Person:
García Tejedor, Álvaro José

First Name

Álvaro José

Last Name

García Tejedor

Faculty

Escuela Politécnica Superior

Identifiers

Full item page

Search Results

Now showing 1 - 10 of 23

A domain categorisation of vocabularies based on a deep learning classifier.
(Journal of Information Science, 2021) Nogales Moyano, Alberto; Sicilia, Miguel Ángel; García Tejedor, Álvaro José
The publication of large amounts of open data has become a major trend nowadays. This is a consequence of pro-jects like the Linked Open Data (LOD) community, which publishes and integrates datasets using techniques like Linked Data. Linked Data publishers should follow a set of principles for dataset design. This information is described in a 2011 document that describes tasks as the consideration of reusing vocabularies. With regard to the latter, another project called Linked Open Vocabularies (LOV) attempts to compile the vocabularies used in LOD. These vocabularies have been classified by domain following the subjective criteria of LOV members, which has the inherent risk introducing personal biases. In this paper, we present an automatic classifier of vocabularies based on the main categories of the well-known knowledge source Wikipedia. For this purpose, word-embedding models were used, in combination with Deep Learning techniques. Results show that with a hybrid model of regular Deep Neural Network (DNN), Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN), vocabularies could be classified with an accuracy of 93.57 per cent. Specifically, 36.25 per cent of the vocabularies belong to the Culture category.
BERT Learns From Electroencephalograms About Parkinson's Disease: Transformer-Based Models for Aid Diagnosis.
(IEEE Access, 2022) Nogales Moyano, Alberto; García Tejedor, Álvaro José; Maitín, Ana María; Pérez Morales, Antonio; Del Castillo, María Dolores; Romero Muñoz, Juan Pablo
Medicine is a complex field with highly trained specialists with extensive knowledge that continuously needs updating. Among them all, those who study the brain can perform complex tasks due to the structure of this organ. There are neurological diseases such as degenerative ones whose diagnoses are essential in very early stages. Parkinson’s disease is one of them, usually having a confirmed diagnosis when it is already very developed. Some physicians have proposed using electroencephalograms as a non-invasive method for a prompt diagnosis. The problem with these tests is that data analysis relies on the clinical eye of a very experienced professional, which entails situations that escape human perception. This research proposes the use of deep learning techniques in combination with electroencephalograms to develop a non-invasive method for Parkinson’s disease diagnosis. These models have demonstrated their good performance in managing massive amounts of data. Our main contribution is to apply models from the field of Natural Language Processing, particularly an adaptation of BERT models, for being the last milestone in the area. This model choice is due to the similarity between texts and electroencephalograms that can be processed as data sequences. Results show that the best model uses electroencephalograms of 64 channels from people without resting states and finger-tapping tasks. In terms of metrics, the model has values around 86%.
Network analysis for food safety: Quantitative and structural study of data gathered through the RASFF system in the European Union.
(Food Control, 2022) Nogales Moyano, Alberto; Mora-Cantallops, Marçal; Díaz Morón, Rodrigo; García Tejedor, Álvaro José
This paper reports a quantitative and structural analysis of data gathered on the food issues reported by the European Union members over the last forty years. The study applies statistical measures and network analysis techniques. For this purpose, a graph was constructed of how different contaminated products have been distributed through countries. The work aims to leverage insights into the structure formed by the involvement of European countries in the exchange of goods that can cause problems for populations. The results obtained show the roles of different countries in the detection of sensitive routes. In particular, the analysis identifies problematic origin countries, such as China or Turkey, whereas European countries, in general, do have good border control policies for the import/export of food.
Analyzing the Influence of Diverse Background Noises on Voice Transmission: A Deep Learning Approach to Noise Suppression.
(Applied Sciences, 2024) Nogales Moyano, Alberto; Caracuel-Cayuela, Javier; García Tejedor, Álvaro José
This paper presents an approach to enhancing the clarity and intelligibility of speech in digital communications compromised by various background noises. Utilizing deep learning techniques, specifically a Variational Autoencoder (VAE) with 2D convolutional filters, we aim to suppress background noise in audio signals. Our method focuses on four simulated environmental noise scenarios: storms, wind, traffic, and aircraft. The training dataset has been obtained from public sources (TED-LIUM 3 dataset, which includes audio recordings from the popular TED-TALK series) combined with these background noises. The audio signals were transformed into 2D power spectrograms, upon which our VAE model was trained to filter out the noise and reconstruct clean audio. Our results demonstrate that the model outperforms existing state-of-the-art solutions in noise suppression. Although differences in noise types were observed, it was challenging to definitively conclude which background noise most adversely affects speech quality. The results have been assessed with objective (mathematical metrics) and subjective (listening to a set of audios by humans) methods. Notably, wind noise showed the smallest deviation between the noisy and cleaned audio, perceived subjectively as the most improved scenario. Future work should involve refining the phase calculation of the cleaned audio and creating a more balanced dataset to minimize differences in audio quality across scenarios. Additionally, practical applications of the model in real-time streaming audio are envisaged. This research contributes significantly to the field of audio signal processing by offering a deep learning solution tailored to various noise conditions, enhancing digital communication quality.
Survey of Machine Learning Techniques in the Analysis of EEG Signals for Parkinson’s Disease: A Systematic Review.
(Applied Sciences, 2022) Maitín, Ana María; Romero Muñoz, Juan Pablo; García Tejedor, Álvaro José
Background: Parkinson’s disease (PD) affects 7–10 million people worldwide. Its diagnosis is clinical and can be supported by image-based tests, which are expensive and not always accessible. Electroencephalograms (EEG) are non-invasive, widely accessible, low-cost tests. However, the signals obtained are difficult to analyze visually, so advanced techniques, such as Machine Learning (ML), need to be used. In this article, we review those studies that consider ML techniques to study the EEG of patients with PD. Methods: The review process was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, which are used to provide quality standards for the objective evaluation of various studies. All publications before February 2022 were included, and their main characteristics and results were evaluated and documented through three key points associated with the development of ML techniques: dataset quality, data preprocessing, and model evaluation. Results: 59 studies were included. The predominating models were Support Vector Machine (SVM) and Artificial Neural Networks (ANNs). In total, 31 articles diagnosed PD with a mean accuracy of 97.35 ± 3.46%. There was no standard cleaning protocol for EEG and a great heterogeneity in EEG characteristics was shown, although spectral features predominated by 88.37%. Conclusions: Neither the cleaning protocol nor the number of EEG channels influenced the classification results. A baseline value was provided for the PD diagnostic problem, although recent studies focus on the identification of cognitive impairment.
Using Game Learning Analytics for Validating the Design of a Learning Game for Adults with Intellectual Disabilities.
(British Journal of Educational Technology, 2018) Rus Cano, Ana; Fernández Manjón, Baltasar; García Tejedor, Álvaro José
Serious Games, defined as a game in which education (in its various forms) is the primary goal rather than entertainment, have been proven as an effective educational tool for engaging and motivating students (Michael & Chen, 2006). However, more research is needed to sustain the suitability of these games to train users with cognitive impairments. This empirical study addresses the use of a Serious Game for training students with Intellectual Disabilities in traveling around the subway as a complement to traditional training. Fifty-one (51) adult people with Down Syndrome, mild cognitive disability or certain types of Autism Spectrum Disorder, all conditions classified as intellectual disabilities, played the learning game Downtown, A Subway Adventure which was designed ad-hoc considering their needs and cognitive skills. We used standards-based Game Learning Analytics techniques (i.e. Experience API –xAPI), to collect and analyze learning data both off-line and in near-real time while the users were playing the videogame. This article analyzes and assesses the evidence data collected using analytics during the game sessions, like time completing tasks, inactivity times or the number of correct/incorrect stations while traveling. Based on a multiple baseline design, the results validated both the game design and the tasks and activities proposed in Downtown as a supplementary tool to train skills in transportation. Differences between High-Functioning and Medium-Functioning users were found and explained in this paper, but the fact that almost all of the students completed at least one route without mistakes, the general improvement trough sessions and the low-mistake ratio are good indicators about the appropriateness of the game design.
Genetic and Swarm Algorithms for Optimizing the Control of Building HVAC Systems Using Real Data: A Comparative Study.
(Mathematics, 2021) Garces Jimenez, Alberto; Gomez Pulido, Jose Manuel; Gallego Salvador, Nuria; García Tejedor, Álvaro José
Buildings consume a considerable amount of electrical energy, the Heating, Ventilation, and Air Conditioning (HVAC) system being the most demanding. Saving energy and maintaining comfort still challenge scientists as they conflict. The control of HVAC systems can be improved by modeling their behavior, which is nonlinear, complex, and dynamic and works in uncertain contexts. Scientific literature shows that Soft Computing techniques require fewer computing resources but at the expense of some controlled accuracy loss. Metaheuristics-search-based algorithms show positive results, although further research will be necessary to resolve new challenging multi-objective optimization problems. This article compares the performance of selected genetic and swarmintelligence- based algorithms with the aim of discerning their capabilities in the field of smart buildings. MOGA, NSGA-II/III, OMOPSO, SMPSO, and Random Search, as benchmarking, are compared in hypervolume, generational distance, ε-indicator, and execution time. Real data from the Building Management System of Teatro Real de Madrid have been used to train a data model used for the multiple objective calculations. The novelty brought by the analysis of the different proposed dynamic optimization algorithms in the transient time of an HVAC system also includes the addition, to the conventional optimization objectives of comfort and energy efficiency, of the coefficient of performance, and of the rate of change in ambient temperature, aiming to extend the equipment lifecycle and minimize the overshooting effect when passing to the steady state. The optimization works impressively well in energy savings, although the results must be balanced with other real considerations, such as realistic constraints on chillers’ operational capacity. The intuitive visualization of the performance of the two families of algorithms in a real multi-HVAC system increases the novelty of this proposal.
EEGraph: An open-source Python library for modeling electroencephalograms using graphs.
(Neurocomputing, 2023) Maitin, Ana M.; Nogales Moyano, Alberto; Chazarra, Pedro; García Tejedor, Álvaro José
Background and objective Connectivity studies make it possible to identify alterations in brain connections and to associate these pathologies with different neurological disorders. However, a clinical test is necessary to obtain information about the state of the brain. Electroencephalograms (EEGs) provide this information in addition to being tests with other benefits for the patient (non-invasive, low-cost, high reproducibility). Graph theory can be used to represent both the anatomical and functional connections of the brain by means of connectivity measures. The procedure of transforming an EEG into a graph can be slightly tedious for researchers, especially when implementing different connectivity measures. Methods The open-source Python library EEGraph automatically performs the modeling of an EEG through a graph, providing its matrix and visual representation. It recognizes various EEG input formats, identifying the number of electrodes and the location of each electrode in the brain. Moreover, it allows the user to choose from 12 connectivity measures to produce the graph from the EEG, with great flexibility to define specific parameters to adapt them to each study, including EEG time-windows segmentation and separation in frequency bands. Results The EEGraph library is developed as a tool, for researchers and clinical specialists in the field of neuroscience, that provides direct information on the connectivity of the brain from electroencephalography signals. Its documentation and source code are available at https://github.com/ufvceiec/EEGRAPH. It can be installed from the Python Package Index using pip install EEGRAPH. Conclusions The EEGraph library was built aiming to facilitate the development of connectivity studies based on the modeling of electroencephalography tests through graphs. It includes a wide range of connectivity measures, which, together with the multiple output options, make EEGraph an easy to use and powerful tool with direct applications in both the clinical and neuroscience research fields.
A light method for data generation: a combination of Markov Chains and Word Embeddings.
(Procesamiento del Lenguaje Natural, 2020) Martínez García, Eva; Nogales Moyano, Alberto; Morales Escudero, Javier; García Tejedor, Álvaro José
Most of the current state-of-the-art Natural Language Processing (NLP) techniques are highly data-dependent. A significant amount of data is required for their training, and in some scenarios data is scarce. We present a hybrid method to generate new sentences for augmenting the training data. Our approach takes advantage of the combination of Markov Chains and word embeddings to produce high-quality data similar to an initial dataset. In contrast to other neural-based generative methods, it does not need a high amount of training data. Results show how our approach can generate useful data for NLP tools. In particular, we validate our approach by building Transformer-based Language Models using data from three different domains in the context of enriching general purpose chatbots.
Down-Town: Misterio en el metro. Un serious game dirigido a personas con síndrome de Down.
(2015) Bonete Román, Saray; Ruano, Oscar; García Tejedor, Álvaro José; Psicología