Pasar al contenido principal

TECNICAS DE APRENDIZAJE PARA RESOLVER LA RECONSTRUCCION Y REGISTRO DEFORMABLES APLICADOS A IMAGENES DE LAPAROSCOPIA

PID2020-115995RB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ALCALA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Preliminary Unknown Appliance Detection using Convolutional Variational Auto-Encoders for AAL

  • Diego Otón, Laura De|||0000-0002-4939-2987
  • Fuentes Jiménez, David|||0000-0001-6424-4782
  • Pizarro Pérez, Daniel|||0000-0003-0622-4884
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Mari, Simone
  • Nieto Capuchino, Rubén|||0000-0002-8293-9665
2024 IEEE International Conference on Omni-layer Intelligent Systems (COINS), 29-31 July 2024, London, United Kingdom., The healthcare landscape is evolving, emphasising the importance of Active Assisted Living in addressing challenges presented by the ageing population. Integrating Non-Intrusive Load Monitoring provides insights into individual appliance usage patterns without additional sensors, enabling the detection of changes in daily activities that may reflect a person's health status. Within the effectiveness of this approach, adaptability is crucial as households evolve, discerning variations in energy consumption patterns caused by new or replaced electrical devices. For this reason, this work introduces a sophisticated hybrid approach combining deep learning and classic machine learning to classify household electrical loads and detect unknown loads using high-frequency electrical current signal data. Finally, while experimental results highlight areas for improvement, the findings suggest promising applications in household settings, marking a step forward in facing hurdles within the AAL context., Agencia Estatal de investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Towards automatic evaluation of human functional limitations: the EYEFUL project

  • Nieva Suárez, Álvaro|||0000-0003-3414-6721
  • Melino Carrero, Alessandro
  • Guardiola Luna, Irene|||0000-0002-5218-4361
  • Calvo del Castillo, Pablo
  • Monasterio Expósito, Leticia
  • Murillo Teruel, Marina
  • Martín Sánchez, José Luis|||0000-0001-9311-3511
  • Palazuelos Cagigas, Sira Elena|||0000-0002-2311-441X
  • Losada Gutiérrez, Cristina|||0000-0001-9545-327X
  • Marrón Romera, Marta|||0000-0001-7723-2262
  • Macías Guarasa, Javier|||0000-0002-3303-3963
  • Obeso Benítez, Paula
  • Hernández Hernández, Lucía
  • Redondo Cardeña, Beatriz
  • Yusta Ceacero, Aitor
  • Fernández Gómez, Gemma
  • Rodríguez Pérez, Pilar
  • García Bravo, Cristina
  • Serrada Tejeda, Sergio
  • Trugeda Pedrajo, Nuria
  • Morales Cabezas, Mª Matilde
  • Martínez Piédrola, Rosa María
  • Pérez de Heredia Torres, Marta
  • Valdez Disla, Leandro
30º Seminario Anual de Automática, Electrónica Industrial e Instrumentación (SAAEI 2023), 05/07/2023-07/07/2023, Sevilla, España., In this paper, the sensors deployment and data analysis for EYEFUL project are described, in order to generate a system for automatic human functional assessment. Human activity monitoring is a traditional topic of interest in different engineering areas, corresponding to the different applications and the sensorial systems used to tackle the task. In these extensive contexts, deep advances have been performed along the last decades, matching with the arrival of better sensors and processing technologies. Nowadays, artificial intelligence, machine learning, fast dedicated processors, as well as audiovisual cheap, small and precise sensors, and a huge amount of wearable systems available in the market have reinforced the solutions to this aim. In EYEFUL project, all of these different types of sensors are going to be used for human activity monitoring applied to the extraction of cues for analyzing the person performance of daily life activities, and in order to accomplish an assessment of its functional limitations. This aim is, as far as we know, still an open issue, although similar problems have recently opened other research lines, with audiovisual and wearables information (mainly in the context of smart cities and internet of things). The global architecture and methodology designed to tackle such problem in the sensible area of health, as well as the sensorial and processing system description, is included in the paper along with some preliminary results from the whole architecture deployed., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

SoC Architecture for High-Frequency Acquisition of Household Electric Signals

  • Navarro Pérez, Víctor Manuel
  • Diego Otón, Laura de|||0000-0002-4939-2987
  • Nieto Capuchino, Rubén|||0000-0002-8293-9665
  • Tapiador Luque, Miguel
  • Ureña Ureña, Jesús|||0000-0003-1408-6039
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC 2024), 20-23 May 2024, Glasgow, United Kingdom., Accurate monitoring of current and voltage in residential power grids is crucial for effective energy manage-ment and the implementation of smart technologies for non-intrusive monitoring of persons, especially those with cognitive or physical impairments. The emergence of high-speed analog-digital converters (ADCs) and wireless Internet-of-Things (IoT) devices has significantly improved measurement rates and realtime data collection capabilities, but the acquisition rates for the correct recognition of some devices in a non-intrusive load monitoring (NILM) aplication might still be insufficient. In order to address this issue, this work describes a System-on-Chip (SoC) architecture based on a Field-Programmable Gate Array (FPGA) and a dedicated analog conditioning circuit for household elec-tric signal acquisition. The architecture simultaneously captures voltage with a bandwidth ranging from 500 Hz to 100 kHz; and current signals from 300 Hz to 100 kHz. It is based on a Zybo z7-10 development platform along with an AD7476A ADC and a conditioning circuit, which consist of a filtering stage, an isolation transformer and a voltage-level adapter. The system is adequate for realtime household electric signal acquisition and processing, being able to capture high frequency harmonics correctly, while enabling the possible implementation of further processing, such as the integration of artificial neural networks and/or machine learning algorithms for event classification, load identification, and the implementation of an alarm system for behaviour anomalies., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Appliance Identification in NILM Applications by means of a Convolutional Auto-Encoder

  • Diego Otón, Laura de|||0000-0002-4939-2987
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • Pizarro Pérez, Daniel|||0000-0003-0622-4884
  • Nieto Capuchino, Rubén|||0000-0002-8293-9665
2023 IEEE International Workshop on Metrology for Living Environment (MetroLivEnv), 29-31 May 2023, Milano, Italy., In energy efficiency applications, Non-Intrusive Load Monitoring techniques (NILM) are typically used to deduce which electrical loads are being used in a building at a given time. The identification of household appliances, in particular manually operated ones, is relevant information that can also be applied to infer the routines of tenants in Active and Assisted Living environments (AAL). These tools and applications are becoming increasingly interesting, especially in Western countries, where the ageing population is putting a strain on public social and health services. In this context, this work aims to classify the on/off events of the devices considered in the BLUED database. For this purpose, an architecture is presented, consisting of a Convolutional Auto-Encoder (CAE) followed by a classifier neural network. The CAE is used to implement a dimensionality reduction process after the encoder. Input data are formatted as images, created with extracted sections of the high-frequency electric current signal captured around the switching events. It is noteworthy that this dimensionality reduction also allows a decrease in the computational load of the classifier. Regarding the CAE functionality, the reconstruction error reaches a value of 1.579 · 10−3, whereas in the validation stage a weighted average classification F1-score of 87 % is obtained for the whole architecture., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

An Open-Source VLBI Digital Backend for Low-Cost FPGA-based SoCs

  • Cubero Vacas, Miguel
  • Hernández Alonso, Álvaro|||0000-0001-9308-8133
  • González, Javier
DCIS2024: 39th Conference on Design of Circuits and Integrated Systems. Catania, Italy, November 13-15, 2024., Very Long Baseline Interferometry (VLBI) techniques have become crucial in radio astronomy and geodesy due to the major improvements that they provide to the observations, outcomes, at the expense of requiring a significant computational load to implement the corresponding processing in real time. The devices responsible for these digital signal processing tasks in the application field, mainly based on Field-Programmable Gate Arrays (FPGAs), are known as Digital Backends. Currently, the costs coming from the state-of-the-art digital backends are high and their FPGA designs either require expensive software licenses to be involved, or they are released as proprietary solutions. This work proposes a novel SoC (System-on-Chip) architecture, based on a Xilinx Zynq device, for a digital backend focused on VLBI applications. The architecture is capable of managing the acquisition stage at the required data rates, and packing data in the well-known VDIF format to upload them. By offering a low-cost open-source architecture, it becomes a suitable solution for dissemination purposes, as well as for specific research fields. Furthermore, the system has been successfully validated with its implementation and test in some preliminary experimental setups., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Object detection for functional assessment applications

  • Melino Carrero, Alessandro
  • Nieva Suárez, Álvaro|||0000-0003-3414-6721
  • Losada Gutiérrez, Cristina|||0000-0001-9545-327X
  • Marrón Romera, Marta|||0000-0001-7723-2262
  • Guardiola Luna, Irene|||0000-0002-5218-4361
  • Baeza Mas, Javier
Engineering Applications of Neural Networks, EANN 2023, This paper presents a proposal for object detection as a first stage for the analysis of Human-Object Interaction (HOI) in the context of automated functional assessment. The proposed system is based in a two-step strategy, thus, in the first stage there are detected the people in the scene, as well as large objects (table, chairs, etc.) using a pre-trained YOLOv8. Then, there is defined a ROI around each person that is processed using a custom YOLO to detect small elements (forks, plates, spoons, etc.). Since there are no large image datasets that include all the objects of interest, there has also been compiled a new dataset including images from different sets, and improving the available labels. The proposal has been evaluated in the novel dataset, and in different images acquired in the area in which the functional assessment is performed, obtaining promising results., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Gaze orientation to evaluate object interaction in human functional assessment

  • Nieva Suárez, Álvaro|||0000-0003-3414-6721
  • Marrón Romera, Marta|||0000-0001-7723-2262
  • Losada Gutiérrez, Cristina|||0000-0001-9545-327X
2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE), 19-21 June 2023, Helsinki, Finland., The paper goal is to identify what and where each person, in a RGB image, is looking at, and correctly handle the case where the gaze target is out-of-frame. Human-Gaze-Target (HGT) projects mainly focus on ?Where the person is looking at? on video-surveillance RGB images, but fail to exploit ?What the person is looking at? in such context. On this document, we present a video-processing workflow that takes that step, fusing an accurate HGT algorithm with an object detection one, and enhancing the resulting system for the application of interest. Concretely, we introduce an algorithm called ?Looking at whose function is transforming the HGT output into a shape comparable to that of the object detection standard algorithms. We also propose the inclusion of a preprocessing layer into the object detection algorithm, in order to increase its confidence on detecting small items, typically used in functional assessment evaluation tasks (such as silverware), that is the application of interest of this proposal. Finally, we generate and use a novel dataset for validating the global workflow proposed, that has been recorded in a specially adapted kitchen for the assessment task, the EYEFUL dataset, obtaining promising quantitative and qualitative results., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Action recognition for functional assessment applications

  • Nieva Suárez, Álvaro|||0000-0003-3414-6721
  • Calvo del Castillo, Pablo
  • Melino Carrero, Alessandro
  • Losada Gutiérrez, Cristina|||0000-0001-9545-327X
  • Marrón Romera, Marta|||0000-0001-7723-2262
  • Macías Guarasa, Javier|||0000-0002-3303-3963
  • Cob Parro, Antonio Carlos
30º Seminario Anual de Automática, Electrónica Industrial e Instrumentación (SAAEI 2023), 05/07/2023-07/07/2023, Sevilla, España., This paper presents two different Deep Learning (DL) proposals that have been proposed along with the specifically collected dataset GEFAD-HAR (GEintra Functional Assessment Dataset - Human Action Recognition) in order to extract action recognition information in the very special context of human functional assessment, that appeals in EYEFUL project (MICINN/AEI/10.13039/501100011033), in order to collaborate with professional occupational therapists within this subjective but important task. In the paper, the video dataset GEFADHAR is gathered from well known Human Activity Recognition (HAR) datasets, putting together videos of people performing actions required by occupational therapists to assess their patients functional capacity. The resulting GEFAD-HAR collection contains over 8000 videos, composing five different actions: squatting, sitting, falling, walking and standing. GEFAD-HAR videos have been selected from different public sources to keep and adapt such advantageous condition information for the application aimed. It must be emphasized that a meticulous manual data cleaning task has been performed within the dataset here presented, in order to have it well adapted to the application objective of interest, that to our knowledge has not been tackled like this in the state-of-the-art. Moreover, as mentioned, two different Deep Learning (DL) proposals are have also been recruited from the state-of-the art in order to propose a prove-ofconcept of the global automatic functional assessment algorithm pursued, within the data-gathered, with successful results that are also here presented. The global proposal (both the models and the database) will be published in the near future., Agencia Estatal de Investigación, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Contribución de congreso (ConferenceOutput)

Real-time weakly supervised anomaly detection with attention mechanism

  • Sarker, Mohammad Ibrahim
  • Marrón Romera, Marta|||0000-0001-7723-2262
  • Losada Gutiérrez, Cristina|||0000-0001-9545-327X
2023 International Conference on Information Network and Computer Communications (INCC), 27/10/2023-29/10/2023, Beijing, China., The use of surveillance cameras for ensuring the safety of people in public gatherings, e.g., roads, intersections, banks, shopping malls, etc., is being used increasingly in recent years. To detect violence and other abnormal behaviors from these surveillance videos, the monitoring, and detection need to be intelligent and precise. Manual monitoring of these videos is tiring and prone to errors. So automatic detection of video anomaly is a very important research topic nowadays. Although many methods have been proposed, research is still ongoing for a reliable method for violence detection. Most of the earlier state-of-the-art works suggest that supervised detection is better in anomaly detection than unsupervised one. However, given the difficulty of manually annotation and training large datasets for supervised learning, weakly supervised methods provide an excellent alternate solution. Generally, in weakly supervised learning, anomaly detection is constructed as a Multiple Instance Learning (MIL) problem. The base of that technique is to build the training model from labeled bags (comprising multiple instances) rather than labeled individual instances (in the computer vision branch: videos or frames). A bag is annotated as negative if all the instances are negative, while it is marked positive if at least one instance is positive. But the problem is that the recognition of positive instances is largely biased by the dominance of negative ones. As in the real world, abnormal events are very subtle, and the difference between normal and abnormal instances is minimal. Addressing this issue, this paper proposes a weakly supervised learning algorithm with an attention mechanism for anomalous events detection. Also, a novel ranking loss function is proposed to lessen the number of false negatives in the anomaly detection task and to extend the distance between classification scores of anomalous and normal videos in the learned model. Experimental results of this proposal within UCF-Crime and Shanghai-Tech datasets show that the proposed method outperforms state-of-the-art ones. Moreover, using an attention mechanism enhances feature extraction in the generated model inference. Finally, it is demonstrated that the proposal can be run in real-time, a contribution that can greatly impact real applications in the context of interest., Agencia Estatal de Investigación, Universidad de Alcalá