Skip to main content

APROVECHANDO LOS NUEVOS PARADIGMAS DE COMPUTO PARA LOS RETOS DE LA SOCIEDAD DIGITAL - UDL

TIN2017-84553-C2-2-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE LLEIDA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 38
Encontrada(s) 1 página(s)

Repositori Obert UdL
Publication Artículo científico (JournalArticle)

A queuing theory model for fog computing

  • Mas, Lluis
  • Vilaplana Mayoral, Jordi
  • Mateo Fornés, Jordi
  • Solsona Tehàs, Francesc
Under many scenarios where resources may be scarce or a good Quality of Service is a requirement, appropriately sizing components and devices is one of the main challenges. New scenarios, such as IoT, mobile cloud computing, mobile edge computing or fog computing, have emerged recently. The ability to design, model and simulate those infrastructures is critical to dimension them correctly. Queuing theory models provide a good approach to understanding how a given architecture would behave for a given set of parameters, thus helping to detect possible bottlenecks and performance issues in advance. This work presents a fog-computing modelling framework based on queuing theory. The proposed framework was used to simulate a given scenario allowing the possibility of adjusting the system by means of user-defned parameters. The results show that the proposed model is a good tool for designing optimal fog architectures regarding QoS requirements. It can also be used to fne-tune the designs to detect possible bottlenecks or improve the performance parameters of the overall environment., This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contract PID2020-113614RB-C22. Dr. Jordi Vilaplana is a Serra Húnter Fellow.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Detection of Bulbar Involvement in Patients With Amyotrophic Lateral Sclerosis by Machine Learning Voice Analysis: Diagnostic Decision Support Development Study

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Meister, Einar
  • Povedano, Mònica
Background: Bulbar involvement is a term used in amyotrophic lateral sclerosis (ALS) that refers to motor neuron impairment in the corticobulbar area of the brainstem, which produces a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar involvement is voice deterioration characterized by grossly defective articulation; extremely slow, laborious speech; marked hypernasality; and severe harshness. Bulbar involvement requires well-timed and carefully coordinated interventions. Therefore, early detection is crucial to improving the quality of life and lengthening the life expectancy of patients with ALS who present with this dysfunction. Recent research efforts have focused on voice analysis to capture bulbar involvement. Objective: The main objective of this paper was (1) to design a methodology for diagnosing bulbar involvement efficiently through the acoustic parameters of uttered vowels in Spanish, and (2) to demonstrate that the performance of the automated diagnosis of bulbar involvement is superior to human diagnosis. Methods: The study focused on the extraction of features from the phonatory subsystem—jitter, shimmer, harmonics-to-noise ratio, and pitch—from the utterance of the five Spanish vowels. Then, we used various supervised classification algorithms, preceded by principal component analysis of the features obtained. Results: To date, support vector machines have performed better (accuracy 95.8%) than the models analyzed in the related work. We also show how the model can improve human diagnosis, which can often misdiagnose bulbar involvement. Conclusions: The results obtained are very encouraging and demonstrate the efficiency and applicability of the automated model presented in this paper. It may be an appropriate tool to help in the diagnosis of ALS by multidisciplinary clinical teams, in particular to improve the diagnosis of bulbar involvement., This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R. Einar Meister’s research has been supported by the European Regional Development Fund through the Centre of Excellence in Estonian Studies. The Neurology Department of the Bellvitge University Hospital in Barcelona allowed the recording of the voices of the participants in its facilities. The clinical records were illustrated by Carlos Augusto Salazar Talavera. Dr Marta Fulla and Maria Carmen Majos Bellmunt advised about the process of eliciting the sounds.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

An Internet of Things Platform Based on Microservices and Cloud Paradigms for Livestock

  • Mateo Fornés, Jordi
  • Pagès Bernaus, Adela
  • Pla Aragonés, Lluís Miquel
  • Castells Gasia, Joan Pau
  • Babot Gaspa, Daniel
With the growing adoption of the Internet of Things (IoT) technology in the agricultural sector, smart devices are becoming more prevalent. The availability of new, timely, and precise data offers a great opportunity to develop advanced analytical models. Therefore, the platform used to deliver new developments to the final user is a key enabler for adopting IoT technology. This work presents a generic design of a software platform based on the cloud and implemented using microservices to facilitate the use of predictive or prescriptive analytics under different IoT scenarios. Several technologies are combined to comply with the essential features¿scalability, portability, interoperability, and usability¿that the platform must consider to assist decision-making in agricultural 4.0 contexts. The platform is prepared to integrate new sensor devices, perform data operations, integrate several data sources, transfer complex statistical model developments seamlessly, and provide a user-friendly graphical interface. The proposed software architecture is implemented with open-source technologies and validated in a smart farming scenario. The growth of a batch of pigs at the fattening stage is estimated from the data provided by a level sensor installed in the silo that stores the feed from which the animals are fed. With this application, we demonstrate how farmers can monitor the weight distribution and receive alarms when high deviations happen., This research was partially supported by the Intelligent Energy Europe (IEE) program and the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R, by the European Union FEDER (CAPAP-H6 network TIN2016-81840-REDT) and the demonstration activity financed by the Operation 01.02.01 of Technological Transfer from the Program of Rural Development in Catalunya 2014–2020 cofinanced by DARP and FEDER.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Increasing online shop revenues with web scraping: a case study for the wine sector

  • Jorge, Oriol
  • Pons, Adrià
  • Rius Torrentó, Josep Maria
  • Vintró Sánchez, Carla
  • Mateo Fornés, Jordi
  • Vilaplana Mayoral, Jordi
Purpose – Wine has been produced for thousands of years and nowadays we have seen a spread in the wine culture. E-commerce sales of wine have increased considerably and online customer’s satisfaction is influenced by quality and price. This paper presents a case study of the company “QuieroVinos, S.L.”, an online wine shop founded in 2015 that sells Spanish wines in two main marketplaces. Design/methodology/approach – With the final target of increasing the company profits it has been designed and developed an application to track the prices of competitors for a set of products. This information will be used to set the product prices in order to offer the products both competitively and profitably in each Marketplace. This application must check, by tacking into account information such as the product cost or the minimum product margin, if it is possible to decrease the price in order to reach the top cheapest position and as a consequence, increase the sales. Findings – The application improved in a notorious way the company’s results in terms of sales and shipping costs. It must be said that without the use of the presented application, performing the price comparison process within each one of the marketplaces would have taken a long time. Moreover, as prices change very frequently, the obtained information has a very limited time value, and the competitors prices should be analyzed daily in order to take accurate decisions regarding the company’s price policy. Originality/value – Although the application has been designed for the wine sector and the two named marketplace, it could be exported to other sectors. For that, it should be implemented new modules to collect information regarding the competitor’s price of the products selling on each corresponding marketplace, This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017- 84553-C2-2-R. Also, the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Managing quality, supplier selection, and cold-storage contracts in agrifood supply chain through stochastic optimization

  • Mateo Fornés, Jordi
  • Soto Silva, Wladimir Eduardo
  • González Araya, Marcela Cecilia
  • Pla Aragonés, Lluís Miquel
  • Solsona Tehàs, Francesc
The quality of such processed agrifood products as dehydrated apple is related to the quality and variety offresh harvested products and connected with wastage reduction throughout the agrifood supply chain. Forthis purpose, cold-storage management is important to avoid or mitigate the quality decay of fresh prod-ucts stored in refrigerated systems. This paper explores the benefits of a two-stage stochastic programmingmodel for product quality through the selection of producers and the management of cold storage to miti-gate deterioration and guarantee the maintenance of quality. A case study with real data from an agribusinesscompany is presented in the case study to illustrate and assess the suitability of the stochastic approach. Un-certainty regarding the conversion rate of fresh apples into the final dehydrated product and the purchasecost of the apples in the system are represented through scenarios generated from historical data. Recourseactions include the purchase of additional fruit and renting of additional cold stores to meet the demand.Based on the different scenarios, the value of the stochastic solution shows that modeling and solving theproposed stochastic model minimizes costs by an average of around 6.4%. In addition, the expected valueof perfect information demonstrates that using a proactive strategy could reduce costs by up to 9%. Theseresults ensure the applicability of this model in practice before and during the harvesting season for planningand replanning as uncertainty is revealed under a rolling horizon., The authors wish to acknowledge Marcos Oliva-Fernández for his valuable comments and sugges-tions and CYTED program for supporting the thematic network BigDSS-Agro (P515RT0123).D.Sc. Marcela González-Araya would like thank to FONDECYT Project 1191764 (Chile) forits financial support and D.Sc. Wladimir Soto-Silva would like to thank MEC Project 80180022(Chile). Moreover, this work was supported by the Ministerio de Economía y Competitividad un-der contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contractPID2020-113614RB-C22. Jordi Mateo and Francesc Solsona are members of the research group2017-SGR363 and Lluís M. Plà of 2017-SGR01193, funded by the Generalitat de Catalunya.Also, this research was partly supported by the European Union FEDER (CAPAP-H5 networkTIN2014-53522-REDT).
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Accurate consistency-based MSA reducing the memory footprint

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
  • Lérida Monsó, Josep Lluís
Background and Objective: The emergence of Next-Generation sequencing has created a push for faster and more accurate multiple sequence alignment tools. The growing number of sequences and their longer sizes, which require the use of increased system resources and produce less accurate results, are heavily challenging to these applications. Consistency-based methods have the most intensive CPU and memory usage requirements. We hypothesize that library reductions can enhance the scalability and performance of consistency-based multiple sequence alignment tools; however, we have previously shown a noticeable impact on the accuracy when extreme reductions were performed. Methods: In this study, we propose Matrix-Based T-Coffee, a consistency-based method that uses library reductions in conjunction with a complementary objective function. The proposed method, implemented in T-Coffee, can mitigate the accuracy loss caused by low memory resources. Results: The use of a complementary objective function with a library reduction of 30% improved the accuracy of T-Coffee. Interestingly, 50% library reduction achieved lower execution times and better overall scalability. Conclusions: Matrix-Based T-Coffee benefits from accurate alignments while achieving better scalability. This leads to a reduction in memory footprint and execution time. In addition, these enhancements could be applied to other aligners based on consistency., This work was supported by the MINECO-Spain under contracts TIN2017-84553-C2-2-R and PID2020-113614RB-C22.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Automated detection of COVID-19 cough

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
Easy detection of COVID-19 is a challenge. Quick biological tests do not give enough accuracy. Success in the fight against new outbreaks depends not only on the efficiency of the tests used, but also on the cost, time elapsed and the number of tests that can be done massively. Our proposal provides a solution to this challenge. The main objective is to design a freely available, quick and efficient methodology for the automatic detection of COVID-19 in raw audio files. Our proposal is based on automated extraction of time–frequency cough features and selection of the more significant ones to be used to diagnose COVID-19 using a supervised machine-learning algorithm. Random Forest has performed better than the other models analysed in this study. An accuracy close to 90% was obtained. This study demonstrates the feasibility of the automatic diagnose of COVID-19 from coughs, and its applicability to detecting new outbreaks., This work was supported by the Intelligent Energy Europe programme and the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contract PID2020-113614RB-C22. We thank Alfredo Jover and Maria Ramirez from the Functional Unit of Nosocomial Infections, and Cristina Acosta from the Internal Medicine, of the Arnau de Vilanova University Hospital in Lleida, who recorded coughs using the website covid.udl.cat. We also thank the University of Cambridge (in particular, Cecilia Mascolo), the Coswara and Virufy projects, who voluntary share their cough datasets. Finally, we also thank everyone who volunteered their cough.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Smart contract formation enabling energy-as-a-service in a virtual power plant

  • Mishra, Sambeet
  • Crasta, Cletus John
  • Bordin, Chiara
  • Mateo Fornés, Jordi
Energy as a service (EaaS) is an emerging business model that enables the otherwise passive energy consumers to play an active role and participate in the energy utility services. This platform is formed through smart contracts registering peer-to-peer (P2P) transactions of energy through price and quantity. Many industries, including finance, have already leveraged smart contracts to introduce digital currencies. At this time, the utility industry is faced with the challenge of how to structure smart contract formation in a local energy market. Specifically, they are faced with the challenge of maintaining a balance between energy generation and demand while enabling traceability, security, and unbiased peer-to-peer energy transactions, especially within a virtual power plant. This article aims at addressing the aforementioned challenges. In particular, this article investigates how to structure the microgrids in a local energy market, and how to ensure balance and resiliency with incomplete information. Taking various generation asset dimensions and demand profiles into account, simulations are performed. A novel evolutionary computing strategy to structure the simulation is proposed. A comparison is made among random order, random selection, profit-based ranking, and evolutionary strategy for coordinating the contract formation. The discussions draw attention to each method's advantages and disadvantages in terms of their value as a strategy for forming smart contracts in a local energy market., Eesti Teadusagentuur, Grant/Award Number: PUTJD915; Ministerio de Economia y Competitividad, Grant/Award Number: TIN2017-84553-C2-2-R; Ministerio de Ciencia e Innovacion, Grant/Award Number: PID2020-113614RB-C22
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Povedano, Mònica
Background and Objective: Bulbar dysfunction is a term used in amyotrophic lateral sclerosis (ALS). It refers to motor neuron disability in the corticobulbar area of the brainstem which leads to a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar dysfunction is voice deterioration characterized by grossly defective articulation, extremely slow laborious speech, marked hypernasality and severe harshness. Recently, research efforts have focused on voice analysis to capture this dysfunction. The main aim of this paper is to provide a new methodology to diagnose this dysfunction automatically at early stages of the disease, earlier than clinicians can do. Methods: The study focused on the creation of a voiceprint consisting of a pattern generated from the quasi-periodic components of a steady portion of the five Spanish vowels and the computation of the five principal and independent components of this pattern. Then, a set of statistically significant features was obtained using multivariate analysis of variance and the outcomes of the most common supervised classification models were obtained. Results: The best model (random forest) obtained an accuracy, sensitivity and specificity of 88.3%, 85.0% and 95.0% respectively when classifying bulbar vs. control participants but the results worsened when classifying bulbar vs. no-bulbar patients (accuracy, sensitivity and specificity of 78.7%, 80.0% and 77.5% respectively for support vector machines). Due to the great uncertainty found in the annotated corpus of the ALS patients without bulbar involvement, we used a safe semi-supervised support vector machine to relabel the ALS participants diagnosed without bulbar involvement as bulbar and no-bulbar. The performance of the results obtained increased, especially when classifying bulbar and no-bulbar patients obtaining an accuracy, sensitivity and specificity of 91.0%, 83.3% and 100.0% respectively for support vector machines. This demonstrates that our model can improve the diagnosis of bulbar dysfunction compared not only with clinicians, but also the methods published to date. Conclusions: The results obtained demonstrate the efficiency and applicability of the methodology presented in this paper. It may lead to the development of a cheap and easy-to-use tool to identify this dysfunction in early stages of the disease and monitor progress., This work was approved by the Research Ethics Committee for Biomedical Research Projects (CEIm) at the Bellvitge University Hospital in Barcelona and was supported by the Ministerio de Economía y Competitividad (TIN2017-84553-C2-2-R) and the Ministerio de Ciencia e Innovacion (PID2020-113614RBC22). AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-000797-S, funded by MCIN/AEI/10.13039/501100011033. The Neurology Department of the Bellvitge University Hospital in Barcelona permitted the recording of the voices of the participants in its facilities. The clinical records were provided by Carlos Augusto Salazar Talavera. Dr. Marta Fulla and Maria Carmen Majos Bellmunt contributed advice about the process of eliciting the sounds.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

The Use of Multiple Correspondence Analysis to Explore Associations between Categories of Qualitative Variables and Cancer Incidence

  • Florensa Cazorla, Dídac
  • Godoy i García, Pere
  • Mateo Fornés, Jordi
  • Solsona Tehàs, Francesc
  • Pedrol, Tere
  • Mesas, Miquel
  • Piñol, Ramon
Background: Previous works have shown that risk factors for some kinds of cancer depend on people's lifestyle (e.g. rural or urban residence). This article looks into this, seeking relationships between cancer, age group, gender and population in the region of Lleida (Catalonia, Spain) using Multiple Correspondence Analysis (MCA). Methods: The dataset analysed was made up of 3,408 cancer episodes between 2012 and 2014, extracted from the Population-based Cancer Registry (PCR) for Lleida province. The cancers studied were colon and rectal (1,059 cases), lung (551 cases), urinary bladder (446 cases), prostate (609 cases) and breast (743 cases). The MCA technique was applied and used to search relationships among the main qualitative features. The basic statistics were the percentage explaining (variance), the inertia and the contribution of each qualitative variable. Results: General outcomes showed a low and moderate contribution of living in rural areas to colorectal and male prostate cancer. Males in urban areas were slightly and heavily affected by lung and urinary bladder cancer respectively. The analysis of each cancer provided additional information. Colorectal cancer greatly affected males aged <60, urban residents aged 70-79, and rural females aged 80. The impact of lung cancer was high among urban females <60, moderate among males aged 70-79 and high among rural females aged 80. The results for urinary bladder cancer results were similar to those for lung cancer. Prostate cancer affected both the <60 and 80 age groups significantly in rural areas. Breast cancer hit the 70-79 group significantly and, somewhat less so, rural females aged 80. Conclusions: MCA was a significant help for detecting the contributions of qualitative variables and the associations between them. MCA has proven to be an effective technique for analyzing the incidence of cancer. The outcomes obtained help to corroborate suspected trends, as well as detecting and stimulating new hypotheses about the risk factors associated with a specific area and cancer. These findings will be helpful for encouraging new studies and prevention campaigns to highlight observed singularities., This work was supported by contract 2019-DI-43 of the Industrial Doctorate Program of the Government of Catalonia and by the Ministerio de Econom´ıa y Competitividad under contract TIN2017-84553-C2-2-R. Some of the authors are members of the research group 2014-SGR163, funded by the Generalitat de Catalunya.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

EasyModel: user-friendly tool for building and analysis of simple mathematical models in systems biology

  • Bartolome, Jordi
  • Alves, Rui
  • Solsona Tehàs, Francesc
  • Teixidó Torrelles, Ivan
EasyModel is a new user-friendly web application that contains ready-for-simulation versions of the BioModels Database, and allows for the intuitive creation of new models. Its main target audience is the experimental biologist and students of bioinformatics or systems biology without programming skills. Expert users can also benefit from it by implementing basic models quickly and downloading the code for further tailoring., This work was partially supported by Ministerio de Economia, Industria y Competitividad [TIN2017-84553-C2-2-R]; Ministerio de Educacion [PRX18/00142]; and by Bridge Grants from Universitat de Lleida and INSPIRES.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

EMPOWERING, a Smart Big Data Framework for Sustainable Electricity Suppliers

  • Mor Martínez, Gerard
  • Vilaplana Mayoral, Jordi
  • Danov, Stoyan
  • Cipriano, Jordi
  • Solsona Tehàs, Francesc
  • Chemisana Villegas, Daniel
This paper presents the EMPOWERING project, a Big Data environment aimed at helping domestic customers to save electricity by managing their consumption positively. This is achieved by improving the information received about energy bills and offering online tools. The main contributions of EMPOWERING are the creation of a novel workflow in the electricity utility sector regarding the implementation of data analytics for their customers and the fast implementation of data-mining techniques in massive datasets within a Big Data platform to achieve scalability. The results obtained show that EMPOWERING can be of use for customers of electrical suppliers by changing their energy habits to decrease consumption and so increase environmental sustainability., This work was supported in part by the Intelligent Energy Europe (IEE) Programme and the Ministerio de Economía y Competitividad under Contract TIN2017-84553-C2-2-R and in part by the European Union FEDER (CAPAP-H6 network) under Grant TIN2016-81840-REDT.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Performance and usability tradeoff in a cluster display wall

  • Arroyo Campos, Ismael
  • Giné, Francesc
  • Roig Mateu, Concepció
  • Granollers i Saltiveri, Toni
Cluster-based display walls provide cost-effective and scalable display infrastructures with high resolution and large display area, making them suitable for a wide range of high-resolution applications. As a consequence, a wide offer of new cluster display-wall platforms together with their software frameworks have been proposed. Their performance and the satisfaction of their users have aroused the interest of some researchers. This work is focused on the Liquid Galaxy cluster display wall originally built to run Google Earth to create an immersive experience for the users. In this paper, the Liquid Galaxy is benchmarked running Google Earth, as a representative interactive application with high performance requirements, in different configurations and environments, to test the satisfaction, effectiveness and efficiency. Thus, we wish to know how users react to the system performance. In order to do so, we use a performance metric defined in previous research to relate the performance of the system with the user’s perception. Taking into account the trend of this metric in the experimentation, we model the behavior of the system in a way that the performance for any given visualization cluster running Google Earth could be predicted by using a reference system., This work was supported by the MEyC under contracts TIN2014-53234-C2-2-R and TIN2017-84553-C2-2-R.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Scalable Consistency in T-Coffee Through Apache Spark and Cassandra Database

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
Next-generation sequencing, also known as high-throughput sequencing, has increased the volume of genetic data processed by sequencers. In the bioinformatic scientific area, highly rated multiple sequence alignment tools, such as MAFFT, ProbCons, and T-Coffee (TC), use the probabilistic consistency as a prior step to the progressive alignment stage to improve the final accuracy. However, such methods are severely limited by the memory required to store the consistency information. Big data processing and persistence techniques are used to manage and store the huge amount of information that is generated. Although these techniques have significant advantages, few biological applications have adopted them. In this article, a novel approach named big data tree-based consistency objective function for alignment evaluation (BDT-Coffee) is presented. BDT-Coffee is based on the integration of consistency information through Cassandra database in TC, previously generated by the MapReduce processing paradigm, to enable large data sets to be processed with the aim of improving the performance and scalability of the original algorithm., This work has been supported by the MEyC-Spain under contract Nos. TIN2014-53234-C2- 2-R and TIN2017-84553-C2-2-R.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Impact of Corporate Social Responsibility in mining industries

  • Pons, Adrià
  • Vintró Sánchez, Carla
  • Rius Torrentó, Josep Maria
  • Vilaplana Mayoral, Jordi
The mining sector plays a fundamental role in the global economy since it provides vital raw materials and energy for a large number of industries but mining activities are commonly criticized due to the effects on workers’ health and local communities, and are seen as a threat to society in general. For these reasons, companies have to deal with the compatibility between the productive activity and the Corporate Social Responsibility (CSR). Under this context, this paper aims to examine CSR communication in the mining sector on Twitter and identify the main topics of CSR and the main participants in the creation of content. A software framework has been developed in order to manage big text data in the study of CSR and sentiment computational content analysis to classify the tweets as positive, negative or neutral. Twitter was chosen since it is one of the three most commonly used social network sites by mining companies for information sharing and stakeholder engagement. The data collection period was from February 2019 to December 2019 and it resulted in 2,000,000 Twitter posts. The results show the CSR debate is increasingly growing in developing countries and in countries with a bad reputation of environmental and health mining conditions. The debate is mainly centered on the impact of mining industries on the land, and many stakeholders advocate for more environmental responsibility since they consider that mining activities are still controversial. Also, results reveal that the mining sector should improve the CSR disclosure and adopt a stakeholder engagement strategy grounded in the corporate stakeholder relationship perspective, the two-way symmetrical communication, and the dialogic theory of public relations. Social network sites such as Twitter can lead to positive outcomes for companies since they are not only a way to advertise what the company does with regards to CSR, but also to receive input from other for their CSR activities., This work was supported by the Ministerio de Economía y Com-petitividad under contract TIN2017-84553-C2-2-R. Also, the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya. Finally, we thank Victor Ferrer for his contribution
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

An Application of the IFM Method for the Risk Assessment of Financial Instruments

  • Pons, Adrià
  • Cristóbal Fransi, Eduard
  • Vintró Sánchez, Carla
  • Rius Torrentó, Josep Maria
  • Querol, Oriol
  • Vilaplana Mayoral, Jordi
External influences or behavioral biases can affect the way risk is perceived. This paper studies the prediction of VaR (Value at Risk) as a measure of the risk of loss for investments on financial products. Our aim is to predict the percentage of loss that a financial product would have in the future to assess the risks and determine the potential loss of a security in the stock market, thus reducing reasoning influenced by feelings for bank and financial firms seeking to deploy AI and advanced automation. We used the IFM (inference function for margins) method in different market scenarios, with particular emphasis on the strengths and weaknesses of it. The study is assessed on single product level with the skewed studen-t GARCH(1,1) model and portfolio level with t-copulas for the inter-dependencies. It has been shown that under normal market conditions the risk is predicted properly for both levels. However, when an unexpected market event occurs, the prediction fails. To address this limitation, a combined model with sentiment analysis and regression is proposed for further investigation as a future work., The authors are pleased to acknowledge the support of the Spanish Ministry of Economy, Industry and Competitiveness (Grant id.: TURCOLAB ECO2017-88984-R). Also, this work was supported by the Spanish Ministry of Economy and Competitiveness under contract TIN2017-84553- C2-2-R. Finally, some of the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Detecting Bulbar Involvement in Patients with Amyotrophic Lateral Sclerosis Based on Phonatory and Time-Frequency Features

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Povedano, Mònica
The term “bulbar involvement” is employed in ALS to refer to deterioration of motor neurons within the corticobulbar area of the brainstem, which results in speech and swallowing dysfunctions. One of the primary symptoms is a deterioration of the voice. Early detection is crucial for improving the quality of life and lifespan of ALS patients suffering from bulbar involvement. The main objective, and the principal contribution, of this research, was to design a new methodology, based on the phonatory-subsystem and time-frequency characteristics for detecting bulbar involvement automatically. This study focused on providing a set of 50 phonatory-subsystem and time-frequency features to detect this deficiency in males and females through the utterance of the five Spanish vowels. Multivariant Analysis of Variance was then used to select the statistically significant features, and the most common supervised classifications models were analyzed. A set of statistically significant features was obtained for males and females to capture this dysfunction. To date, the accuracy obtained (98.01% for females and 96.10% for males employing a random forest) outperformed the models in the literature. Adding time-frequency features to more classical phonatory-subsystem features increases the prediction capabilities of the machine-learning models for detecting bulbar involvement. Studying men and women separately gives greater success. The proposed method can be deployed in any kind of recording device (i.e., smartphone)., This research was funded by the Spanish Ministerio de Economía, Industria y Competitividad and the Ministerio de Ciencia e Innovación under contracts TIN2017-84553-C2-2-R and PID2020- 113614RB-C22, respectively. AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-000797-S, funded by MCIN/AEI/10.13039/501100011033.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Optimization of Consistency-Based Multiple Sequence Alignment using Big Data technologies

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
With the advent of new high-throughput next-generation sequencing technologies, the volume of genetic data processed has increased significantly. It is becoming essential for these applications to achieve large-scale alignments with thousands of sequences or even whole genomes. However, all current MSA tools have exhibited scalability issues when the number of sequences increases. The main drawback of these methods is that errors made in early pairwise alignments are propagated to the nal result, a ecting the accuracy of the global alignment. The use of consistency information enables the nal result to be improved and makes it more stable from the accuracy point of view. However, such methods are severely limited by the memory required to store the consistency information. Authors in a previous work analyzed the structure and distribution of the data stored in the constraint library and demonstrated that it could be possible to reduce it without loosing accuracy and thus it is possible to increase the number of sequences to be aligned. However, the execution time for obtaining the constraint library for a bigger number of sequences also increases greatly. In the present paper, the authors apply Big Data technologies to take advantage of the high degree of parallelism provided by the MapReduce paradigm in order to reduce considerably the library calculation time. Moreover, Big Data infrastructure provides a distributed storage system to improve the library scalability and machine-learning algorithms to enhance the consistency selection policies., This work has been supported by the MEyC-Spain under contract TIN2014-53234-C2-2-R, TIN2017-84553-C2-2-R and TIN2016-81840-REDT.
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

  • Tena, Alberto
  • Clarià, Francesc
  • Solsona, Francesc
  • Povedano, Mónica
Background and Objective: Bulbar dysfunction is a term used in amyotrophic lateral sclerosis (ALS). It refers to motor neuron disability in the corticobulbar area of the brainstem which leads to a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar dysfunction is voice deterioration characterized by grossly defective articulation, extremely slow laborious speech, marked hypernasality and severe harshness. Recently, research efforts have focused on voice analysis to capture this dysfunction. The main aim of this paper is to provide a new methodology to diagnose this dysfunction automatically at early stages of the disease, earlier than clinicians can do. Methods: The study focused on the creation of a voiceprint consisting of a pattern generated from the quasi-periodic components of a steady portion of the five Spanish vowels and the computation of the five principal and independent components of this pattern. Then, a set of statistically significant features was obtained using multivariate analysis of variance and the outcomes of the most common supervised classification models were obtained. Results: The best model (random forest) obtained an accuracy, sensitivity and specificity of 88.3%, 85.0% and 95.0% respectively when classifying bulbar vs. control participants but the results worsened when classifying bulbar vs. no-bulbar patients (accuracy, sensitivity and specificity of 78.7%, 80.0% and 77.5% respectively for support vector machines). Due to the great uncertainty found in the annotated corpus of the ALS patients without bulbar involvement, we used a safe semi-supervised support vector machine to relabel the ALS participants diagnosed without bulbar involvement as bulbar and no-bulbar. The performance of the results obtained increased, especially when classifying bulbar and no-bulbar patients obtaining an accuracy, sensitivity and specificity of 91.0%, 83.3% and 100.0% respectively for support vector machines. This demonstrates that our model can improve the diagnosis of bulbar dysfunction compared not only with clinicians, but also the methods published to date. Conclusions: The results obtained demonstrate the efficiency and applicability of the methodology presented in this paper. It may lead to the development of a cheap and easy-to-use tool to identify this dysfunction in early stages of the disease and monitor progress., This work was approved by the Research Ethics Committee for Biomedical Research Projects (CEIm) at the Bellvitge University Hospital in Barcelona and was supported by the Ministerio de Economía y Competitividad (TIN2017-84553-C2-2-R) and the Ministerio de Ciencia e Innovacion (PID2020-113614RBC22). AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-0 0 0797-S, funded by MCIN/AEI/10.13039/50110 0 011033., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Impact of Corporate Social Responsibility in mining industries

  • Pons, Adrià
  • Vintró Sánchez, Carla
  • Rius Torrentó, Josep Maria
  • Vilaplana Mayoral, Jordi
The mining sector plays a fundamental role in the global economy since it provides vital raw materials and energy for a large number of industries but mining activities are commonly criticized due to the effects on workers’ health and local communities, and are seen as a threat to society in general. For these reasons, companies have to deal with the compatibility between the productive activity and the Corporate Social Responsibility (CSR). Under this context, this paper aims to examine CSR communication in the mining sector on Twitter and identify the main topics of CSR and the main participants in the creation of content. A software framework has been developed in order to manage big text data in the study of CSR and sentiment computational content analysis to classify the tweets as positive, negative or neutral. Twitter was chosen since it is one of the three most commonly used social network sites by mining companies for information sharing and stakeholder engagement. The data collection period was from February 2019 to December 2019 and it resulted in 2,000,000 Twitter posts. The results show the CSR debate is increasingly growing in developing countries and in countries with a bad reputation of environmental and health mining conditions. The debate is mainly centered on the impact of mining industries on the land, and many stakeholders advocate for more environmental responsibility since they consider that mining activities are still controversial. Also, results reveal that the mining sector should improve the CSR disclosure and adopt a stakeholder engagement strategy grounded in the corporate stakeholder relationship perspective, the two-way symmetrical communication, and the dialogic theory of public relations. Social network sites such as Twitter can lead to positive outcomes for companies since they are not only a way to advertise what the company does with regards to CSR, but also to receive input from other for their CSR activities., This work was supported by the Ministerio de Economía y Com-petitividad under contract TIN2017-84553-C2-2-R. Also, the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya. Finally, we thank Victor Ferrer for his contribution
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Detecting Bulbar Involvement in Patients with Amyotrophic Lateral Sclerosis Based on Phonatory and Time-Frequency Features

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Povedano, Mònica
The term “bulbar involvement” is employed in ALS to refer to deterioration of motor neurons within the corticobulbar area of the brainstem, which results in speech and swallowing dysfunctions. One of the primary symptoms is a deterioration of the voice. Early detection is crucial for improving the quality of life and lifespan of ALS patients suffering from bulbar involvement. The main objective, and the principal contribution, of this research, was to design a new methodology, based on the phonatory-subsystem and time-frequency characteristics for detecting bulbar involvement automatically. This study focused on providing a set of 50 phonatory-subsystem and time-frequency features to detect this deficiency in males and females through the utterance of the five Spanish vowels. Multivariant Analysis of Variance was then used to select the statistically significant features, and the most common supervised classifications models were analyzed. A set of statistically significant features was obtained for males and females to capture this dysfunction. To date, the accuracy obtained (98.01% for females and 96.10% for males employing a random forest) outperformed the models in the literature. Adding time-frequency features to more classical phonatory-subsystem features increases the prediction capabilities of the machine-learning models for detecting bulbar involvement. Studying men and women separately gives greater success. The proposed method can be deployed in any kind of recording device (i.e., smartphone)., This research was funded by the Spanish Ministerio de Economía, Industria y Competitividad and the Ministerio de Ciencia e Innovación under contracts TIN2017-84553-C2-2-R and PID2020- 113614RB-C22, respectively. AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-000797-S, funded by MCIN/AEI/10.13039/501100011033.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Managing quality, supplier selection, and cold-storage contracts in agrifood supply chain through stochastic optimization

  • Mateo Fornés, Jordi
  • Soto Silva, Wladimir Eduardo
  • González Araya, Marcela Cecilia
  • Pla Aragonés, Lluís Miquel
  • Solsona Tehàs, Francesc
The quality of such processed agrifood products as dehydrated apple is related to the quality and variety offresh harvested products and connected with wastage reduction throughout the agrifood supply chain. Forthis purpose, cold-storage management is important to avoid or mitigate the quality decay of fresh prod-ucts stored in refrigerated systems. This paper explores the benefits of a two-stage stochastic programmingmodel for product quality through the selection of producers and the management of cold storage to miti-gate deterioration and guarantee the maintenance of quality. A case study with real data from an agribusinesscompany is presented in the case study to illustrate and assess the suitability of the stochastic approach. Un-certainty regarding the conversion rate of fresh apples into the final dehydrated product and the purchasecost of the apples in the system are represented through scenarios generated from historical data. Recourseactions include the purchase of additional fruit and renting of additional cold stores to meet the demand.Based on the different scenarios, the value of the stochastic solution shows that modeling and solving theproposed stochastic model minimizes costs by an average of around 6.4%. In addition, the expected valueof perfect information demonstrates that using a proactive strategy could reduce costs by up to 9%. Theseresults ensure the applicability of this model in practice before and during the harvesting season for planningand replanning as uncertainty is revealed under a rolling horizon., The authors wish to acknowledge Marcos Oliva-Fernández for his valuable comments and sugges-tions and CYTED program for supporting the thematic network BigDSS-Agro (P515RT0123).D.Sc. Marcela González-Araya would like thank to FONDECYT Project 1191764 (Chile) forits financial support and D.Sc. Wladimir Soto-Silva would like to thank MEC Project 80180022(Chile). Moreover, this work was supported by the Ministerio de Economía y Competitividad un-der contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contractPID2020-113614RB-C22. Jordi Mateo and Francesc Solsona are members of the research group2017-SGR363 and Lluís M. Plà of 2017-SGR01193, funded by the Generalitat de Catalunya.Also, this research was partly supported by the European Union FEDER (CAPAP-H5 networkTIN2014-53522-REDT).
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Scalable Consistency in T-Coffee Through Apache Spark and Cassandra Database

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
Next-generation sequencing, also known as high-throughput sequencing, has increased the volume of genetic data processed by sequencers. In the bioinformatic scientific area, highly rated multiple sequence alignment tools, such as MAFFT, ProbCons, and T-Coffee (TC), use the probabilistic consistency as a prior step to the progressive alignment stage to improve the final accuracy. However, such methods are severely limited by the memory required to store the consistency information. Big data processing and persistence techniques are used to manage and store the huge amount of information that is generated. Although these techniques have significant advantages, few biological applications have adopted them. In this article, a novel approach named big data tree-based consistency objective function for alignment evaluation (BDT-Coffee) is presented. BDT-Coffee is based on the integration of consistency information through Cassandra database in TC, previously generated by the MapReduce processing paradigm, to enable large data sets to be processed with the aim of improving the performance and scalability of the original algorithm., This work has been supported by the MEyC-Spain under contract Nos. TIN2014-53234-C2- 2-R and TIN2017-84553-C2-2-R.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

The Use of Multiple Correspondence Analysis to Explore Associations between Categories of Qualitative Variables and Cancer Incidence

  • Florensa Cazorla, Dídac
  • Godoy i García, Pere
  • Mateo Fornés, Jordi
  • Solsona Tehàs, Francesc
  • Pedrol, Tere
  • Mesas, Miquel
  • Piñol, Ramon
Background: Previous works have shown that risk factors for some kinds of cancer depend on people's lifestyle (e.g. rural or urban residence). This article looks into this, seeking relationships between cancer, age group, gender and population in the region of Lleida (Catalonia, Spain) using Multiple Correspondence Analysis (MCA). Methods: The dataset analysed was made up of 3,408 cancer episodes between 2012 and 2014, extracted from the Population-based Cancer Registry (PCR) for Lleida province. The cancers studied were colon and rectal (1,059 cases), lung (551 cases), urinary bladder (446 cases), prostate (609 cases) and breast (743 cases). The MCA technique was applied and used to search relationships among the main qualitative features. The basic statistics were the percentage explaining (variance), the inertia and the contribution of each qualitative variable. Results: General outcomes showed a low and moderate contribution of living in rural areas to colorectal and male prostate cancer. Males in urban areas were slightly and heavily affected by lung and urinary bladder cancer respectively. The analysis of each cancer provided additional information. Colorectal cancer greatly affected males aged <60, urban residents aged 70-79, and rural females aged 80. The impact of lung cancer was high among urban females <60, moderate among males aged 70-79 and high among rural females aged 80. The results for urinary bladder cancer results were similar to those for lung cancer. Prostate cancer affected both the <60 and 80 age groups significantly in rural areas. Breast cancer hit the 70-79 group significantly and, somewhat less so, rural females aged 80. Conclusions: MCA was a significant help for detecting the contributions of qualitative variables and the associations between them. MCA has proven to be an effective technique for analyzing the incidence of cancer. The outcomes obtained help to corroborate suspected trends, as well as detecting and stimulating new hypotheses about the risk factors associated with a specific area and cancer. These findings will be helpful for encouraging new studies and prevention campaigns to highlight observed singularities., This work was supported by contract 2019-DI-43 of the Industrial Doctorate Program of the Government of Catalonia and by the Ministerio de Econom´ıa y Competitividad under contract TIN2017-84553-C2-2-R. Some of the authors are members of the research group 2014-SGR163, funded by the Generalitat de Catalunya.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Detection of Bulbar Involvement in Patients With Amyotrophic Lateral Sclerosis by Machine Learning Voice Analysis: Diagnostic Decision Support Development Study

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Meister, Einar
  • Povedano, Mònica
Background: Bulbar involvement is a term used in amyotrophic lateral sclerosis (ALS) that refers to motor neuron impairment in the corticobulbar area of the brainstem, which produces a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar involvement is voice deterioration characterized by grossly defective articulation; extremely slow, laborious speech; marked hypernasality; and severe harshness. Bulbar involvement requires well-timed and carefully coordinated interventions. Therefore, early detection is crucial to improving the quality of life and lengthening the life expectancy of patients with ALS who present with this dysfunction. Recent research efforts have focused on voice analysis to capture bulbar involvement. Objective: The main objective of this paper was (1) to design a methodology for diagnosing bulbar involvement efficiently through the acoustic parameters of uttered vowels in Spanish, and (2) to demonstrate that the performance of the automated diagnosis of bulbar involvement is superior to human diagnosis. Methods: The study focused on the extraction of features from the phonatory subsystem—jitter, shimmer, harmonics-to-noise ratio, and pitch—from the utterance of the five Spanish vowels. Then, we used various supervised classification algorithms, preceded by principal component analysis of the features obtained. Results: To date, support vector machines have performed better (accuracy 95.8%) than the models analyzed in the related work. We also show how the model can improve human diagnosis, which can often misdiagnose bulbar involvement. Conclusions: The results obtained are very encouraging and demonstrate the efficiency and applicability of the automated model presented in this paper. It may be an appropriate tool to help in the diagnosis of ALS by multidisciplinary clinical teams, in particular to improve the diagnosis of bulbar involvement., This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R. Einar Meister’s research has been supported by the European Regional Development Fund through the Centre of Excellence in Estonian Studies. The Neurology Department of the Bellvitge University Hospital in Barcelona allowed the recording of the voices of the participants in its facilities. The clinical records were illustrated by Carlos Augusto Salazar Talavera. Dr Marta Fulla and Maria Carmen Majos Bellmunt advised about the process of eliciting the sounds.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

An Application of the IFM Method for the Risk Assessment of Financial Instruments

  • Pons, Adrià
  • Cristóbal Fransi, Eduard
  • Vintró Sánchez, Carla
  • Rius Torrentó, Josep Maria
  • Querol, Oriol
  • Vilaplana Mayoral, Jordi
External influences or behavioral biases can affect the way risk is perceived. This paper studies the prediction of VaR (Value at Risk) as a measure of the risk of loss for investments on financial products. Our aim is to predict the percentage of loss that a financial product would have in the future to assess the risks and determine the potential loss of a security in the stock market, thus reducing reasoning influenced by feelings for bank and financial firms seeking to deploy AI and advanced automation. We used the IFM (inference function for margins) method in different market scenarios, with particular emphasis on the strengths and weaknesses of it. The study is assessed on single product level with the skewed studen-t GARCH(1,1) model and portfolio level with t-copulas for the inter-dependencies. It has been shown that under normal market conditions the risk is predicted properly for both levels. However, when an unexpected market event occurs, the prediction fails. To address this limitation, a combined model with sentiment analysis and regression is proposed for further investigation as a future work., The authors are pleased to acknowledge the support of the Spanish Ministry of Economy, Industry and Competitiveness (Grant id.: TURCOLAB ECO2017-88984-R). Also, this work was supported by the Spanish Ministry of Economy and Competitiveness under contract TIN2017-84553- C2-2-R. Finally, some of the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

A queuing theory model for fog computing

  • Mas, Lluis
  • Vilaplana Mayoral, Jordi
  • Mateo Fornés, Jordi
  • Solsona Tehàs, Francesc
Under many scenarios where resources may be scarce or a good Quality of Service is a requirement, appropriately sizing components and devices is one of the main challenges. New scenarios, such as IoT, mobile cloud computing, mobile edge computing or fog computing, have emerged recently. The ability to design, model and simulate those infrastructures is critical to dimension them correctly. Queuing theory models provide a good approach to understanding how a given architecture would behave for a given set of parameters, thus helping to detect possible bottlenecks and performance issues in advance. This work presents a fog-computing modelling framework based on queuing theory. The proposed framework was used to simulate a given scenario allowing the possibility of adjusting the system by means of user-defned parameters. The results show that the proposed model is a good tool for designing optimal fog architectures regarding QoS requirements. It can also be used to fne-tune the designs to detect possible bottlenecks or improve the performance parameters of the overall environment., This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contract PID2020-113614RB-C22. Dr. Jordi Vilaplana is a Serra Húnter Fellow.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Smart contract formation enabling energy-as-a-service in a virtual power plant

  • Mishra, Sambeet
  • Crasta, Cletus John
  • Bordin, Chiara
  • Mateo Fornés, Jordi
Energy as a service (EaaS) is an emerging business model that enables the otherwise passive energy consumers to play an active role and participate in the energy utility services. This platform is formed through smart contracts registering peer-to-peer (P2P) transactions of energy through price and quantity. Many industries, including finance, have already leveraged smart contracts to introduce digital currencies. At this time, the utility industry is faced with the challenge of how to structure smart contract formation in a local energy market. Specifically, they are faced with the challenge of maintaining a balance between energy generation and demand while enabling traceability, security, and unbiased peer-to-peer energy transactions, especially within a virtual power plant. This article aims at addressing the aforementioned challenges. In particular, this article investigates how to structure the microgrids in a local energy market, and how to ensure balance and resiliency with incomplete information. Taking various generation asset dimensions and demand profiles into account, simulations are performed. A novel evolutionary computing strategy to structure the simulation is proposed. A comparison is made among random order, random selection, profit-based ranking, and evolutionary strategy for coordinating the contract formation. The discussions draw attention to each method's advantages and disadvantages in terms of their value as a strategy for forming smart contracts in a local energy market., Eesti Teadusagentuur, Grant/Award Number: PUTJD915; Ministerio de Economia y Competitividad, Grant/Award Number: TIN2017-84553-C2-2-R; Ministerio de Ciencia e Innovacion, Grant/Award Number: PID2020-113614RB-C22
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

  • Tena, Alberto
  • Clarià, Francesc
  • Solsona, Francesc
  • Povedano, Mónica
Background and Objective: Bulbar dysfunction is a term used in amyotrophic lateral sclerosis (ALS). It refers to motor neuron disability in the corticobulbar area of the brainstem which leads to a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar dysfunction is voice deterioration characterized by grossly defective articulation, extremely slow laborious speech, marked hypernasality and severe harshness. Recently, research efforts have focused on voice analysis to capture this dysfunction. The main aim of this paper is to provide a new methodology to diagnose this dysfunction automatically at early stages of the disease, earlier than clinicians can do. Methods: The study focused on the creation of a voiceprint consisting of a pattern generated from the quasi-periodic components of a steady portion of the five Spanish vowels and the computation of the five principal and independent components of this pattern. Then, a set of statistically significant features was obtained using multivariate analysis of variance and the outcomes of the most common supervised classification models were obtained. Results: The best model (random forest) obtained an accuracy, sensitivity and specificity of 88.3%, 85.0% and 95.0% respectively when classifying bulbar vs. control participants but the results worsened when classifying bulbar vs. no-bulbar patients (accuracy, sensitivity and specificity of 78.7%, 80.0% and 77.5% respectively for support vector machines). Due to the great uncertainty found in the annotated corpus of the ALS patients without bulbar involvement, we used a safe semi-supervised support vector machine to relabel the ALS participants diagnosed without bulbar involvement as bulbar and no-bulbar. The performance of the results obtained increased, especially when classifying bulbar and no-bulbar patients obtaining an accuracy, sensitivity and specificity of 91.0%, 83.3% and 100.0% respectively for support vector machines. This demonstrates that our model can improve the diagnosis of bulbar dysfunction compared not only with clinicians, but also the methods published to date. Conclusions: The results obtained demonstrate the efficiency and applicability of the methodology presented in this paper. It may lead to the development of a cheap and easy-to-use tool to identify this dysfunction in early stages of the disease and monitor progress., This work was approved by the Research Ethics Committee for Biomedical Research Projects (CEIm) at the Bellvitge University Hospital in Barcelona and was supported by the Ministerio de Economía y Competitividad (TIN2017-84553-C2-2-R) and the Ministerio de Ciencia e Innovacion (PID2020-113614RBC22). AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-0 0 0797-S, funded by MCIN/AEI/10.13039/50110 0 011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

EMPOWERING, a Smart Big Data Framework for Sustainable Electricity Suppliers

  • Mor Martínez, Gerard
  • Vilaplana Mayoral, Jordi
  • Danov, Stoyan
  • Cipriano, Jordi
  • Solsona Tehàs, Francesc
  • Chemisana Villegas, Daniel
This paper presents the EMPOWERING project, a Big Data environment aimed at helping domestic customers to save electricity by managing their consumption positively. This is achieved by improving the information received about energy bills and offering online tools. The main contributions of EMPOWERING are the creation of a novel workflow in the electricity utility sector regarding the implementation of data analytics for their customers and the fast implementation of data-mining techniques in massive datasets within a Big Data platform to achieve scalability. The results obtained show that EMPOWERING can be of use for customers of electrical suppliers by changing their energy habits to decrease consumption and so increase environmental sustainability., This work was supported in part by the Intelligent Energy Europe (IEE) Programme and the Ministerio de Economía y Competitividad under Contract TIN2017-84553-C2-2-R and in part by the European Union FEDER (CAPAP-H6 network) under Grant TIN2016-81840-REDT.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

An Internet of Things Platform Based on Microservices and Cloud Paradigms for Livestock

  • Mateo Fornés, Jordi
  • Pagès Bernaus, Adela
  • Pla Aragonés, Lluís Miquel
  • Castells Gasia, Joan Pau
  • Babot Gaspa, Daniel
With the growing adoption of the Internet of Things (IoT) technology in the agricultural sector, smart devices are becoming more prevalent. The availability of new, timely, and precise data offers a great opportunity to develop advanced analytical models. Therefore, the platform used to deliver new developments to the final user is a key enabler for adopting IoT technology. This work presents a generic design of a software platform based on the cloud and implemented using microservices to facilitate the use of predictive or prescriptive analytics under different IoT scenarios. Several technologies are combined to comply with the essential features¿scalability, portability, interoperability, and usability¿that the platform must consider to assist decision-making in agricultural 4.0 contexts. The platform is prepared to integrate new sensor devices, perform data operations, integrate several data sources, transfer complex statistical model developments seamlessly, and provide a user-friendly graphical interface. The proposed software architecture is implemented with open-source technologies and validated in a smart farming scenario. The growth of a batch of pigs at the fattening stage is estimated from the data provided by a level sensor installed in the silo that stores the feed from which the animals are fed. With this application, we demonstrate how farmers can monitor the weight distribution and receive alarms when high deviations happen., This research was partially supported by the Intelligent Energy Europe (IEE) program and the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R, by the European Union FEDER (CAPAP-H6 network TIN2016-81840-REDT) and the demonstration activity financed by the Operation 01.02.01 of Technological Transfer from the Program of Rural Development in Catalunya 2014–2020 cofinanced by DARP and FEDER.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Accurate consistency-based MSA reducing the memory footprint

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
  • Lérida Monsó, Josep Lluís
Background and Objective: The emergence of Next-Generation sequencing has created a push for faster and more accurate multiple sequence alignment tools. The growing number of sequences and their longer sizes, which require the use of increased system resources and produce less accurate results, are heavily challenging to these applications. Consistency-based methods have the most intensive CPU and memory usage requirements. We hypothesize that library reductions can enhance the scalability and performance of consistency-based multiple sequence alignment tools; however, we have previously shown a noticeable impact on the accuracy when extreme reductions were performed. Methods: In this study, we propose Matrix-Based T-Coffee, a consistency-based method that uses library reductions in conjunction with a complementary objective function. The proposed method, implemented in T-Coffee, can mitigate the accuracy loss caused by low memory resources. Results: The use of a complementary objective function with a library reduction of 30% improved the accuracy of T-Coffee. Interestingly, 50% library reduction achieved lower execution times and better overall scalability. Conclusions: Matrix-Based T-Coffee benefits from accurate alignments while achieving better scalability. This leads to a reduction in memory footprint and execution time. In addition, these enhancements could be applied to other aligners based on consistency., This work was supported by the MINECO-Spain under contracts TIN2017-84553-C2-2-R and PID2020-113614RB-C22.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Automated detection of COVID-19 cough

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
Easy detection of COVID-19 is a challenge. Quick biological tests do not give enough accuracy. Success in the fight against new outbreaks depends not only on the efficiency of the tests used, but also on the cost, time elapsed and the number of tests that can be done massively. Our proposal provides a solution to this challenge. The main objective is to design a freely available, quick and efficient methodology for the automatic detection of COVID-19 in raw audio files. Our proposal is based on automated extraction of time–frequency cough features and selection of the more significant ones to be used to diagnose COVID-19 using a supervised machine-learning algorithm. Random Forest has performed better than the other models analysed in this study. An accuracy close to 90% was obtained. This study demonstrates the feasibility of the automatic diagnose of COVID-19 from coughs, and its applicability to detecting new outbreaks., This work was supported by the Intelligent Energy Europe programme and the Ministerio de Economía y Competitividad under contract TIN2017-84553-C2-2-R and the Ministerio de Ciencia e Innovación under contract PID2020-113614RB-C22. We thank Alfredo Jover and Maria Ramirez from the Functional Unit of Nosocomial Infections, and Cristina Acosta from the Internal Medicine, of the Arnau de Vilanova University Hospital in Lleida, who recorded coughs using the website covid.udl.cat. We also thank the University of Cambridge (in particular, Cecilia Mascolo), the Coswara and Virufy projects, who voluntary share their cough datasets. Finally, we also thank everyone who volunteered their cough.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

EasyModel: user-friendly tool for building and analysis of simple mathematical models in systems biology

  • Bartolome, Jordi
  • Alves, Rui
  • Solsona Tehàs, Francesc
  • Teixidó Torrelles, Ivan
EasyModel is a new user-friendly web application that contains ready-for-simulation versions of the BioModels Database, and allows for the intuitive creation of new models. Its main target audience is the experimental biologist and students of bioinformatics or systems biology without programming skills. Expert users can also benefit from it by implementing basic models quickly and downloading the code for further tailoring., This work was partially supported by Ministerio de Economia, Industria y Competitividad [TIN2017-84553-C2-2-R]; Ministerio de Educacion [PRX18/00142]; and by Bridge Grants from Universitat de Lleida and INSPIRES.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Optimization of Consistency-Based Multiple Sequence Alignment using Big Data technologies

  • Lladós Segura, Jordi
  • Cores Prado, Fernando
  • Guirado Fernández, Fernando
With the advent of new high-throughput next-generation sequencing technologies, the volume of genetic data processed has increased significantly. It is becoming essential for these applications to achieve large-scale alignments with thousands of sequences or even whole genomes. However, all current MSA tools have exhibited scalability issues when the number of sequences increases. The main drawback of these methods is that errors made in early pairwise alignments are propagated to the nal result, a ecting the accuracy of the global alignment. The use of consistency information enables the nal result to be improved and makes it more stable from the accuracy point of view. However, such methods are severely limited by the memory required to store the consistency information. Authors in a previous work analyzed the structure and distribution of the data stored in the constraint library and demonstrated that it could be possible to reduce it without loosing accuracy and thus it is possible to increase the number of sequences to be aligned. However, the execution time for obtaining the constraint library for a bigger number of sequences also increases greatly. In the present paper, the authors apply Big Data technologies to take advantage of the high degree of parallelism provided by the MapReduce paradigm in order to reduce considerably the library calculation time. Moreover, Big Data infrastructure provides a distributed storage system to improve the library scalability and machine-learning algorithms to enhance the consistency selection policies., This work has been supported by the MEyC-Spain under contract TIN2014-53234-C2-2-R, TIN2017-84553-C2-2-R and TIN2016-81840-REDT.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Voiceprint and machine learning models for early detection of bulbar dysfunction in ALS

  • Tena del Pozo, Alberto
  • Clarià Sancho, Francisco
  • Solsona Tehàs, Francesc
  • Povedano, Mònica
Background and Objective: Bulbar dysfunction is a term used in amyotrophic lateral sclerosis (ALS). It refers to motor neuron disability in the corticobulbar area of the brainstem which leads to a dysfunction of speech and swallowing. One of the earliest symptoms of bulbar dysfunction is voice deterioration characterized by grossly defective articulation, extremely slow laborious speech, marked hypernasality and severe harshness. Recently, research efforts have focused on voice analysis to capture this dysfunction. The main aim of this paper is to provide a new methodology to diagnose this dysfunction automatically at early stages of the disease, earlier than clinicians can do. Methods: The study focused on the creation of a voiceprint consisting of a pattern generated from the quasi-periodic components of a steady portion of the five Spanish vowels and the computation of the five principal and independent components of this pattern. Then, a set of statistically significant features was obtained using multivariate analysis of variance and the outcomes of the most common supervised classification models were obtained. Results: The best model (random forest) obtained an accuracy, sensitivity and specificity of 88.3%, 85.0% and 95.0% respectively when classifying bulbar vs. control participants but the results worsened when classifying bulbar vs. no-bulbar patients (accuracy, sensitivity and specificity of 78.7%, 80.0% and 77.5% respectively for support vector machines). Due to the great uncertainty found in the annotated corpus of the ALS patients without bulbar involvement, we used a safe semi-supervised support vector machine to relabel the ALS participants diagnosed without bulbar involvement as bulbar and no-bulbar. The performance of the results obtained increased, especially when classifying bulbar and no-bulbar patients obtaining an accuracy, sensitivity and specificity of 91.0%, 83.3% and 100.0% respectively for support vector machines. This demonstrates that our model can improve the diagnosis of bulbar dysfunction compared not only with clinicians, but also the methods published to date. Conclusions: The results obtained demonstrate the efficiency and applicability of the methodology presented in this paper. It may lead to the development of a cheap and easy-to-use tool to identify this dysfunction in early stages of the disease and monitor progress., This work was approved by the Research Ethics Committee for Biomedical Research Projects (CEIm) at the Bellvitge University Hospital in Barcelona and was supported by the Ministerio de Economía y Competitividad (TIN2017-84553-C2-2-R) and the Ministerio de Ciencia e Innovacion (PID2020-113614RBC22). AT is a member of CIMNE, a Severo Ochoa Centre of Excellence (2019-2023) under grant CEX2018-000797-S, funded by MCIN/AEI/10.13039/501100011033. The Neurology Department of the Bellvitge University Hospital in Barcelona permitted the recording of the voices of the participants in its facilities. The clinical records were provided by Carlos Augusto Salazar Talavera. Dr. Marta Fulla and Maria Carmen Majos Bellmunt contributed advice about the process of eliciting the sounds.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Performance and usability tradeoff in a cluster display wall

  • Arroyo Campos, Ismael
  • Giné, Francesc
  • Roig Mateu, Concepció
  • Granollers i Saltiveri, Toni
Cluster-based display walls provide cost-effective and scalable display infrastructures with high resolution and large display area, making them suitable for a wide range of high-resolution applications. As a consequence, a wide offer of new cluster display-wall platforms together with their software frameworks have been proposed. Their performance and the satisfaction of their users have aroused the interest of some researchers. This work is focused on the Liquid Galaxy cluster display wall originally built to run Google Earth to create an immersive experience for the users. In this paper, the Liquid Galaxy is benchmarked running Google Earth, as a representative interactive application with high performance requirements, in different configurations and environments, to test the satisfaction, effectiveness and efficiency. Thus, we wish to know how users react to the system performance. In order to do so, we use a performance metric defined in previous research to relate the performance of the system with the user’s perception. Taking into account the trend of this metric in the experimentation, we model the behavior of the system in a way that the performance for any given visualization cluster running Google Earth could be predicted by using a reference system., This work was supported by the MEyC under contracts TIN2014-53234-C2-2-R and TIN2017-84553-C2-2-R.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Increasing online shop revenues with web scraping: a case study for the wine sector

  • Jorge, Oriol
  • Pons, Adrià
  • Rius Torrentó, Josep Maria
  • Vintró Sánchez, Carla
  • Mateo Fornés, Jordi
  • Vilaplana Mayoral, Jordi
Purpose – Wine has been produced for thousands of years and nowadays we have seen a spread in the wine culture. E-commerce sales of wine have increased considerably and online customer’s satisfaction is influenced by quality and price. This paper presents a case study of the company “QuieroVinos, S.L.”, an online wine shop founded in 2015 that sells Spanish wines in two main marketplaces. Design/methodology/approach – With the final target of increasing the company profits it has been designed and developed an application to track the prices of competitors for a set of products. This information will be used to set the product prices in order to offer the products both competitively and profitably in each Marketplace. This application must check, by tacking into account information such as the product cost or the minimum product margin, if it is possible to decrease the price in order to reach the top cheapest position and as a consequence, increase the sales. Findings – The application improved in a notorious way the company’s results in terms of sales and shipping costs. It must be said that without the use of the presented application, performing the price comparison process within each one of the marketplaces would have taken a long time. Moreover, as prices change very frequently, the obtained information has a very limited time value, and the competitors prices should be analyzed daily in order to take accurate decisions regarding the company’s price policy. Originality/value – Although the application has been designed for the wine sector and the two named marketplace, it could be exported to other sectors. For that, it should be implemented new modules to collect information regarding the competitor’s price of the products selling on each corresponding marketplace, This work was supported by the Ministerio de Economía y Competitividad under contract TIN2017- 84553-C2-2-R. Also, the authors are members of the research group 2017-SGR363, funded by the Generalitat de Catalunya.