fund (a member of Qatar Foundation). The findings achieved herein are solely the responsibility of the last author. The work of Paolo Rosso was also partially funded by Generalitat Valenciana under grant PROMETEO/2019/121.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Profiling hate speech spreaders on twitter task at PAN 2021

  • Rangel, Francisco
  • Peña-Sarracén, Gretel Liz de la
  • Chulvi-Ferriols, María Alberta
  • Fersini, Elisabetta
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This overview presents the Author Profiling shared task at PAN 2021. The focus of this year¿s task is on determining whether or not the author of a Twitter feed is keen to spread hate speech. The main aim is to show the feasibility of automatically identifying potential hate speech spreaders on Twitter. For this purpose a corpus with Twitter data has been provided, covering the English and Spanish languages. Altogether, the approaches of 66 participants have been evaluated., First of all, we thank the participants: again 66 this year, as the previous year on Profiling Fake News Spreaders! We have to thank also Martin Potthast, Matti Wiegmann, Nikolay Kolyada, and Magdalena Anna Wolska for their technical support with the TIRA platform. We thank Symanto for sponsoring again the award for the best performing system at the author profiling shared task. The work of Francisco Rangel was partially funded by the Centre for the Development of Industrial Technology (CDTI) of the Spanish Ministry of Science and Innovation under the research project IDI-20210776 on Proactive Profiling of Hate Speech Spreaders - PROHATER (Perfilador Proactivo de Difusores de Mensajes de Odio). The work of the researchers from Universitat Politècnica de València was partially funded by the Spanish MICINN under the project MISMIS-FAKEnHATE on MISinformation and MIScommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31), and by the Generalitat Valenciana under the project DeepPattern (PROMETEO/2019/121). This article is also based upon work from the Dig-ForAsp COST Action 17124 on Digital Forensics: evidence analysis via intelligent systems and practices, supported by European Cooperation in Science and Technology.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Efficient finite element modelling of sound propagation in after treatment devices with arbitrary cross section

  • F. D. Denia|||0000-0003-4536-8610
  • Sánchez-Orgaz, Eva María|||0000-0002-8864-3056
  • Martínez Casas, José|||0000-0001-5706-4951
  • Baeza González, Luis Miguel|||0000-0002-3815-8706
  • Ferrándiz-Catalá, Borja
[EN] The acoustic modelling of exhaust after-treatment devices, such as catalytic converters (CC) and diesel particulate filters (DPF), usually requires the use of multidimensional numerical techniques to assess the influence of higher order modes on the sound attenuation performance. Three-dimensional (3D) wave propagation can be considered through the finite element method (FEM). With a view to improving the computational expenditure of full 3D FEM, an efficient modelling technique is presented in this work to speed up transmission loss (TL) calculations in after-treatment devices with arbitrary cross section incorporating monoliths. The efficient modelling approach is based on the mode matching method, combining: (1) transversal pressure modes computed through a 2D FEM approach for devices with arbitrary but axially uniform cross section; (2) compatibility conditions of the acoustic fields at the device geometric discontinuities. For the acoustic modelling of monoliths, these are replaced by four pole transfer matrices relating the acoustic fields at both sides of the monolithic region. Mode matching TL results are compared with full 3D FE simulations and experimental measurements for some selected configurations, showing a good agreement. For a given accuracy, the computational efficiency of the mode matching technique proposed in this work improves that of full 3D FE calculations. TL improvements are achieved by suitable locations of a DPF inlet/outlet ducts. Next, a Genetic Algorithm (GA)-based optimization approach is used in order to improve the attenuation performance of the after-treatment device by varying the geometry as well as the monolith properties. Results show that the optimized configuration outperforms the initial design at target frequencies., The authors gratefully acknowledge the financial support of Ministerio de Ciencia, Innovación y Universidades-Agencia Estatal de Investigación through project TRA2017-84701-R and Generalitat Valenciana through project PROMETEO/2016/007.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Extension of the modal superposition method for general damping applied in railway dynamics

  • Giner Navarro, Juan|||0000-0002-0513-3625
  • Martínez Casas, José|||0000-0001-5706-4951
  • F. D. Denia|||0000-0003-4536-8610
  • Andrés-Ruiz, Víctor Tomás
[EN] The frequency response function (FRF) permits to characterise in the frequency domain the systems governed by linear dynamics by means of a relationship between an excitation applied at one degree of freedom (dof) and the consequent output response in a particular dof. A modal approach is widely extended in the engineering fields as efficient method of computing the FRF of matrix second-order linear equations of motion derived from the application of the Finite Element Method (FEM) [1]. This approach is based on the truncation of the number of vibration modes that conform the base of the new modal coordinates. The criterion for the truncation is linked to the frequency range of the dynamic study, ordering the vibration modes with respect to the eigenvalues (the square of natural frequencies) associated. The natural frequency associated with the last vibration mode selected establishes the maximum frequency that can describe the time response of the system. The truncation permits to reduce the dimension of the system from N number of dofs in physical coordinates to m truncated vibration modes in modal coordinates. The fundamental numerical problem derived from the truncation is the resulting non-square vibration modes matrix, used as transformation matrix in the physical to modal change of variable [1,2]. This change should allow the diagonalisation of the matrices involved in the equation of motion: mass, stiffness and damping matrices. The diagonalisation is essential to decouple the system in m second-order linear differential equations that can be solved analytically in the time domain. Nevertheless, the inverse of vibration modes matrix required for the diagonalisation cannot be applied from its non-square nature and it can only be replaced by the transpose matrix if both mass and stiffness matrices are symmetric. The complexity increases in a case of general damping instead of proportional or spectral ones [3], in which the damping matrix must be included in the eigenproblem in order to diagonalise the whole modal system. This work proposes a methodology to overcome the issues abovementioned and applies this in the field of railway dynamics in order to compute the modal properties of a railway wheel modelled by using FEM [4]. The paper includes a study of the numerical performance of this method and its comparison with other numerical procedures to find the FRF of the wheel., The authors gratefully acknowledge the financial support of FEDER/Ministerio de Ciencia, Innovacion y Universidades Agencia Estatal de Investigacion (project TRA2017-84701-R), as well as Conselleria d¿Educacio, Investigacio, Cultura i Esport (project Prometeo/2016/007) and European Commission through the project RUN2Rail - Innovative RUNning gear soluTiOns for new dependable, sustainable, intelligent and comfortable RAIL vehicles (Horizon 2020 Shift2Rail JU call 2017, grant number 777564).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Arrhythmogenicity quantification of two genetic defects affecting IKr channel in AF patients

  • Belletti, R.
  • Martínez Mateu, L.
  • Cherry, E.
  • Fenton, F. H.
  • Romero Pérez, Lucia|||0000-0003-4605-8630
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
[EN] Atrial fibrillation (AF) is the most common cardiac arrhythmia characterized by disorganized electrical activations of the upper chambers of the heart, leading to uncoordinated contraction and compromising the pumping action of the organ. AF risk factors include cardiovascular pathologies, endocrine disorders, advanced age, obesity, smoking and heritability. Genetic mutations affecting gene encoding for ion channel protein structures are in fact considered as cause of fibrillatory events in individuals who do not present any other co-morbidities. In this work, two genetic mutations found in literature and affecting the alpha-subunit of the rapid delayed rectifier potassium channel are modelled, by reparametrizing the IKr current formulation and by fitting it to mutant experimental data. The modified potassium current was then incorporated into the Courtemanche-Ramirez-Nattel (CRN) model and single cell simulations have been performed to study the mutations¿ effects on action potential and current traces, as well as, restitution properties, in right and left atrium. Both mutations produced a shortening of the action potential duration at 90% of repolarization (APD90), a higher current peak and lower APD values in the restitution curves. T895M yielded also to a reduction in the maximum slope of restitution curve. Tissue patch simulations revealed that T895M and T436M provide a substrate to initiate and maintain re-entries during the 5 seconds of simulation. Rotor¿s meandering in T895M appears more stable with a less extended area and more regular pattern than in T436M. Investigation on 3D atria and torso models will be necessary to provide further insights in understanding the mechanisms behind these genetic mutations., I am grateful to the teams at GaTech, who helped me in the realization of this work. This project has been funded by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie gran agreement No.766082 and by Generalitat Valenciana, Prometeo programme 2020/043.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Simulation Study of the Arrhythmogenic Effects of Two Missense Mutations in Human Atrial Fibrillation

  • Belletti, Rebecca
  • Martínez-Mateu, Laura
  • Romero Pérez, Lucia|||0000-0003-4605-8630
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
[EN] Genetic mutations affecting genes encoding for ion channel protein structures have been associated with the presence of atrial fibrillation (AF) in healthy individuals. The aim of this study is to model and simulate the effects of two gain-of-function mutations found in literature, T895M and T436M, and affecting the rapid delayed rectifier potassium current. Courtemanche human atrial model has been chosen to reproduce myocytes behaviour and an optimization algorithm has been employed to fit model parameters to experimental data. Single cell and tissue patch simulations have been performed to study the effects of the two mutations in control, paroxysmal and permanent AF conditions, both in right and left atrium. 0D simulations revealed that both mutations cause an increase in IKr current, leading to action potential duration shortening and flattening of restitution curves, especially in presence of the mutation T895M. Initiation of a re-entrant activity in 2D simulations were possible both in case of T895M and T436M. The study reports the arrhythmogenicity of the two mutants and reveals T895M having a stronger effect with respect to T436M, in particular in control rather than in paroxysmal and permanent AF conditions. Differences in the dynamics of the two mutations highlight the importance of a patient-specific approach in planning targeted drug therapies., I acknowledge this work to the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie gran agreement No.766082 and to Generalitat Valenciana, Prometeo programme 2020/043
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Bimodal waveguide sensors enabled by subwavelength grating structures

  • Torrijos-Morán, Luis
  • García-Rupérez, Jaime|||0000-0002-2036-0084
  • Griol Barres, Amadeu
[EN] A subwavelength grating sensor based on a bimodal waveguide configuration is presented for continuous in-flow measurements of refractive index variations. An experimental bulk sensitivity of 1350nm/RIU and a limit of detection of 2x10-5RIU is obtained in a single-channel refractive index sensor.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Direct Segmentation Models for Streaming Speech Translation

  • Iranzo-Sánchez, Javier
  • Baquero-Arnal, Pau
  • Giménez Pastor, Adrián
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into, hopefully, semantically self-contained chunks to be fed into the MT system. This is specially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and thorough experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work., The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 761758 (X5Gon); the Government of Spain's research project Multisub, ref. RTI2018- 094879-B-I00 (MCIU/AEI/FEDER,EU), the Generalitat Valenciana's research project Classroom Activity Recognition, ref. PROMETEO/2019/111., FPU scholarship FPU18/04135; and the Generalitat Valencianas predoctoral research scholarship ACIF/2017/055. The authors wish to thank the anonymous reviewers for their criticisms and suggestions.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Cambios en los loops de las ondas P del vectocardiograma tras el aislamiento de las venas pulmonares

  • Ortigosa, Nuria|||0000-0002-5272-7661
  • Cano, O.
  • Sandberg, F.
[ES] La fibrilación auricular es la arritmia más frecuente en la práctica clínica. Además de los tratamientos antiarrítmicos, el aislamiento de las venas pulmonares mediante ablación por catéter es uno de los tratamientos utilizados acorde a las guías clínicas para ayudar a mantener el ritmo sinusal de forma indefinida en el paciente. El propósito de este estudio es analizar cómo dicho procedimiento afecta a los patrones de conducción eléctrica en las aurículas, y cómo estos se ven modificados en los registros electrocardiográficos registrados al paciente. Para ello, se ha comparado la morfología de las ondas P de los loops extraídos de los vectocardiogramas calculados a partir del electrocardiograma de superficie, antes y después del procedimiento en pacientes con fibrilación auricular paroxística. Estos pacientes tienen episodios autolimitados, permaneciendo gran parte del tiempo en ritmo sinusal y sin un alto grado de evolución de la arritmia. El primer y segundo autovalor de los loops, así como una medida de la redondez de los mismos señalaron cambios significativos tras el procedimiento, mostrando que el aislamiento de las venas pulmonares induce cambios morfológicos en los loops de las ondas P., N. Ortigosa agradece el apoyo del Ministerio de Ciencia, Innovación y Universidades en el marco del Programa Estatal de Promoción del Talento y su Empleabilidad en I+D+i -Subprograma Estatal de Movilidad- con la beca CAS19/00168, de la Generalitat Valenciana con el proyecto Prometeo/2017/102 y del MINECO con el proyecto MTM2016-76647-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Acoustic modelling of large aftertreatment devices with multimodal incident sound fields

  • F. D. Denia|||0000-0003-4536-8610
  • Sánchez-Orgaz, Eva María|||0000-0002-8864-3056
  • Martínez Casas, José|||0000-0001-5706-4951
  • Carballeira, Javier|||0000-0002-4179-8499
  • Baeza González, Luis Miguel|||0000-0002-3815-8706
[EN] The influence of multimodal incident sound fields on the acoustic behaviour of large aftertreatment devices (ATD) is analysed in detail. The mode matching method is applied to the compatibility conditions of the three-dimensional (3D) acoustic fields at the device geometric discontinuities, leading to the computation of the complex wave amplitudes in all the subdomains involved and the corresponding transmission loss (TL). To have a realistic model, 3D propagation must be considered in the inlet/outlet ducts and chambers, while 1D wave propagation has to be assumed along the small capillaries of the catalytic converter/particulate filter monoliths of the ATD; therefore, these monoliths can be replaced by plane wave four pole transfer matrices from an acoustical point of view [1]. On the other hand, for large ATD inlet ducts such as those found in heavy-duty and off-road engines, the usual models with plane incident wave excitation are not accurate since the onset of higher order incident modes in the inlet duct is expected for the frequency range of interest. Therefore, a TL variation is likely to occur depending on these modes, similar to the results found in large dissipative silencers [2]. Results are presented for three different multimodal incident sound field hypotheses [3]: equal modal amplitude (EMA), equal modal power (EMP) and equal modal energy density (EMED). A relevant influence on the sound attenuation is found for the test problems considered in the current investigation. References [1] Denia, F. D., Martínez-Casas, J., Carballeira, J., Nadal, E., Fuenmayor, F. J., Computational performance of analytical methods for the acoustic modelling of automotive exhaust devices incorporating monoliths. Journal of Computational and Applied Mathematics, 330: 995--1006, 2018. [2] Kirby, R., Lawrie, J. B., A point collocation approach to modelling large dissipative silencers. Journal of Sound and Vibration, 286: 313--339, 2005. [3] Mechel, F. P., Formulas of Acoustics. Berlin, Springer, 2008., The authors gratefully acknowledge Grants PID2020-112886RA-I00 and PID2020-118013RB-C21 funded by MCIN/AEI/10.13039/501100011033 and Project PROMETEO/2021/046 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Towards the edge intelligence: Robot assistant for the detection and classification of human emotions

  • Rincón Arango, Jaime Andrés
  • Julian, Vicente|||0000-0002-2743-6037
  • Carrascosa Casamayor, Carlos|||0000-0003-3649-6530
[EN] Deep learning is being introduced more and more in our society. Nowadays, there are very few applications that do not use deep learning as a classification tool. One of the main application areas is focused on improving people¿s life quality, allowing to create personal assistants with canned benefits. More recently, with the proliferation of mobile computing and the emergence of the Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet. This allows the generation of millions of bytes of information about sensors, images, sounds, etc. Driven by this trend, there is an urgent need to push the IoT frontiers to the edge of the network, in order to decrease this massive sending of information to large exchanges for analysis. As a result of this trend, a new discipline has emerged: edge intelligence or edge AI, a widely recognised and promising solution that attracts with special interest to the community of researchers in artificial intelligence. We adapted edge AI to classify human emotions. Results show how edge AI-based emotion classification can greatly benefit in the field of cognitive assistants for the elderly or people living alone., This work was partly supported by the Generalitat Valenciana (PROMETEO/2018/002) and by the Spanish Government (RTI2018-095390-B-C31). Universitat Politecnica de Valencia Research Grant PAID-10-19.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Reversible Computations in Logic Programming

  • Vidal, Germán|||0000-0002-1857-6951
[EN] In this work, we say that a computation is reversible if one can find a procedure to undo the steps of a standard (or forward) computation in a deterministic way. While logic programs are often invertible (e.g., one can use the same predicate for adding and for subtracting natural numbers), computations are not reversible in the above sense. In this paper, we present a so-called Landauer embedding for SLD resolution, the operational principle of logic programs, so that it becomes reversible. A proof-of-concept implementation of a reversible debugger for Prolog that follows the ideas in this paper has been developed and is publicly available., This work is partially supported by the EU (FEDER) and the Spanish MCI/AEI under grants TIN2016-76843-C4-1-R/PID2019-104735RB-C41, by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust), and by the COST Action IC1405 on Reversible Computation - extending horizons of computing.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

64-QAM LTE signal transmission at 25 GHz over hybrid SSMF and non-uniform turbulent FSO channel

  • Vallejo-Castro, Luis
  • Nguyen, Dong-Nhat
  • Bohata, Jan
  • Zvanovec, Stanislav
  • Ortega Tamarit, Beatriz|||0000-0003-1196-4756
[EN] This contribution describes the impact of non uniform thermal-induced turbulence on 64-QAM LTE signal transmission at 25 GHz millimeter wave (mmW) signal along hybrid RoF/RoFSO links. Microwave photonic signal generation has been employed by using the optical frequency doubling with intensity modulator biased at the minimum transmission point. The optical and electrical power budgets of different scenarios have been defined and error vector magnitude (EVM) performance has been measured. It is shown that the uniform scenario with high turbulence in the middle of the link is the one with greater impact on the quality of the received data., This work was also supported by the Research Excellence Award Programme GVA PROMETEO 2017/103, the Spanish Ministerio de Ciencia, Innovación y Universidades RTI2018- 101658-B-I00 FOCAL project, Ministry of Industry and Trade in Czech Republic project (FV30427) and within COST CA16220.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Three-Dimensional Model of the Human Atria With Heterogeneous Wall Thickness and Fibre Transmurallity - A Realistic Platform for the Study of Atrial Fibrillation

  • Rocher-Ventura, Sara
  • Martínez, Laura
  • López, Alejandro
  • Sánchez-Quintana, Damián
  • FERRER ALBERO, ANA|||0000-0001-7642-916X
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
[EN] Multiscale cardiac modelling has been increasingly used since it provides a promising framework to improve our understanding of atrial fibrillation physiopathology. In this study, we present a highly detailed threedimensional model of the human atria including heterogenous wall thickness and fibre transmurality, suggested as relevant factor in arrhythmogenic dynamics. We hypothesized that the structural definition of computer models influences the electrical propagation and to test it we compared the fibrillatory activity of the new model with two models less detailed anatomically but with the same electrical and tissular properties. The three studied models generated different arrhythmic patterns, with the appearance of re-entrant drivers at different atrial regions. We conclude that it is very important to use complete realistic atrial models, especially for atrial fibrillation studies, to obtain reliable results. Additionally, the developed model allows to consider new variables of study involving atrial wall thickness transmurality., This work was partially supported by funding sources from Generalitat Valenciana ACIF/2018/174 and Programa Prometeu de la Conselleria d'Educació, Formació I Ocupació de la Generalitat Valenciana, award number PROMETEU/2016/088.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Towards a Dynamic Edge AI Framework applied to autonomous driving cars

  • Muratore, G.
  • Rincón Arango, Jaime Andrés
  • Greco, G.
  • Fortino, G.
  • Julian, Vicente|||0000-0002-2743-6037
  • Carrascosa Casamayor, Carlos|||0000-0003-3649-6530
[EN] This work proposes an innovative solution in the field of Edge AI in order to efficiently exploit new hardware components available on the market at low cost. Edge AI means that algorithms are processed locally on a hardware device. The algorithms use data (sensor data or signals) that are created on the own device. The idea of this paper focuses on demonstrating the validity of the proposed solution by implementing an autonomous driving system that exploits communication between intelligent agents. In this case, our self-driving cars are equipped with a low-cost device that allows you to recognise objects along the way and consequently take actions by running a machine learning model. The presence of a machine learning model also allows the developer to modify it by extending the flexibility and application possibilities of the proposed solution., This work was partly supported by: ERASMUS+ Programme, KA1 Istruzione Superiore, Carta Erasmus+: 29388-EPP-1-2014-1-IT-EPPKA3-ECHE, ACCORDO PER LA MOBILITÀ ERASMUS PER STUDIO - a.a. 2019/2020, Progetto n o 2019-1-IT02-KA103-061203 - CUP: H25J19000080006, Generalitat Valenciana (PROMETEO/2018/002). Universitat Politecnica de Valencia Research Grant PAID-10-19.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Deep Modeling of Latent Representations for Twitter Profiles on Hate Speech Spreaders Identification Task

  • Labadie Tamayo, Roberto
  • Castro Castro, Daniel
  • Ortega-Bueno, Reynier
[EN] In this paper, we describe the system proposed by UO-UPV team for addressing the task Profiling Hate Speech Spreaders on Twitter shared at PAN 2021. The system relies on a modular architecture, combining Deep Learning models with an introduced variant of the Impostor Method (IM). It receives a single profile composed of a fixed quantity of tweets. These posts are encoded as dense feature vectors using a fine-tuned transformer model and later combined to represent the whole profile. For classifying a new profile as hate speech spreader or not, it is compared by a similarity function with the Impostor Method with respect to random sampled prototypical profiles. In the final evaluation phase, our model achieved 74% and 82% of accuracy for English and Spanish languages respectively, ranking our team at 2¿¿ position and giving a starting point for further improvements., The work of the third author was in the framework of the research project MISMIS-FAKEnHATE on MISinformation and MIScommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31), funded by Spanish Ministry of Science and Innovation, and DeepPattern (PROMETEO/2019/121), funded by the Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Two Methods to Improve Confidence Scores for Lexicon-Free Word Spotting in Handwritten Text

  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
  • Puigcerver, Joan
[EN] Two methods are presented to improve word confidence scores for Line-Level Query-by-String Lexicon-Free Keyword Spotting (KWS) in handwritten text images. The first one approaches true relevance probabilities by means of computations directly carried out on character lattices obtained from the lines images considered. The second method uses the same character lattices, but it obtains relevance scores by first computing frame-level character sequence scores which resemble the word posteriorgrams used in previous approaches for lexicon-based KWS. The first method results from a formal probabilistic derivation, which allow us to better understand and further develop the underlying ideas. The second one is less formal but, according with experiments presented in the paper, it obtains almost identical results with much lower computational cost. Moreover, in contrast with the first method, the second one allows to directly obtain accurate bounding boxes for the spotted words., This work was partially supported by the Spanish MEC under FPU grant FPU13/06281, by the Generalitat Valenciana under the Prometeo/2009/014 project grant ALMAMATER, and through the EU projects: HIMANIS (JPICH programme, Spanish grant Ref. PCIN-2015-068) and READ (Horizon-2020 programme, grant Ref. 674943).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Speech Interaction in a Multimodal Tool for Handwritten Text Transcription

  • Castro-Bleda, Maria Jose|||0000-0003-1001-8258
  • España Boquera, Salvador|||0000-0002-0335-9997
  • Llorens, David
  • Marzal Varó, Andrés
  • Prat, Federico
  • Vilar Torres, Juan Miguel
  • Zamora Martínez, Francisco
[EN] STATE is a multimodal tool for document processing and text transcription. Its graphical front-end can be easily connected to different text recognition back-ends. New features and improvements are presented in this work: the interactive correction of one word in the transcribed line has been improved to reestimate the entire transcription line using the user feedback and speech input has been integrated in the multimodal interface enabling the user to also utter the word to be corrected, giving the user the possibility to use the interface according to her preferences or the task at hand. Thus, at the current version of STATE, the user can type, write on the screen with a stylus, or utter the incorrectly recognized word, and then, the system uses the user feedback in any of the proposed modalities to reestimate the transcribed line so as to hopefully correct other errors which could be caused by the mistaken word the user has corrected., Work partially supported by the Spanish Government (TIN2010-18958 and Consolider Ingenio 2010 CSD2007-00018), the Generalitat Valenciana (Prometeo/2010/028), and Fundació Caixa CastellóBancaixa (P11B2009-48)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Symmetry relations between dynamical planes

  • Chicharro, Francisco I.|||0000-0001-9116-2870
  • Cordero Barbero, Alicia|||0000-0002-7462-9173
  • Garrido-Saez, Neus|||0000-0002-7903-8591
  • Torregrosa Sánchez, Juan Ramón|||0000-0002-9893-0761
This research was partially supported by MCIU/AEI/FEDER, UE PGC-2018-095896-B-C22 and Generalitat Valenciana PROMETEO/2016/089.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Medical Image Restoration with Different Types of Noise

  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
  • Vidal-Gimeno, Vicente-Emilio|||0000-0002-2384-7015
  • Ródenas Escribá, Francisco De Asís|||0000-0003-4564-5171
  • Mayo, Patricia|||0000-0002-8403-5221
[EN] The images obtained by X-Ray or computed tomography (CT) in adverse conditions may be contaminated with noise that can affect the detection of diseases. A large number of image processing techniques (filters) have been proposed to remove noise. These techniques depend on the type of noise present in the image. In this work, we propose a method designed to reduce the Gaussian, the impulsive and speckle noise and combined noise. This filter, called PGNDF, combines a non-linear diffusive filter with a peer group with fuzzy metric technique. The proposed filter is able to reduce efficiently the image noise without any information about what kind of noise might be present. To evaluate the filter performance, we use mammographic images from the miniMIAS database which we have damaged by adding Gaussian, impulsive and speckle noises of different magnitudes. As a result, the proposed method obtains a good performance in most of the different types of noise., This work was funded by the Spanish Ministry of Science and Innovation: Project TIN2011-26254), ANITRAN PROMETEO/2010/039, Project TIN2008-06570-C04-04, and to DGEST ITCG for the PROMEP program (Mexico).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

An Optimizing Protocol Transformation for Constructor Finite Variant Theories in Maude-NPA

  • Aparicio-Sánchez, Damián
  • Escobar Román, Santiago|||0000-0002-3550-4781
  • Gutiérrez Gil, Raúl|||0000-0002-3984-2868
  • Sapiña-Sanchis, Julia|||0000-0003-2994-6986
[EN] Maude-NPA is an analysis tool for cryptographic security protocols that takes into account the algebraic properties of the cryptosystem. Maude-NPA can reason about a wide range of cryptographic properties. However, some algebraic properties, and protocols using them, have been beyond Maude-NPA capabilities, either because the cryptographic properties cannot be expressed using its equational unification features or because the state space is unmanageable. In this paper, we provide a protocol transformation that can safely get rid of cryptographic properties under some conditions. The time and space difference between verifying the protocol with all the crypto properties and verifying the protocol with a minimal set of the crypto properties is remarkable. We also provide, for the first time, an encoding of the theory of bilinear pairing into Maude-NPA that goes beyond the encoding of bilinear pairing available in the Tamarin tool, Partially supported by the EU (FEDER) and the Spanish MCIU under grant RTI2018-094403-B-C32, by the Spanish Generalitat Valenciana under grant PROMETEO/2019/098, and by the US Air Force Office of Scientific Research under award number FA9550-17-1-0286. Julia Sapiña has been supported by the Generalitat Valenciana APOSTD/2019/127 grant
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Space-Division Multiplexing Fibers for Microwave Signal Processing

  • Ureña-Gisbert, Mario
  • García-Cortijo, Sergi|||0000-0002-7237-9457
  • Gasulla Mestre, Ivana|||0000-0001-8088-7796
[EN] We report the implementation of tunable microwave signal processing based on sampled true time delay line operation using a dispersion-engineered heterogeneous multicore fiber link., This research was supported by the ERC Consolidator Grant 724663, Spanish MINECO Project TEC2016-80150-R, Generalitat Valenciana (PROMETEO 2017/017 research excellency award); Spanish MINECO scholarship BES2015-073359 for S. García and Spanish MINECO fellowship RYC-2014-16247 for I. Gasulla.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

The New THOT Toolkit for Fully-Automatic and Interactive Statistical Machine Translation

  • Ortiz-Martínez, Daniel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] We present the new THOT toolkit for fullyautomatic and interactive statistical machine translation (SMT). Initial public versions of THOT date back to 2005 and did only include estimation of phrase-based models. By contrast, the new version offers several new features that had not been previously incorporated. The key innovations provided by the toolkit are computeraided translation, including post-editing and interactive SMT, incremental learning and robust generation of alignments at phrase level. In addition to this, the toolkit also provides standard SMT features such as fully-automatic translation, scalable and parallel algorithms for model training, client-server implementation of the translation functionality, etc. The toolkit can be compiled in Unix-like and Windows platforms and it is released under the GNU Lesser General Public License (LGPL)., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grant agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

CU2rCU: towards the Complete rCUDA Remote GPU Virtualization and Sharing Solution

  • Reaño González, Carlos
  • Peña Monferrer, Antonio José
  • Duato Marín, José Francisco
  • Mayo Gual, Rafael
  • Silla, Federico|||0000-0002-6435-1200
  • Quintana-Ortí, Enrique S.|||0000-0002-5454-165X
GPUs are being increasingly embraced by the high performance computing and computational communities as an effective way of considerably reducing execution time by accelerating significant parts of their application codes. However, despite their extraordinary computing capabilities, the adoption of GPUs in current HPC clusters may present certain negative side-effects. In particular, to ease job scheduling in these platforms, a GPU is usually attached to every node of the cluster. In addition to increasing acquisition costs this favors that GPUs may frequently remain idle, as applications usually do not fully utilize them. On the other hand, idle GPUs consume non-negligible amounts of energy, which translates into very poor energy efficiency during idle cycles. rCUDA was recently developed as a software solution to address these concerns. Specifically, it is a middleware that allows transparently sharing a reduced number of GPUs among the nodes in a cluster. rCUDA thus increases the GPU-utilization rate, taking care of job scheduling. While the initial prototype versions of rCUDA demonstrated its functionality, they also revealed several concerns related with usability and performance. With respect to usability, in this paper we present a new component of the rCUDA suite that allows an automatic transformation of any CUDA source code, so that it can be effectively accommodated within this technology. In response to performance, we briefly show some interesting results, which will be deeply analyzed in future publications. The net outcome is a new version of rCUDA that allows, for any CUDA-compatible program, to use remote GPUs in a cluster with minimum overhead., The researchers at UPV were supported by the Spanish MICINN, Plan E funds, under Grant TIN2009-14475-C04-01 and also by PROMETEO from Generalitat Valenciana (GVA) under Grant PROMETEO/2008/060. Researchers at UJI were supported by the Spanish Ministry of Science and FEDER (contract no. TIN2011-23283), and by the Fundacion Caixa- ´ Castello/Bancaixa (no. P1-1B2009-35)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Novel Method to Decouple Temperature and Strain Using a Customized Femtosecond Laser-inscribed Superstructure Fiber Bragg Grating

  • Sanipatin-Urquizo, Bryan David|||0000-0003-4042-2286
  • Maldonado-Hurtado, Daniel Gustavo|||0000-0001-8585-0271
  • Madrigal-Madrigal, Javier|||0000-0003-3156-1321
  • Barrera Vilar, David|||0000-0002-1700-6842
  • Sales Maicas, Salvador|||0000-0001-9457-976X
[EN] This paper introduces a novel technique to simultaneously measure temperature and strain using a single 5 mm femtosecond laser-inscribed superstructure FBG. Analyzing resonance distances, it allows distinguishing and complements the contributions of strain and temperature, improving measurements in sensing applications., This work is partially supported by the I+D+I projects SYNERGY PID2020-118310RB-I00 and INSTILL PID2020 120071RJ I00 funded by MCIN/AEI/10.13039/501100011033. Also, by the Generalitat Valenciana, the PROMETEO 2021/015 Research Excellency Award, the IDIFEDER/2020/032, as well as IDIFEDER/2021/050 GV A Infraestructura. D and PAID-10-22 de la Universitat Politècnica de València. Maldonado- Hurtado is supported by a scholarship PRE2018-085654, funded by MCIN/AEI/10.13039/501100011033, and ESF Investing in your future. . B. Sanipatin is supported by the Generalitat Valenciana, the PROMETEO 2021/015.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

UPV-Symanto at eRisk 2021: Mental Health Author Profiling for Early Risk Prediction on the Internet

  • Basile, Angelo
  • Chinea-Ríos, Mara
  • Uban, Ana-Sabina
  • Müller, Thomas
  • Rössler, Luise
  • Yenikent, Seren
  • Chulvi-Ferriols, María Alberta
  • Franco-Salvador, Marc
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This paper presents the contributions of the UPV-Symanto team, a collaboration between Symanto Research and the PRHLT Center, in the eRisk 2021 shared tasks on gambling addiction, self-harm detection and prediction of depression levels. We have used a variety of models and techniques, including Transformers, hierarchical attention networks with multiple linguistic features, a dedicated early alert decision mechanism, and temporal modelling of emotions. We trained the models using additional training data that we collected and annotated thanks to expert psychologists. Our emotions-over-time model obtained the best results for the depression severity task in terms of ACR (and second best according to ADODL). For the self-harm detection task, our Transformer-based model obtained the best absolute result in terms of ERDE5 and we ranked equal first in terms of speed and latency., The authors from Universitat Politècnica de València thank the EU-FEDER Comunitat Valenciana 2014-2020 grant IDIFEDER/2018/025. The work of Paolo Rosso was in the framework of the research project PROMETEO/2019/121 (DeepPattern) by the Generalitat Valenciana. We would like to thank the two anonymous reviewers who helped us improve this paper.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Análisis del Filtro FPGA en Imágenes de Tomografía Computarizada para la Reducción de Dosis Radiactiva

  • PARCERO IGLESIAS, ESTIBALIZ|||0000-0002-5155-2900
  • Vidal-Gimeno, Vicente-Emilio|||0000-0002-2384-7015
  • Verdú Martín, Gumersindo Jesús|||0000-0001-5098-080X
  • Mayo, Patricia|||0000-0002-8403-5221
  • Josep Arnal García
[EN] X-Ray or CT (computed tomography) images may have noise due to image acquisition process. As contaminated images complicate diagnosis many filters have been developed to overcome this problem. In this work we study the behavior of a Fuzzy method called FPGA, which detect and correct impulsive and Gaussian noise, used over a medical image obtained from the mini-MIAS database that has been altered with impulsive and/or Gaussian noise. The aim of the study is verify if FPGA is a candidate to be used as a method to reduce the radiation dose in CT. Results show that FPGA outperforms the rest of the methods studied and it reveals itself as a good candidate to be employed in CT images to reduce the radiation dose., [ES] Las imágenes de Rayos-X o de tomografía computarizada (CT) pueden contener ruido debido al proceso de adquisición. Este ruido complica sustancialmente el proceso diagnóstico, por lo que será necesario el desarrollo de filtros efectivos. En este trabajo se estudia el comportamiento del filtro Fuzzy Peer Group Averaging (FPGA) sobre una colección de imágenes mamográficas que ha sido previamente contaminada con ruido impulsivo y gaussiano. El objetivo del trabajo es averiguar si FPGA es adecuado para la mejora de imágenes CT obtenidas con una dosis de radiación reducida. Los resultados indican que FPGA se comporta, efectivamente, mejor que el resto de métodos estudiados en este trabajo y por tanto resulta un candidato adecuado., This work was partially funded by ANITRAN PROMETEO/2010/039, the Spanish Ministry of Science and Innovation (Project TIN2008-06570-C04-04), and the spin-off Titania (Grupo Dominguis).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Simulación de los efectos de fármacos antiarrítmicos en la electrofisiología auricular

  • Puche-García, Violeta|||0000-0002-3386-1478
  • Romero Pérez, Lucia|||0000-0003-4605-8630
  • Saiz Rodríguez, Francisco Javier|||0000-0002-9850-0825
[ES] La terapia farmacológica es la primera línea contra la fibrilación auricular; aunque los mecanismos no se comprenden por completo. Nuestro objetivo es comparar datos experimentales a nivel unicelular de varios fármacos con la respuesta de tres modelos computacionales diferentes: Courtemanche (CRN), Grandi y Skibsbye (SKI) empleando un modelo de bloqueo de poro simple, así como una variante de modelo dinámico para los fármacos flecainida y vernakalant en CRN (+INa,Marvok). La mayoría de las simulaciones consiguen reproducir la dependencia del aumento del APD90 y la disminución de la dV/dtmax con la frecuencia y la concentración. Además, las respuestas de CRN, CRN+INa,Marvok y SKI reprodujeron de manera más adecuada las tendencias encontradas en los resultados experimentales. El análisis realizado contribuye a la mejora de la simulación de fármacos antiarrítmicos., Este trabajo ha sido financiado por el Programa Prometeo de la Generalitat Valenciana (2020/043) y por el programa de investigación e innovación Horizon 2020 de la Unión Europea bajo subvención No 101016496 (SimCardioTest).