Contribuciones a congresos

Permanent URI for this collectionhttps://hdl.handle.net/10486/723460

Browse

Now showing 1 - 20 of 1163

Prevalencia de concepciones erroneas entre el profesorado en activo en España
(Universidad Autónoma de Madrid. Facultad de Formación de Profesorado y Educación, 2024) Fernández, Juan G.; Ferrero González, Marta; Vadillo Nistal, Miguel Ángel; Departamento de Psicología Básica; Departamento de Psicología Evolutiva y de la Educación; Departamento Interfacultativo: Facultad de Formación de Profesorado y Educación y Facultad de Psicología; Facultad de Psicología; Facultad de Formación de Profesorado y Educación
A review of the digital transformation maturity models for SMEs in search of a self-assessment
(IEEE, 0028-12-22) Viloria Núñez, Cesar; Vázquez Hernández, Francisco José; Fernández Márquez, Carlos Manuel; Departamento de Análisis Económico: Economía Cuantitativa; Facultad de Ciencias Económicas y Empresariales
This paper shows a summary of the review related to digital transformation maturity models used for SMEs. The dimensions and items taken into account by the different models were mainly analyzed in order to establish the key factors for measuring the level of maturity of Digital Transformation. The methodology used by the different reviewed models was also analyzed in order to find opportunities for improvement in a potential new model. The review focused on maturity models that are suitable for SMEs and are not specialized at a specific sector of company. Many similarities were found in the dimensions and elements that the models got, but it was also evident that the vast majority require experts accompanying the diagnostic process, which may be the main opportunity for improvement with the possibility of proposing a self-assessment model, which allows the organization to assess its digital maturity through an interactive questionnaire by itself without any external support
Enredando en el barrio de la Ermita del Santo: Un proyecto entre la innovación docente y la transferencia a la comunidad local
(UAM Unidad de Apoyo a la Docencia, 2024-10) González Medina, Moneyba; Bouza García, Luis; Gregorio Hurtado, Sonia de; Facultad de Derecho; Departamento de Ciencia Política y Relaciones Internacionales
El trabajo que se presenta en esta comunicación da cuenta de un proyecto de innovación docente y transferencia de conocimiento multidisciplinar desarrollado en el marco de SEEDS. Estos proyectos, denominados nODoS, se alinean con las metas de los Objetivos de Desarrollo Sostenible (ODS) e involucran a la comunidad universitaria – en este caso, estudiantes y docentes de arquitectura y ciencia política – y al entorno local. El trabajo ha consistido en un análisis del conflicto y realización de propuestas de mejora utilizando metodologías de innovación docente como el Aprendizaje Basado en Proyectos (ABP) y el Aprendizaje-Servicio (ApS) aplicadas al caso de la Modificación Puntual del Plan General de Ordenación Urbana de Madrid (PGOUM) que conducirá a la demolición del actual Centro Comercial Ermita del Santo para construir en su lugar torres de viviendas. Las propuestas pasan por proyectos urbanísticos alternativos para la zona, por el diseño de estrategias más participativas para equilibrar los intereses de los distintos afectados y por el aprendizaje de la experiencia comparada.
demoBeam: a platform for teaching of phased array beam steering
(IEEE, 2024-06-28) Alejos, Ana Vázquez; Folgar, Manuel Abelleira; Muriel-Barrado, Alfonso T.; De La Torre, Pablo Padilla; González, José Manuel Fernández; Gobierno de España; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
This contribution describes a phased array beam steering demonstrator for the 24-31 GHz frequency band encompassing array antennas, beamformer, XY positioners, VNA and software tools for practical teaching. Comprehensive training and inclusion of contents of technological updating benefits students, encouraging critical thinking and problem solving, and enhances educational institution role in advancing wireless technology
Inteligencia artificial y radiómica para diferenciar lipoma de tumor lipomatoso atípico en la resonancia magnética
(SERAM (Sociedad Española de Radiología Médica), 2024-05-25) Ramírez García-Mina, Alberto; Morán Blanco, Luz M.; García Martín, Álvaro; Corredor Jerez, Ricardo A.; Bernal León, Rut; Dinc, Ezgi; Pintado Murillo, Javier; Li Cai, Chao Yuan; Royuela Vicente, Ana; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
OBJETIVOS Diferenciar el lipoma del tumor lipomatoso atípico (TLA) por imagen es complicado, y en muchos casos se requiere biopsia o resección quirúrgica para llegar al diagnóstico definitivo. El objetivo de este estudio es desarrollar un algoritmo basado en machine learning empleando las variables radiómicas de RM preoperatorias para mejorar la distinción entre lipoma y TLA. MATERIAL Y MÉTODO Se seleccionó retrospectivamente una cohorte de 80 pacientes con sospecha de lipoma vs TLA en RM. Todos los pacientes tenían diagnóstico mediante biopsia (determinación inmunohistoquímica de MDM2). Cada tumor se segmentó tridimensionalmente utilizando una aplicación de segmentación y radiómica. Se extrajeron las variables radiómicas de la segmentación en secuencias potenciadas en T1, T2 y densidad protónica y se emplearon para entrenar un modelo de machine learning. Se utilizaron diferentes aproximaciones para entrenar el algoritmo: support vector machine, naïve Bayes, redes neuronales artificiales y regresión logística. Se valoró el rendimiento de cada modelo y se seleccionó el mejor en función de la AUC-ROC, sensibilidad, especificidad y accuracy. RESULTADOS Resultados preliminares con una muestra de menor tamaño (10 pacientes): el rendimiento de un modelo basado en support vector machine obtuvo una AUC-ROC de 0.85. CONCLUSIONES Incluso con resultados preliminares en una muestra muy pequeña, los resultados destacan el potencial beneficio de la inteligencia artificial y la radiómica en la diferenciación entre lipoma y tumor lipomatoso atípico en resonancia magnética. Análisis más exhaustivos se completarán en la muestra de mayor tamaño
Monitoring web QoE in satellite networks from passive measurements
(IEEE, 2024-03-18) Perna, Gianluca; Trevisan, Martino; Giordano, Danilo; Perdices Burrero, Daniel; Mellia, Marco; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
Satellite Communication (SatCom) is the only choice to access the Internet in remote regions and is characterized by extreme latency and constrained capacity. For SatCom operators, it is thus fundamental to monitor the Quality of Experience (QoE) of subscribers, to measure their satisfaction, spot anomalies and optimize the peculiar network setup. The Web has become the primary source of Internet content, and Web browsing is the main activity of internauts. This paper addresses the challenge of monitoring Web QoE in SatCom environments, proposing a tailored system that employs a supervised approach to predict Web QoE using passive measurements. The system collects training data through Test Agents that mimic real subscribers’ traffic patterns and uses them to build Machine Learning (ML) models that predict performance metrics. The findings demonstrate the feasibility of monitoring Web QoE in SatCom environments, with limitations on website applicability and temporal stability. The need for periodic data generation and the development of a general machine learning model for unseen websites remain open challenges. This research contributes to enhancing web browsing experiences in SatCom and expanding understanding of Web QoE monitoring in diverse network settings
A criterion based on fisher's exact test for item splitting in context-aware recommender systems
(IEEE, 2016-09-05) Campos Soto, Pedro G.; Cantador Gutiérrez, Iván; Díez Rubio, Fernando; Fernández Tobías, Ignacio; Departamento de Ingeniería Informática; Escuela Politécnica Superior
Item Splitting is a context-aware recommendation technique based on Collaborative Filtering (CF), which groups and exploits ratings according to the contexts in which they were generated. It shows positive effects on recommendation accuracy in the presence of significant differences between the users' preferences from distinct contexts. To determine whether such differences are significant, in this paper we propose a novel impurity criterion based on the Fisher's exact test, which returns a score on the difference between ratings given to an item. Experimental results on a dataset of movie ratings show a lower rating prediction error with respect to other impurity criteria - in particular, related with time context signals - , letting us improve the recommendation performance of a state-of-the-art CF algorithm in an offline evaluation setting that simulates real-world conditions
Recurrent neural network based counter automata
(ESANN, 2024-10-11) Leal Andrés, Sergio; Lago Fernández, Luis Fernando; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
This paper presents a neural network architecture that aims to merge RNNs and push-down automata in order to address the recognition of formal languages improving interpretability. The model manages to reproduce a behaviour equivalent to that of an automaton, making it more generalizable and interpretable. Validation has been carried out through several experiments, testing not only convergence but also adaptability and training speed, and comparing the results with similar existing models, as well as with an LSTM. The proposed model serves as a starting point with excellent results, and serves as a basis for future extensions to more sophisticated architectures
Evolution of EEG fractal dimension along a sequential finger movement task
(Springer Science and Business Media Deutschland GmbH, 2024-05-31) Kamali, Sara; Baroni, Fabiano; Varona Martínez, Pablo; Gobierno de España; Neurocomputación Biológica (ING EPS-005); Escuela Politécnica Superior; Departamento de Ingeniería Informática
We used dual EEG and EMG recordings to assess the neural dynamics of motor activity during a stereotyped sequential finger movement. We analyzed the evolution of EEG complexity, assessed using Katz fractal dimension (KFD), in three brain regions involved in the task (multisensory association (MA), sensory and left and right motor areas) and its relation with response time, defined by EMG onset. The KFD was calculated for multiple time windows, defined with respect to the go cue or the EMG onset. We observed a positive correlation between the KFD and the EMG onset latency in various time windows in all the areas. This relationship reversed for trials with a late EMG onset. While all the areas manifested a similar pattern of correlations, the motor area showed the lowest, and the MA area the highest, complexity values between these four brain regions. The KFD tended to decrease as the task progressed, consistently with previous observations of reduced neural variability with task engagement
Product lines of graphical modelling languages
(ACM, 2024-09-22) Garmendia, Antonio; Guerra Sánchez, Esther; Lara Jaramillo, Juan de; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
Modelling languages are essential in many disciplines to express knowledge in a precise way. Furthermore, some domains require families of notations (rather than individual languages) that account for variations of a language. Some examples of language families include those to define automata, Petri nets, process models or software architectures. Several techniques have been proposed to engineer families of languages, but they often neglect the language’s concrete syntax, especially if it is graphical. To fill this gap, we propose a modular method to build product lines of graphical modelling languages. Language features are defined in modules, which comprise both the abstract and graphical concrete syntax of the feature. A language variant is selected by choosing a valid configuration of modules, from which the abstract and concrete syntax of the variant is synthesised. Our approach permits composition and overriding of graphical elements (e.g., symbol styles, visualisation layers), the injection of pre-defined graphical styles into language families (e.g., to obtain a high-intensity contrast variant for accessibility), and the analysis of graphical conflicts at the product line level. We report on an implementation atop Eclipse/Sirius, and demonstrate its benefits by an evaluation which shows a substantial specification size reduction of our product line method with respect to a case-by-case specification approach
Mutation testing for task-oriented chatbots
(ACM, 2024-06-18) Gomez Abajo, Pablo; Pérez-Soler, Sara; Pablo C. Cañizares; Guerra Sánchez, Esther; Lara Jaramillo, Juan de; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
Conversational agents, or chatbots, are increasingly used to access all sorts of services using natural language. While open-domain chatbots – like ChatGPT – can converse on any topic, task-oriented chatbots – the focus of this paper – are designed for specific tasks, like booking a flight, obtaining customer support, or setting an appointment. Like any other software, task-oriented chatbots need to be properly tested, usually by defining and executing test scenarios (i.e., sequences of user-chatbot interactions). However, there is currently a lack of methods to quantify the completeness and strength of such test scenarios, which can lead to low-quality tests, and hence to buggy chatbots. To fill this gap, we propose adapting mutation testing (MuT) for task-oriented chatbots. To this end, we introduce a set of mutation operators that emulate faults in chatbot designs, an architecture that enables MuT on chatbots built using heterogeneous technologies, and a practical realisation as an Eclipse plugin. Moreover, we evaluate the applicability, effectiveness and efficiency of our approach on open-source chatbots, with promising results.
Personalizing Keyword Spotting with Speaker Information
(IEEE, 2025-03) Labrador, Beltrán; Zhu, Pai; Zhao, Guanlong; Scorza Scarpati, Angelo; Wang, Quan; Lozano Díez, Alicia; Lopez-Moreno, Ignacio; Audias - Audio, Data Intelligence and Speech; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
Keyword spotting systems often struggle to generalize to a diverse population with various accents and age groups. To address this challenge, we propose a novel approach that integrates speaker information into keyword spotting using Feature-wise Linear Modulation (FiLM), a recent method that allows models to learn from different data inputs and features. We explore both Text-Dependent and Text-Independent speaker recognition systems to extract speaker information, and we experiment on extracting this information from both the input audio and pre-enrolled user audio. Evaluating our systems on a diverse dataset, our primary approach yields a notable 2.6% relative improvement on Equal Error Rate overall, particularly improving performance by 5.9% for children under 12 years old and up to 24% for underrepresented speaker groups. Moreover, our proposed approach only requires a small 1% increase in the number of parameters, with a minimum impact on latency and computational cost, which makes it a practical solution for real-world applications
Integrating sentiment features in factorization machines: Experiments on music recommender systems
(ACM, 2024-06-22) Wang, Javier; Bellogin Kouki, Alejandro; Cantador Gutiérrez, Iván; Escuela Politécnica Superior; Departamento de Ingeniería Informática
Music recommender systems play a pivotal role in catering to diverse user preferences and fostering personalized listening experiences. At the same time, sentiments can profoundly influence music by shaping its emotional expression and evoking specific moods onto listeners. Expressed in textual content, these sentiments may be analyzed through natural language processing techniques to gauge emotions or opinions, hopefully increasing their relevance when exploited for recommendation. This work aims to investigate how to better integrate such information and understand its potential impact on personalized music suggestions, attempting to enhance recommendation models by incorporating sentiment features into factorization machines. For this purpose, a dataset was collected from Last.fm and enhanced with sentiment information extracted from Wikipedia. Empirical results evidence that not all sentiment-related features are equally useful, showing that each tested factorization machine approach varies in sensitivity to these features.
Creative coding for dance movement therapy in children with autism
(SCITEPRESS – Science and Technology Publications, Lda., 2024-02-23) Araya Quintar, Nicolas Alejandro; Gómez Escribano, Javier; Montoro Manrique, Germán; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
People diagnosed with an Autism Spectrum Disorder (ASD) have deficits in social interaction, communication and cognitive development. Children with ASD may also present motor difficulties growing up, which motivates interventions of Dance Movement Therapy (DMT) that helps them to develop social skills and integrate in society. Current technological advances have integrated into DMT interventions, enriched with virtual scenarios, projections, sensors and robot partners. These works have positive outcomes in social skills development and motor skills refinement, even though, due to confinement for COVID-19, online DMT has yet to be further explored. We propose a research methodology for the development of a tool that aims to develop self expression for ASD youth, with the creation of an artistic image based on dance and body movements. Our initial study case is Movarte, a web based tool that creates graphic pieces based on body movement and proxemic areas. 15 users evaluated the application, showing positive outcomes in terms of engagement and novelty, though it was not considered so clear and limited in terms of parameter control. Future research will provide more insight to adapt an interface for DMT in self expression for people with ASD.
Coverage-based strategies for the automated synthesis of test scenarios for conversational agents
(ACM, 2024-06-10) Cañizares, Pablo C.; Ávila, Daniel; Pérez-Soler, Sara; Guerra Sánchez, Esther; Lara Jaramillo, Juan de; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
Conversational agents – or chatbots – are increasingly used as the user interface to many software services. While open-domain chatbots like ChatGPT excel in their ability to chat about any topic, task-oriented conversational agents are designed to perform goaloriented tasks (e.g., booking or shopping) guided by a dialoguebased user interaction, which is explicitly designed. Like any kind of software system, task-oriented conversational agents need to be properly tested to ensure their quality. For this purpose, some tools permit defining and executing conversation test cases. However, there are currently no established means to assess the coverage of the design of a task-oriented agent by a test suite, or mechanisms to automate quality test case generation ensuring the agent coverage. To attack this problem, we propose test coverage criteria for task-oriented conversational agents, and define coverage-based strategies to synthesise test scenarios, some oriented to test case reduction. We provide an implementation of the criteria and the strategies that is independent of the agent development platform. Finally, we report on their evaluation on open-source Dialogflow and Rasa agents, and a comparison against a state-of-the-art testing tool. The experiment shows benefits in terms of test generation correctness, increased coverage and reduced testing time.
Conversational assistants for software development: integration, traceability and coordination
(Science and Technology Publications, Lda., 2024-04-29) Contreras Romero, Albert; Guerra Sánchez, Esther; Lara Jaramillo, Juan de; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
The recent advances in generative artificial intelligence are revolutionising our daily lives. Large language models (LLMs) – the technology underlying conversational agents like ChatGPT – can produce sensible text in response to user prompts, and so, they are being used to solve tasks in many disciplines like marketing, law, human resources or media content creation. Software development is also following this trend, with recent proposals for conversational assistants tailored for this domain. However, there is still a need to understand the possibilities of integrating these assistants within integrated development environments (IDEs), coordinating multiple assistants, and tracing their contributions to the software project under development. This paper tackles this gap by exploring alternatives for assistant integration within IDEs, and proposing a general architecture for conversational assistance in software development that comprises a rich traceability model of the user-assistant interaction, and a multi-assistant coordination model. We have realised our proposal building an assistant (named CARET) for Java development within Eclipse. The assistant supports tasks like code completion, documentation, maintenance, code comprehension and testing. We present an evaluation for one specific development task (method renaming), showing promising results
Second edition FRCSyn challenge at CVPR 2024: Face recognition challenge in the era of synthetic data
(IEEE, 2024-09-27) DeAndres-Tame, Ivan; Tolosana Moranchel, Ruben; Melzi, Pietro; Vera Rodríguez, Rubén; Morales Moreno, Aythami; Fiérrez Aguilar, Julián; Ortega García, Javier; European Commission; Gobierno de España; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intraclass variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new subtasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition
How SAM Perceives Different mp-MRI Brain Tumor Domains?
(IEEE, 2024-06-22) Diana Albelda, Cecilia; Alcover Couso, Roberto; García Martín, Álvaro; Bescos Cano, Jesús; Gobierno de España; Escuela Politécnica Superior; Departamento de Tecnología Electrónica y de las Comunicaciones
Gliomas, among the deadliest forms of cancer, are brain tumors that present a significant challenge due to their rapid progression and resistance to treatment. Effective and early diagnosis is critical for improving patient prognosis. Deep learning, particularly through large-scale vision models like Segment Anything Model (SAM), offers a new pathway for tumor segmentation. This study seeks to address the primary challenge of adapting SAM for mpMRI brain scans, which typically encompass multiple imaging modalities not fully utilized by standard three-channel vision models. We demonstrate that leveraging all available MRI modalities achieves superior performance compared to the standard mechanism of repeating a MRI scan to fit the input embedding. Our research also focuses on parameter-efficient tuning of SAM to effectively train the model while minimizing resource usage, showcasing significant improvements when evaluated across multiple datasets. Finally, we expose how SAM perceives differences across varied brain tumor domains by visually analyzing the features extracted on each of them. Our code and models are available at github.com/vpulab/med-sam-brain
Biometrics and behavior analysis for detecting distractions in e-learning
(IEEE, 2024-06-21) Becerra Jimenez, Alvaro; Irigoyen Muñoz, Javier; Daza Garcia, Roberto; Cobos Pérez, Ruth; Morales Moreno, Aythami; Fiérrez Aguilar, Julián; Cukurova, Mutlu; Gobierno de España; Comunidad de Madrid; Escuela Politécnica Superior; Departamento de Ingeniería Informática; Departamento de Tecnología Electrónica y de las Comunicaciones
In this article, we explore computer vision approaches to detect abnormal head pose during e-learning sessions and we introduce a study on the effects of mobile phone usage during these sessions. We utilize behavioral data collected from 120 learners monitored while participating in a MOOC learning sessions. Our study focuses on the influence of phone-usage events on behavior and physiological responses, specifically attention, heart rate, and meditation, before, during, and after phone usage. Additionally, we propose an approach for estimating head pose events using images taken by the webcam during the MOOC learning sessions to detect phone-usage events. Our hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-learning sessions. We propose an approach designed to detect deviations in head posture from the average observed during a learner’s session, operating as a semi-supervised method. This system flags events indicating alterations in head posture for subsequent human review and selection of mobile phone usage occurrences with a sensitivity over 90%
Automating the development of task-oriented LLM-based chatbots
(ACM, 2024-07-08) Sánchez Cuadrado, Jesús; Pérez-Soler, Sara; Guerra Sánchez, Esther; Lara Jaramillo, Juan de; Gobierno de España; Escuela Politécnica Superior; Departamento de Ingeniería Informática
Task-oriented chatbots are increasingly used to access all sorts of services – like booking a flight, or setting a medical appointment – through natural language conversation. There are many technologies for implementing task-oriented chatbots, including Dialogflow, Watson, and Rasa. They rely on an explicit definition of the user intents, conversation flows, and chatbot outputs, which is costly to specify, and sometimes results in suboptimal user experiences and artificial conversations with limited diversity of chatbot responses. Recently, the advances in generative artificial intelligence fostered by Large Language Models (LLMs) have enabled a new range of open-domain chatbots, like ChatGPT, able to converse fluently on any topic. However, they are general-purpose, and therefore not directly usable to solve specialised tasks reliably. In this paper, we study the power of LLMs to build task-oriented chatbots, resulting in lighter specifications – no intent definition required – and more natural conversations than in intent-based approaches. To this end, we propose a lightweight domain-specific language based on YAML to specify chatbots using modules of different types (e.g., menus, question-answering, data gathering). These specifications are compiled into structured LLM prompts that use the ReAct framework to inform our runtime howto interpret the user input and coordinate the tasks that the chatbot must perform. The paper presents the design and realisation of our framework, and an assessment that encodes a set of existing intent-based chatbots using our approach, showing its benefits in terms of specification size, conversation flexibility and output diversity

Browse

Recent Submissions