DI - LABDA - Artículos de Revistas

Permanent URI for this collection


Recent Submissions

Now showing 1 - 20 of 81
  • Publication
    Virality, only the tip of the iceberg: ways of spread and interaction around COVID-19 misinformation in Twitter
    (Universidad de Navarra, 2022-04-01) Villar Rodriguez, Guillermo; Souto Rico, Monica Maria; Martín, Alejandro; Villar Rodríguez, Guillermo; Souto Rico, Mónica María; Martín, Alejandro; Comunidad de Madrid; European Commission; Ministerio de Ciencia e Innovación (España)
    Misinformation has long been a weapon that helps the political, social, and economic interests of different sectors. This became more evident with the transmission of false information in the COVID-19 pandemic, compromising citizens' health by anti-vaccine recommendations, the denial of the coronavirus and false remedies. Online social networks are the breeding ground for falsehoods and conspiracy theories. Users can share viral misinformation or publish it on their own. This encourages a double analysis of this issue: the need to capture the deluge of false information as opposed to the real one and the study of users' patterns to interact with that infodemic. As a response to this, our work combines the use of artificial intelligence and journalism through fact-checked false claims to provide an in-depth study of the number of retweets, likes, replies, quotes and repeated texts in posts stating or contradicting misinformation in Twitter. The large sample of tweets was collected and automatically analysed through Natural Language Processing (NLP) techniques, not to give all the attention only to the posts with a big impact but to all the messages contributing to the expansion of false information or its rejection regardless of their virality. This analysis revealed that the diffusion of tweets surrounding coronavirus-related misinformation is not only a domain of viral tweets, but also from posts without interactions, which represent most of the sample, and that there are no big differences between misinformation and its contradiction in general, except for the use of replies.
  • Publication
    Point cloud voxel classification of aerial urban LiDAR using voxel attributes and random forest approach
    (Elservier, 2023-04-01) Aljumaily, Harith; Laefer, Debra F.; Cuadra Fernández, María Dolores; Velasco de Diego, Manuel
    The opportunities now afforded by increasingly available, dense, aerial urban LiDAR point clouds (greater than100 pts/m2) are arguably stymied by their sheer size, which precludes the effective use of many tools designed for point cloud data mining and classification. This paper introduces the point cloud voxel classification (PCVC) method, an automated, two-step solution for classifying terabytes of data without overwhelming the computational infrastructure. First, the point cloud is voxelized to reduce the number of points needed to be processed sequentially. Next, descriptive voxel attributes are assigned to aid in further classification. These attributes describe the point distribution within each voxel and the voxel's geo-location. These include 5 point-descriptors (density, standard deviation, clustered points, fitted plane, and plane's angle) and 2 voxel position attributes (elevation and neighbors). A random forest algorithm is then used for final classification of the object within each voxel using four categories: ground, roof, wall, and vegetation. The proposed approach was evaluated using a 297,126,417 point dataset from a 1 km2 area in Dublin, Ireland and 50% denser dataset of New York City of 13,912,692 points (150 m2). PCVC's main advantage is scalability achieved through a 99 % reduction in the number of points that needed to be sequentially categorized. Additionally, PCVC demonstrated strong classification results (precision of 0.92, recall of 0.91, and F1-score of 0.92) compared to previous work on the same data set (precision of 0.82-0.91, recall 0.86-0.89, and F1-score of 0.85-0.90).
  • Publication
    Digital transformation in organizational health and safety to mitigate Burnout Syndrome
    (Frontiers, 2023-03-21) Sánchez Segura, María Isabel; Dugarte Peña, Germán Lenin; Medina Domínguez, Fuensanta; Amescua Seco, Antonio de; Menchen Viso, Rosa; Universidad Carlos III de Madrid
    In 2000, the World Health Organization (WHO) identified Burnout Syndrome as an occupational risk factor, affecting an estimated 10% of workers, resulting in lost productivity and increased costs due to sick leave. Some claim that Burnout Syndrome has reached epidemic proportions in workplaces around the world. While signs of burnout are not difficult to identify and palliate, its real impact is not easy to measure, generating a number of risks for companies from possible loss of human talent to decreased productivity and diminished quality of life. Given the complexity of Burnout Syndrome, it must be addressed in a creative, innovative and systematic way; traditional approaches cannot be expected to deliver different results. This paper describes the experience where an innovation challenge was launched to collect creative ideas to identify, prevent or mitigate Burnout Syndrome through the use of technological tools and software. The challenge was endowed with an economic award and its guidelines stated that the proposals must be both creative and feasible from an economic and organizational point of view. A total of twelve creative projects were submitted, including each of them, the analysis, design and management plans, to envision an idea that is feasible and with the appropriate budget, implemented. In this paper, we present a summary of these creative projects and how the IRSST (Instituto Regional de Seguridad y Salud en el Trabajo) experts and leaders in OHS in the Madrid Region (Spain) envision their potential impact on improving the OHS landscape.
  • Publication
    CESARSC: Framework for creating Cultural Entertainment Systems with Augmented Reality in Smart Cities
    (ComSIS Consortium, 2016) García Crespo, Ángel; González Carrasco, Israel; López Cuadrado, José Luis; Villanueva, Daniel; Gonzalez, Alvaro; Ministerio de Economía y Competitividad (España)
    The areas of application for augmented reality technology are heterogeneous but the content creation tools available are usually single-user desktop applications. Moreover, there is no online development tool that enables the creation of such digital content. This paper presents a framework for the creation of Cultural Entertainment Systems and Augmented Reality, employing cloud-based technologies and the interaction of heterogeneous mobile technology in real time in the field of mobile tourism. The proposed system allows players to carry out a series of games and challenges that will improve their tourism experience. The system has been evaluated in a real scenario, obtaining promising results.The areas of application for augmented reality technology are heterogeneous but the content creation tools available are usually single-user desktop applications. Moreover, there is no online development tool that enables the creation of such digital content. This paper presents a framework for the creation of Cultural Entertainment Systems and Augmented Reality, employing cloud-based technologies and the interaction of heterogeneous mobile technology in real time in the field of mobile tourism. The proposed system allows players to carry out a series of games and challenges that will improve their tourism experience. The system has been evaluated in a real scenario, obtaining promising results.
  • Publication
    Adapting the Web for People With Upper Body Motor Impairments Using Touch Screen Tablets
    (Oxford University Press, 2017-11-01) Moreno López, Lourdes; Valencia, Xavier; Perez, J. Eduardo; Arrue, Myriam; Abascal, Julio; Duarte, Carlos; Ministerio de Economía, Industria y Competitividad (España)
    People with disabilities frequently use the Internet to perform a variety of common activities; however, they may often encounter aggravated accessibility barriers when using mobile devices to access the Web. In order to alleviate the problems faced by this group when using mobile devices, we have extended a previously developed transcoding-based system that adapts non-accessible web pages to the needs of specific users in order to enhance their accessibility. In this version, we included new adaptation techniques gathered from the literature in order to apply transcoding techniques to mobile devices. The enhanced system was evaluated with eight users with reduced mobility using tablets. The exploratory study suggests that alternative interaction methods such as the ones named 'end tap' and 'steady tap' are beneficial for some participants with reduced mobility, dexterity or strength in the upper limbs. Other results show that six of the eight users preferred the adapted version with enlarged interaction elements which required less physical effort, even if this adaptation increases the size of the page with the disadvantages associated with such a change.
  • Publication
    How to interweave accessibility with didactic and technological quality of digital educational materials
    (Universitat Politècnica de Catalunya (UPC), 2019-11-17) Moreno López, Lourdes; Fernandez-Pampillon, Ana Maria; Sarasa, Antonio; Rodrigo, Covadonga; Garcia-Villalobos, Julian; Gonzalez, Yolanda; Garcia-Mata, Ricardo
    Accessibility is a quality requirement for digital educational materials (or contents) in interactive learning environments. It ensures that students with disabilities do not face barriers when using such content. However, guaranteeing the accessibility of these materials is no easy task, at least for a significant part of the producers, evaluators, and users of educational materials, such as teachers. Proof of this can be found in the results of the case studies on the usability and reliability of technological accessibility evaluation standards conducted by Spanish Association for Standardisation (UNE) during the development of the Spanish Standard for the Quality of Digital Educational Materials UNE 71362. The results obtained show the difficulty of ensuring a good level of accessibility to digital educational materials, concluding that most creators and evaluators did not apply the guidelines due to either ignorance or difficulties. In order to minimise this problem, a new research approach has been taken based on unifying and abstracting the technology accessibility indicators from the regulations in force and integrating them, according to their applicability, transversally in the teaching and technological criteria of the new standard. This paper presents, explains and justifies this new approach in which the accessibility criteria are not isolated.
  • Publication
    Disambiguating Clinical Abbreviations Using a One-Fits-All Classifier Based on Deep Learning Techniques
    (Thieme, 2022-02-01) Jaber, Areej Mustafa Mahmoud; Martínez Fernández, Paloma; Comunidad de Madrid
    Abbreviations are considered an essential part of the clinical narrative; they are used not only to save time and space but also to hide serious or incurable illnesses. Misreckoning interpretation of the clinical abbreviations could affect different aspects concerning patients themselves or other services like clinical support systems. There is no consensus in the scientific community to create new abbreviations, making it difficult to understand them. Disambiguate clinical abbreviations aim to predict the exact meaning of the abbreviation based on context, a crucial step in understanding clinical notes
  • Publication
    Mechanistic interrogation of mutation-independent disease modulators of RDEB identifies the small leucine-rich proteoglycan PRELP as a TGF-beta antagonist and inhibitor of fibrosis
    (Elsevier, 2022-06-30) Chacon Solano, Esteban Gonzalo; León Canseco, Carlos; Carretero, M.; García Díez, Marta; Sánchez Domínguez, R.; Quero, F.; Méndez Jiménez, Estela; Bonafont Aragó, José; Ruiz Mezcua, María Belén; Escámez Toledano, María José; Larcher Laguzzi, Fernando; Rio Nechaevsky, Marcelan Andra del; European Commission; Ministerio de Economía y Competitividad (España)
    Recessive dystrophic epidermolysis bullosa (RDEB) is a genetic extracellular matrix disease caused by deficiency in type VII collagen (Col VII). The disease manifests with devastating mucocutaneous fragility leading to progressive fibrosis and metastatic squamous cell carcinomas. Although Col VII abundance is considered the main predictor of symptom course, previous studies have revealed the existence of mutation-independent mechanisms that control disease progression. Here, to investigate and validate new molecular modifiers of wound healing and fibrosis in a natural human setting, and toward development of disease-modulating treatment of RDEB, we performed gene expression profiling of primary fibroblast from RDEB siblings with marked phenotypic variations, despite having equal COL7A1 genotype. Gene enrichment analysis suggested that severe RDEB was associated with enhanced response to TGFB stimulus, oxidoreductase activity, and cell contraction. Consistently, we found an increased response to TGFB, higher levels of basal and induced reactive oxygen species (ROS), and greater contractile ability in collagen lattices in RDEB fibroblasts (RDEBFs) from donors with severe RDEB vs mild RDEB. Treatment with antioxidants allowed a reduction of the pro-fibrotic and contractile phenotype. Importantly, our analyses revealed higher expression and deposition in skin of the relatively uncharacterized small leucine-rich extracellular proteoglycan PRELP/prolargin associated with milder RDEB manifestations. Mechanistic investigations showed that PRELP effectively attenuated fibroblasts' response to TGFB stimulus and cell contractile capacity. Moreover, PRELP overexpression in RDEBFs enhanced RDEB keratinocyte attachment to fibroblast-derived extracellular matrix in the absence of Col VII. Our results highlight the clinical relevance of pro-oxidant status and hyper-responsiveness to TGFB in RDEB severity and progression. Of note, our study also reveals PRELP as a novel and natural TGFB antagonist with a likely dermo-epidermal pro-adhesive capacity.
  • Publication
    Modular 3-D-printed education tool for blind and visually impaired students oriented to net structures
    (IEEE, 2023-02) Domínguez Reyes, Ricardo; Moreno López, Lourdes; Muñoz Sánchez, Ana; Ruiz Mezcua, María Belén; Savoini Cardiel, Begoña
    Contribution: This article presents the design, creation, testing, and results after the use of a 3-D-printed educational tool that helped a blind student learning electric circuits theory in higher education. Background: Educational tools oriented to visually impaired and blind students in higher education are limited or even nonexistent in the STEM area. Previous developments on the field present in the literature, including other 3-D printing solutions, have been revised and compared to the proposed educational tool. Intended Outcomes: The tool was tested by a blind student in order to test the potential of the design to achieve a better understanding of the topology and performance of electric circuits. The main purpose of the tool described in this work is helping to increase the resources available in the field of teaching students with visual impairments. Application Design: 3-D technology has the potential to be used to create accessibility tools for visually impaired and blind individuals. Modular systems can be used to create complex structures using simple elements. A modular 3-D-printed tool was fabricated to help blind and visually impaired students to learn net structures. Findings: The 3-D tool has allowed the blind student to work autonomously in the study of simple electric circuits and supplies the teacher with a resource to communicate with the student in an easy and fast way. Updated design can be used to describe more complex net structures that can be applied to most electric circuits despite their complexity. The use of the modular system provided the blind student with a direct representation of the whole subject, even when it involved a great amount of graphical information and manipulation.
  • Publication
    Analyzing transfer learning impact in biomedical cross lingual named entity recognition and normalization
    (BMC, 2021-12-17) Rivera Zavala, Renzo; Martínez Fernández, Paloma; Ministerio de Economía y Competitividad (España)
    Background The volume of biomedical literature and clinical data is growing at an exponential rate. Therefore, efficient access to data described in unstructured biomedical texts is a crucial task for the biomedical industry and research. Named Entity Recognition (NER) is the first step for information and knowledge acquisition when we deal with unstructured texts. Recent NER approaches use contextualized word representations as input for a downstream classification task. However, distributed word vectors (embeddings) are very limited in Spanish and even more for the biomedical domain. Methods In this work, we develop several biomedical Spanish word representations, and we introduce two Deep Learning approaches for pharmaceutical, chemical, and other biomedical entities recognition in Spanish clinical case texts and biomedical texts, one based on a Bi-STM-CRF model and the other on a BERT-based architecture. Results Several Spanish biomedical embeddigns together with the two deep learning models were evaluated on the PharmaCoNER and CORD-19 datasets. The PharmaCoNER dataset is composed of a set of Spanish clinical cases annotated with drugs, chemical compounds and pharmacological substances; our extended Bi-LSTM-CRF model obtains an F-score of 85.24% on entity identification and classification and the BERT model obtains an F-score of 88.80% . For the entity normalization task, the extended Bi-LSTM-CRF model achieves an F-score of 72.85% and the BERT model achieves 79.97%. The CORD-19 dataset consists of scholarly articles written in English annotated with biomedical concepts such as disorder, species, chemical or drugs, gene and protein, enzyme and anatomy. Bi-LSTM-CRF model and BERT model obtain an F-measure of 78.23% and 78.86% on entity identification and classification, respectively on the CORD-19 dataset. Conclusion These results prove that deep learning models with in-domain knowledge learned from large-scale datasets highly improve named entity recognition performance. Moreover, contextualized representations help to understand complexities and ambiguity inherent to biomedical texts. Embeddings based on word, concepts, senses, etc. other than those for English are required to improve NER tasks in other languages.
  • Publication
    Lexical Simplification System to Improve Web Accessibility
    (IEEE, 2021-04-12) Alarcón García, Rodrigo; Moreno López, Lourdes; Martínez Fernández, Paloma; Comunidad de Madrid; Universidad Carlos III de Madrid
    People with intellectual, language and learning disabilities face accessibility barriers when reading texts with complex words. Following accessibility guidelines, complex words can be identified, and easy synonyms and definitions can be provided for them as reading aids. To offer support to these reading aids, a lexical simplification system for Spanish has been developed and is presented in this article. The system covers the complex word identification (CWI) task and offers replacement candidates with the substitute generation and selection (SG/SS) task. These tasks have followed machine learning techniques and contextual embeddings using Easy Reading and Plain Language resources, such as dictionaries and corpora. Additionally, due to the polysemy present in the language, the system provides definitions for complex words, which are disambiguated by a rule-based method supported by a state-of-the-art embedding resource. This system is integrated into a web system that provides an easy way to improve the readability and comprehension of Spanish texts. The results obtained are satisfactory; in the CWI task, better results were obtained than with other systems that used the same dataset. The SG/SS task results are comparable to similar works in the English language and provide a solid starting point to improve this task for the Spanish language. Finally, the results of the disambiguation process evaluation were good when evaluated by a linguistic expert. These findings represent an additional advancement in the lexical simplification of texts in Spanish and in a generic domain using easy-to-read resources, among others, to provide systematic support to compliance with accessibility guidelines
  • Publication
    Multimodal Fake News Detection
    (MDPI, 2022-06-02) Segura-Bedmar, Isabel; Alonso Bartolomé, Santiago; Comunidad de Madrid; Universidad Carlos III de Madrid
    Over the last few years, there has been an unprecedented proliferation of fake news. As a consequence, we are more susceptible to the pernicious impact that misinformation and disinformation spreading can have on different segments of our society. Thus, the development of tools for the automatic detection of fake news plays an important role in the prevention of its negative effects. Most attempts to detect and classify false content focus only on using textual information. Multimodal approaches are less frequent and they typically classify news either as true or fake. In this work, we perform a fine-grained classification of fake news on the Fakeddit dataset, using both unimodal and multimodal approaches. Our experiments show that the multimodal approach based on a Convolutional Neural Network (CNN) architecture combining text and image data achieves the best results, with an accuracy of 87%. Some fake news categories, such as Manipulated content, Satire, or False connection, strongly benefit from the use of images. Using images also improves the results of the other categories but with less impact. Regarding the unimodal approaches using only text, Bidirectional Encoder Representations from Transformers (BERT) is the best model, with an accuracy of 78%. Exploiting both text and image data significantly improves the performance of fake news detection.
  • Publication
    The RareDis corpus: A corpus annotated with rare diseases, their signs and symptoms
    (Elsevier, 2022-01) Martinez De Miguel, Claudia; Segura-Bedmar, Isabel; Chacon Solano, Esteban Gonzalo; Guerrero Aspizua, Sara; Comunidad de Madrid; Ministerio de Economía y Competitividad (España); Universidad Carlos III de Madrid
    Rare diseases affect a small number of people compared to the general population. However, more than 6,000 different rare diseases exist and, in total, they affect more than 300 million people worldwide. Rare diseases share as part of their main problem, the delay in diagnosis and the sparse information available for researchers, clinicians, and patients. Finding a diagnostic can be a very long and frustrating experience for patients and their families. The average diagnostic delay is between 6–8 years. Many of these diseases result in different manifestations among patients, which hampers even more their detection and the correct treatment choice. Therefore, there is an urgent need to increase the scientific and medical knowledge about rare diseases. Natural Language Processing (NLP) can help to extract relevant information about rare diseases to facilitate their diagnosis and treatments, but most NLP techniques require manually annotated corpora. Therefore, our goal is to create a gold standard corpus annotated with rare diseases and their clinical manifestations. It could be used to train and test NLP approaches and the information extracted through NLP could enrich the knowledge of rare diseases, and thereby, help to reduce the diagnostic delay and improve the treatment of rare diseases. The paper describes the selection of 1,041 texts to be included in the corpus, the annotation process and the annotation guidelines. The entities (disease, rare disease, symptom, sign and anaphor) and the relationships (produces, is a, is acron, is synon, increases risk of, anaphora) were annotated. The RareDis corpus contains more than 5,000 rare diseases and almost 6,000 clinical manifestations are annotated. Moreover, the Inter Annotator Agreement evaluation shows a relatively high agreement (F1-measure equal to 83.5% under exact match criteria for the entities and equal to 81.3% for the relations). Based on these results, this corpus is of high quality, supposing a significant step for the field since there is a scarcity of available corpus annotated with rare diseases. This could open the door to further NLP applications, which would facilitate the diagnosis and treatment of these rare diseases and, therefore, would improve dramatically the quality of life of these patients.
  • Publication
    Extracting information from radiology reports by Natural Language Processing and Deep Learning
    (Ceur Workshop Proceedings, 2021-09-21) Martín-Caro García-Largo, Miguel Ángel; Segura-Bedmar, Isabel; Comunidad de Madrid; Universidad Carlos III de Madrid
  • Publication
    Sarcasm detection with BERT
    (Sociedad Española para el Procesamiento del Lenguaje Natural, 2021-09-23) Scola, Elsa; Segura-Bedmar, Isabel; Comunidad de Madrid; Universidad Carlos III de Madrid
    Sarcasm is often used to humorously criticize something or hurt someone's feelings. Humans often have difficulty in recognizing sarcastic comments since we say the opposite of what we really mean. Thus, automatic sarcasm detection in textual data is one of the most challenging tasks in Natural Language Processing (NLP). It has also become a relevant research area due to its importance in the improvement of sentiment analysis. In this work, we explore several deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT) to address the task of sarcasm detection. While most research has been conducted using social media data, we evaluate our models using a news headlines dataset. To the best of our knowledge, this is the first study that applies BERT to detect sarcasm in texts that do not come from social media. Experiment results show that the BERT-based approach overcomes the state-of-the-art on this type of dataset.
  • Publication
    Evaluación de un modelo transformador aplicado a la tarea de generación de resúmenes en distintos dominios = Evaluation of a transformer model applied to the task of text summarization in different domains
    (Sociedad Española para el Procesamiento del Lenguaje Natural, 2021-03-01) Segura-Bedmar, Isabel; Ruz, Lucía; Guerrero Aspizua, Sara; Comunidad de Madrid; Ministerio de Economía y Competitividad (España); Universidad Carlos III de Madrid
    En los últimos años, las técnicas de deep learning han supuesto un gran impulso tecnológico en muchas de las tareas de Procesamiento de Lenguaje Natural (PLN). La tarea de generación de resúmenes también se ha beneficiado de estas técnicas, y en los últimos años se han implementado distintos modelos, logrando superar los resultados del estado de la cuestión. La mayoría de estos trabajos han sido evaluados en colecciones de textos periodísticos. Este artículo presenta un trabajo preliminar donde aplicamos un modelo transformador, BART, para la tarea de generación de resúmenes y lo evaluamos en varios datasets, uno de ellos formado por textos del dominio biomédico. = In recent years, deep learning techniques have provided a significant technological advance in many Natural Language Processing (NLP) tasks. Text summarization has also benefited from these techniques. Recently, several deep learning approaches have been implemented, surpassing the previous state of the art performances. Most of these works have been evaluated on collections of journalistic texts. This article presents a preliminary work where we apply a transforming model, BART, for text summarization. The model is evaluated on several datasets, one of them consisting of texts from the biomedical domain.
  • Publication
    Exploring the impact of covid-19 on social life by deep learning
    (MDPI, 2021-11) Jijon Vorbeck, José Antonio; Segura-Bedmar, Isabel; Comunidad de Madrid; Universidad Carlos III de Madrid
    Due to the globalisation of the COVID-19 pandemic, and the expansion of social media as the main source of information for many people, there have been a great variety of different reactions surrounding the topic. The World Health Organization (WHO) announced in December 2020 that they were currently fighting an “infodemic” in the same way as they were fighting the pandemic. An “infodemic” relates to the spread of information that is not controlled or filtered, and can have a negative impact on society. If not managed properly, an aggressive or negative tweet can be very harmful and misleading among its recipients. Therefore, authorities at WHO have called for action and asked the academic and scientific community to develop tools for managing the infodemic by the use of digital technologies and data science. The goal of this study is to develop and apply natural language processing models using deep learning to classify a collection of tweets that refer to the COVID-19 pandemic. Several simpler and widely used models are applied first and serve as a benchmark for deep learning methods, such as Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers (BERT). The results of the experiments show that the deep learning models outperform the traditional machine learning algorithms. The best approach is the BERT-based model.
  • Publication
    Mujeres intérpretes de lengua de signos en la TDT española
    (Centro de Normalización Lingüística de la Lengua de Signos Española, 2021) López Sánchez, Gema
    La existencia de los servicios de accesibilidad audiovisual en medios tan populares como la televisión, así como su regulación, su calidad y su implementación, han sido uno de los temas por excelencia dentro de la literatura académica relacionada con los estudios de la discapacidad o disability studies. Este estudio pretende profundizar e ir más allá del propio servicio de accesibilidad para ahondar en las características propias de los intérpretes de lengua de signos, en concreto, a razón de su género. ¿Qué género tiene más representación en la televisión? A esta pregunta de investigación, se ha hecho un análisis cuantitativo y comparativo del número de horas de televisión signada por hombres y por mujeres en todos los canales de la TDT española durante el mes de noviembre del año 2020.
  • Publication
    An IoT-based contribution to improve mobility of the visually impaired in Smart Cities
    (Springer, 2021-04-17) Rodrigo Salazar, Lucas; González Carrasco, Israel; García Ramírez, Alejandro Rafael
    The Internet of Things envisions that objects of everyday life will be equipped with sensors, microcontrollers, transceivers for digital communication and suitable protocol which communicates among them and with users, becoming an integral part of Internet. Due to the growing developments in digital technologies, Smart Cities have been equipped with different electronic devices based on IoT and several applications are being created for most diverse areas of knowledge making systems more efficient. However, Assistive technology is a field that is not enough explored in this scenario yet. In this work, an integrated framework with an IoT architecture customized for an electronic cane (electronic travel aid designed for the visually impaired) has been designed. The architecture is organized by a five-layer architecture: edge technology, gateway, Internet, middleware and application. This new feature brings the ability to connect to environment devices, receiving the coordinates of their geographic locations, alerting the user when it is close to anyone of these devices and sending those coordinates to a web application for smart monitoring. Preliminary studies and experimental tests with three blind users of the Cane show that this approach would contribute to get more spatial information from the environment improving mobility of visually impaired people.
  • Publication
    Framework for the Classification of Emotions in People With Visual Disabilities Through Brain Signals
    (Frontiers Media, 2021-05-07) López Hernández, Jesús Leonardo; González Carrasco, Israel; López Cuadrado, José Luis; Ruiz Mezcua, María Belén
    Nowadays, the recognition of emotions in people with sensory disabilities still represents a challenge due to the difficulty of generalizing and modeling the set of brain signals. In recent years, the technology that has been used to study a person’s behavior and emotions based on brain signals is the brain–computer interface (BCI). Although previous works have already proposed the classification of emotions in people with sensory disabilities using machine learning techniques, a model of recognition of emotions in people with visual disabilities has not yet been evaluated. Consequently, in this work, the authors present a twofold framework focused on people with visual disabilities. Firstly, auditory stimuli have been used, and a component of acquisition and extraction of brain signals has been defined. Secondly, analysis techniques for the modeling of emotions have been developed, and machine learning models for the classification of emotions have been defined. Based on the results, the algorithm with the best performance in the validation is random forest (RF), with an accuracy of 85 and 88% in the classification for negative and positive emotions, respectively. According to the results, the framework is able to classify positive and negative emotions, but the experimentation performed also shows that the framework performance depends on the number of features in the dataset and the quality of the Electroencephalogram (EEG) signals is a determining factor.