DI - Artículos de Revistas

Permanent URI for this collection

https://hdl.handle.net/10016/37011

Browse

Now showing 1 - 20 of 22

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts
(Springer Nature, 2022-07-06) Segura Bedmar, Isabel; Camino Perdones, David; Guerrero Aspizua, Sara; Comunidad de Madrid; Ministerio de Ciencia e Innovación (España)
Background and objective: Although rare diseases are characterized by low prevalence, approximately 400 million people are affected by a rare disease. The early and accurate diagnosis of these conditions is a major challenge for general practitioners, who do not have enough knowledge to identify them. In addition to this, rare diseases usually show a wide variety of manifestations, which might make the diagnosis even more difficult. A delayed diagnosis can negatively affect the patient"s life. Therefore, there is an urgent need to increase the scientific and medical knowledge about rare diseases. Natural Language Processing (NLP) and Deep Learning can help to extract relevant information about rare diseases to facilitate their diagnosis and treatments. Methods: The paper explores several deep learning techniques such as Bidirectional Long Short Term Memory (BiLSTM) networks or deep contextualized word representations based on Bidirectional Encoder Representations from Transformers (BERT) to recognize rare diseases and their clinical manifestations (signs and symptoms). Results: BioBERT, a domain-specific language representation based on BERT and trained on biomedical corpora, obtains the best results with an F1 of 85.2% for rare diseases. Since many signs are usually described by complex noun phrases that involve the use of use of overlapped, nested and discontinuous entities, the model provides lower results with an F1 of 57.2%. Conclusions: While our results are promising, there is still much room for improvement, especially with respect to the identification of clinical manifestations (signs and symptoms).
Embracing first-person perspectives in soma-based design
(MDPI, 2018-02-01) Isbister, Katherine; Márquez Segura, Elena
A set of prominent designers embarked on a research journey to explore aesthetics in movement-based design. Here we unpack one of the design sensitivities unique to our practice: A strong first person perspective-where the movements, somatics and aesthetic sensibilities of the designer, design researcher and user are at the forefront. We present an annotated portfolio of design exemplars and a brief introduction to some of the design methods and theory we use, together substantiating and explaining the first-person perspective. At the same time, we show how this felt dimension, despite its subjective nature, is what provides rigor and structure to our design research. Our aim is to assist researchers in soma-based design and designers wanting to consider the multiple facets when designing for the aesthetics of movement. The applications span a large field of designs, including slow introspective, contemplative interactions, arts, dance, health applications, games, work applications and many others.
Challenges and Opportunities of Agriculture Digitalization in Spain
(MDPI, 2023-01-01) Sadjadi, Ebrahim; Fernandez, Roemi; Comunidad de Madrid; European Commission; Ministerio de Ciencia e Innovación (España)
Motivated by the ongoing debate on food security and the global trend of adopting new emerging technologies in the aftermath of COVID-19, this research focuses on the challenges and opportunities of agriculture digitalization in Spain. This process of digital transformation of the agricultural sector is expected to significantly affect productivity, product quality, production costs, sustainability and environmental protection. For this reason, our study reviews the legal, technical, infrastructural, educational, financial and market challenges that can hinder or impose barriers to the digitalization of agriculture in Spain. In addition, the opportunities that digitalization can bring are identified, with the intention of contributing to provide insights that helps strengthen the Spanish agricultural model and make the necessary decision so that professionals in the sector are prepared to adapt to this intense change.
Yamove! A movement synchrony game that choreographs social interaction
(Centre of Sociological Research, 2016-05) Isbister, Katherine; Márquez Segura, Elena; Kirkpatrick, Suzanne; Chen, Xiaofeng; Salahuddin, Syed; Cao, Gang; Tang, Raybit
This paper presents a design case study of Yamove!, a well-received dance battle game. The primary aim for the project was to design a mobile-based play experience that enhanced in-person social interaction and connection. The game emphasized the pleasures of mutual, improvised amateur movement choreography at the center of the experience, achieved through a core mechanic of synchronized movement. The project team engaged techniques from the independent ("indie") game development community that proved valuable in tempering the constraints to which technologically driven design can sometimes fall prey. Contributions of this work include (a) presentation and discussion of a polished digital game that embodies design knowledge about engaging players in mutual physical improvisation that is socially supported by technology, and (b) a case study of a design process influenced by indie game development that may help others interested in creating technologies that choreograph pleasurable intentional human movement in social contexts.
Bodystorming for movement-based interaction design
(Centre of Sociological Research, 2016-11) Márquez Segura, Elena; Turmo Vidal, Laia; Rostami, Asreen
After a decade of movement-based interaction in human-computer interaction, designing for the moving body still remains a challenge. Research in this field requires methods to help access, articulate, and harness embodied experiences in ways that can inform the design process. To address this challenge, this article appropriates bodystorming, an embodied ideation method for movement-based interaction design. The proposed method allows for early consideration of the physical, collocated, and social aspects of a designed activity as illustrated with two explorative workshops in different application domains: interactive body games and interactive performances. Using a qualitative methods approach, we used video material from the workshops, feedback from participants, and our own experience as participants and facilitators to outline important characteristics of the bodystorming method in the domain of movement-based interaction. The proposed method is compared with previous ones and application implications are discussed.
Action sounds modulate arm reaching movements
(Frontiers, 2016-09) Tajadura Jiménez, Ana; Marquardt, Torsten; Swapp, David; Kitagawa, Norimichi; Bianchi-Berthouze, Nadia; Ministerio de Economía y Competitividad (España)
Our mental representations of our body are continuously updated through multisensory bodily feedback as we move and interact with our environment. Although it is often assumed that these internal models of body-representation are used to successfully act upon the environment, only a few studies have actually looked at how body-representation changes influence goal-directed actions, and none have looked at this in relation to body-representation changes induced by sound. The present work examines this question for the first time. Participants reached for a target object before and after adaptation periods during which the sounds produced by their hand tapping a surface were spatially manipulated to induce a representation of an elongated arm. After adaptation, participants' reaching movements were performed in a way consistent with having a longer arm, in that their reaching velocities were reduced. These kinematic changes suggest auditory-driven recalibration of the somatosensory representation of the arm morphology. These results provide support to the hypothesis that one's represented body size is used as a perceptual ruler to measure objects' distances and to accordingly guide bodily actions.
Identifying Real Estate Opportunities Using Machine Learning
(MDPI, 2018-11-22) Baldominos Gómez, Alejandro; Blanco, Ivan; Moreno, Antonio Jose; Iturrarte, Ruben; Bernardez, Oscar; Afonso, Carlos
The real estate market is exposed to many fluctuations in prices because of existing correlations with many variables, some of which cannot be controlled or might even be unknown. Housing prices can increase rapidly (or in some cases, also drop very fast), yet the numerous listings available online where houses are sold or rented are not likely to be updated that often. In some cases, individuals interested in selling a house (or apartment) might include it in some online listing, and forget about updating the price. In other cases, some individuals might be interested in deliberately setting a price below the market price in order to sell the home faster, for various reasons. In this paper, we aim at developing a machine learning application that identifies opportunities in the real estate market in real time, i.e., houses that are listed with a price substantially below the market price. This program can be useful for investors interested in the housing market. We have focused in a use case considering real estate assets located in the Salamanca district in Madrid (Spain) and listed in the most relevant Spanish online site for home sales and rentals. The application is formally implemented as a regression problem that tries to estimate the market price of a house given features retrieved from public online listings. For building this application, we have performed a feature engineering stage in order to discover relevant features that allows for attaining a high predictive performance. Several machine learning algorithms have been tested, including regression trees, k-nearest neighbors, support vector machines and neural networks, identifying advantages and handicaps of each of them.
Company Cybersecurity System: Assessment, Risks and Expectations
(Sciendo, 2023-10-27) Kuzior, Aleksandra; Yarovenko, Hanna; Brozek, Paulina; Sidelnyk, Natalia; Boyko, Anton; Vasilyeva, Tetyana
The consequences of Industry 4.0 have adverse side effects on cybercrime growth, which requires creating an effective cybersecurity system for companies. Therefore, this study aims to develop a composite indicator of company cybersecurity to assess its development needs. For this purpose, the authors modified Porter's method by constructing a superposition matrix based on the growth rates of cyber threats and risks, calculating their quantitative characteristics and a composite indicator. The computations are based on indicators for 2016-2022 characterizing cybersecurity vulnerabilities and the consequences of cyber threats: the share of companies experiencing one, six or more successful cyberattacks, considering the likely and very likely success of cyberattacks on them in the next 12 months, security threat and concern indices, the share of companies with a growing security budget affected by ransomware and experiencing a shortage of skilled IT security personnel, the cost of stolen or compromised credentials. As a result, cybersecurity needs increased significantly for 2020-2022, mainly due to digital transformation and the cyber threats growth after the COVID-19 pandemic. A comparative analysis of the proposed indicator with those characterizing the development of Indus-try 4.0 showed that the need for a reliable cybersecurity system is much more important than the active development of modern technologies. Spending on IT is also increasing, but not enough to meet the needs of cybersecurity development, except for the 2022 results. The proposed indicator is defined for companies worldwide, but its versatility allows the methodology to be applied to enterprises of various industries and sizes.
Challenges and Opportunities for Education Systems with the Current Movement toward Digitalization at the Time of COVID-19
(MDPI, 2023-01-01) Sadjadi, Ebrahim
The spread of coronavirus has caused the shutdown of businesses and classroom participation to enable social distancing. It has led to the promotion of digitalization in societies and online activities. This manuscript presents an overview of the measures education systems could take to present appropriate courses in accordance with the present movement toward digitalization, and other requirements of societies in the (post) crisis period.
SREQP: A Solar Radiation Extraction and Query Platform for the Production and Consumption of Linked Data from Weather Stations Sensors
(Hindawi, 2016-03-15) Sánchez-Cervantes, José Luis; Radzimski, Mateusz; Rodríguez-Enríquez, Cristian Aaron; Alor-Hernández, Giner; Rodríguez-Mazahua, Lisbeth; Sánchez-Ramírez, Cauauhtemoc; Rodríguez-González, Alejandro
Nowadays, solar radiation information is provided from sensors installed in different geographic locations and platforms of meteorological agencies. However, common formats such as PDF files and HTML documents to provide solar radiation information do not offer semantics in their content, and they may pose problems to integrate and fuse data from multiple resources. One of the challenges of sensors Web is the unification of data from multiple sources, although this type of information facilitates interoperability with other sensor Web systems. This research proposes architecture SREQP (Solar Radiation Extraction and Query Platform) to extract solar radiation data from multiple external sources and merge them on a single and unique platform. SREQP makes use of Linked Data to generate a set of triples containing information about extracted data, which allows final users to query data through a SPARQL endpoint. The conceptual model was developed by using known vocabularies, such as SSN or WGS84. Moreover, an Analytic Hierarchy Process was carried out for the evaluation of SREQP in order to identify and evaluate the main features of Linked-Sensor-Data and the sensor Web systems. Results from the evaluation indicated that SREQP contained most of the features considered essential in Linked-Sensor-Data and sensor Web systems.
Countering Cybercrime Risks in Financial Institutions: Forecasting Information Trends
(MDPI, 2022-12-16) Kuzior, Aleksandra; Brozek, Paulina; Kuzmendo, Olha; Yarovenko, Hanna; Vasilyeva, Tetyana
This article aims to forecast the information trends related to the most popular cyberattacks, seen as the cyber-crimes’ consequences reflecting on the Internet. The study database was formed based on online users’ search engine requests regarding the terms “Cyberattacks on the computer systems of a financial institution”, “Cyberattacks on the network infrastructure of a financial institution”, and “Cyberattacks on the cloud infra-structure of a financial institution”, obtained with Google Trends for the period from 16 April 2017 to 4 October 2022. The authors examined the data using the Z-score, the QS test, and the method of differences of average levels. The data were found to be non-stationary with outliers and a seasonal component, so exponential smoothing was applied to reduce fluctuations and clarify the trends. As a result, the authors built additive and multiplicative cyclical and trend-cyclical models with linear, exponential, and damped trends. According to the models’ quality evaluation, the best results were shown by the trend-cyclic additive models with an exponential trend for predicting cyberattacks on computer systems and the cloud infrastructure and a trend-cyclic additive model with a damped tendency for predicting cyberattacks on the network infrastructure. The obtained results indicate that the U.S. can expect cybercrimes in the country’s financial system in the short and medium term and develop appropriate countermeasures of a financial institution to reduce potential financial losses.
Analysis of Barriers to the Deployment of Health Information Systems: A Stakeholder Perspective
(2018-06-30) Serrano-Rico, Alan Edwin; García Guzmán, Javier; Xydopoulos, Georgios; Tarhini, Ali
This paper argues that the cross-analysis of barriers with stakeholders provides a richer picture than analyzing the barriers on their own, as most of the literature in this area does. To test this hypothesis, we used the data from 33 interviews across 19 different types of stakeholders that were involved in a telemedicine system for the Chronically-ill Patient. Our findings show encouraging results. For instance, it was found that the group of stakeholders who are directly related to the governance and policy-making identified most of the barriers. This finding may imply that this group is more aware of the challenges when implementing HIS, or it may suggest that this group poses more resistance due to the current economic and Organizational models in health care. It was also found that some barriers are cited by all stakeholders whereas others not, suggesting that some barriers may be more relevant than others.
Embodiment in a child-like talking virtual body influences object size perception, self-identification, and subsequent real speaking
(Springer Nature, 2017-08-29) Tajadura Jiménez, Ana; Banakou, Domna; Bianchi-Berthouze, Nadia; Slater, Mel; European Commission; Ministerio de Economía y Competitividad (España)
People's mental representations of their own body are malleable and continuously updated through sensory cues. Altering one's body-representation can lead to changes in object perception and implicit attitudes. Virtual reality has been used to embody adults in the body of a 4-year-old child or a scaled-down adult body. Child embodiment was found to cause an overestimation of object sizes, approximately double that during adult embodiment, and identification of the self with child-like attributes. Here we tested the contribution of auditory cues related to one's own voice to these visually-driven effects. In a 2 x 2 factorial design, visual and auditory feedback on one's own body were varied across conditions, which included embodiment in a child or scaled-down adult body, and real (undistorted) or child-like voice feedback. The results replicated, in an older population, previous findings regarding size estimations and implicit attitudes. Further, although auditory cues were not found to enhance these effects, we show that the strength of the embodiment illusion depends on the child-like voice feedback being congruent or incongruent with the age of the virtual body. Results also showed the positive emotional impact of the illusion of owning a child's body, opening up possibilities for health applications.
A survey on machine learning for recurring concept drifting data streams
(Elsevier, 2023-03-01) Suárez Cetrulo, Andrés L.; Quintana, David; Cervantes, Alejandro; Ministerio de Ciencia, Innovación y Universidades (España)
The problem of concept drift has gained a lot of attention in recent years. This aspect is key in many domains exhibiting non-stationary as well as cyclic patterns and structural breaks affecting their generative processes. In this survey, we review the relevant literature to deal with regime changes in the behaviour of continuous data streams. The study starts with a general introduction to the field of data stream learning, describing recent works on passive or active mechanisms to adapt or detect concept drifts, frequent challenges in this area, and related performance metrics. Then, different supervised and non-supervised approaches such as online ensembles, meta-learning and model-based clustering that can be used to deal with seasonalities in a data stream are covered. The aim is to point out new research trends and give future research directions on the usage of machine learning techniques for data streams which can help in the event of shifts and recurrences in continuous learning scenarios in near real-time.
Use of the Blue Ocean Strategy to obtain ports 4.0
(Universidad del Valle, 2021-01-01) Molina Serrano, Beatriz; Ortiz Rey, Noemi; González Cancelas, Nicoletta; Soler Flores, Francisco Jose; Camarero Orive, Alberto
La cuarta revolución industrial se caracteriza por una alta digitalización de los sistemas y los procesos. Esta revolución ha llegado a los puertos españoles. Estos llevan años invirtiendo en la implantación de nuevas tecnologías dirigidas a impulsar la sostenibilidad y la calidad medioambiental, así como a buscar una logística más eficiente y ordenada. Los puertos avanzan imparablemente hacia su transformación digital, que se materializa en los conocidos Puertos 4.0. Estos puertos inteligentes o Smart Ports, abarcan multitud de aspectos y variables. Automatización, digitalización, tecnologías que permiten la interoperabilidad, transparencia, descentralización y experiencia del cliente definen el contexto de aplicación del concepto 'Puertos 4.0' al sector logístico-portuario español. Cómo alcanzar un proceso de digitalización satisfactorio que permita avanzar hacia puerto 4.0 en el sistema portuario español es una de las cuestiones que se están planteando enlos últimos tiempos. El mundo portuario español podría representarse por un océano rojo, pues de forma muy generalista, se puede decir que está marcado por una feroz competencia carente de diferenciación. Por ello, con la propuesta lo que se pretende es llevar al sistema portuario español a un océano azul, donde una estrategia e innovación adecuada generan saltos de valor que hacen que los competidores sean irrelevantes porque los clientes comparan productos y servicios absolutamente diferentes. Para poderdar respuesta a ello se planta la Estrategia del Océano Azul, dejando de lado la competencia entre puertos y generando una nueva demanda. Del estudio desarrollado se concluye que los puertos españoles aún tienen un largo camino que recorrer en materia de sostenibilidad. Asimismo, se concluye que un nuevo modelo de gestión supondría la innovación en valor que necesaria en el proceso hacía puertos 4.0
Análisis Business Observation Tool de la sostenibilidad portuaria. Aplicación al sistema portuario español
(Programa Transporte y Territorio del Instituto de Geografía “Romualdo Ardissone”, Facultad de Filosofía y Letras, Universidad de Buenos Aires, 2021-12-21) Gonzalez Cancelas, Nicoletta; Santos Martin, Ana Eladia; Molina Serrano, Beatriz; Soler Flores, Francisco Jose
Cada día el mundo actual avanza, gracias a las numerosas investigaciones, el desarrollo de tecnologías, la aparición de las plataformas digitales y multitud de iniciativas de crecimiento. Actualmente casi todo está enfocado a proteger el medio ambiente y los recursos disponibles, haciendo un uso eficiente e inteligente de ellos no sólo para que la sociedad actual disfrute de ello, sino también las generaciones futuras, tal y como dictamina el concepto de desarrollo sostenible. Trasladado a los puertos, espacios destinados al flujo de mercancías, personas e información y abrigo de las naves, todas las actividades allí efectuadas han de velar y proteger su compromiso con la sostenibilidad. Por lo que se propone aquí un análisis minucioso de la sostenibilidad del sistema portuario español a través de una herramienta gráfica y pionera en el ámbito portuario como es el Business Observation Tool. Herramienta dedicada a dar inicio y reconocer elementos mínimos a considerar al formular una idea sobre la sostenibilidad portuaria, permitiendo conocer la realidad de las condiciones del entorno portuario y establecer los escenarios posibles para evolucionar más allá de la realidad observada
Testing contextualized word embeddings to improve NER in spanish clinical case narratives
(IEEE, 2020-08-24) Akhtyamova, Liliya; Martínez Fernández, Paloma; Verspoor, Karin; Cardiff, John; Ministerio de Economía y Competitividad (España)
In the Big Data era, there is an increasing need to fully exploit and analyze the huge quantity of information available about health. Natural Language Processing (NLP) technologies can contribute by extracting relevant information from unstructured data contained in Electronic Health Records (EHR) such as clinical notes, patients' discharge summaries and radiology reports. The extracted information can help in health-related decision making processes. The Named Entity Recognition (NER) task, which detects important concepts in texts (e.g., diseases, symptoms, drugs, etc.), is crucial in the information extraction process yet has received little attention in languages other than English. In this work, we develop a deep learning-based NLP pipeline for biomedical entity extraction in Spanish clinical narratives. We explore the use of contextualized word embeddings, which incorporate context variation into word representations, to enhance named entity recognition in Spanish language clinical text, particularly of pharmacological substances, compounds, and proteins. Various combinations of word and sense embeddings were tested on the evaluation corpus of the PharmacoNER 2019 task, the Spanish Clinical Case Corpus (SPACCC). This data set consists of clinical case sections extracted from open access Spanish-language medical publications. Our study shows that our deep-learning-based system with domain-specific contextualized embeddings coupled with stacking of complementary embeddings yields superior performance over a system with integrated standard and general-domain word embeddings. With this system, we achieve performance competitive with the state-of-the-art.
The impact of pretrained language models on negation and speculation detection in cross-lingual medical text: Comparative study
(JMIR Publications, 2020-12) Rivera Zabala, Renzo; Martínez Fernández, Paloma; Ministerio de Economía y Competitividad (España)
Background: Negation and speculation are critical elements in natural language processing (NLP)-related tasks, such as information extraction, as these phenomena change the truth value of a proposition. In the clinical narrative that is informal, these linguistic facts are used extensively with the objective of indicating hypotheses, impressions, or negative findings. Previous state-of-the-art approaches addressed negation and speculation detection tasks using rule-based methods, but in the last few years, models based on machine learning and deep learning exploiting morphological, syntactic, and semantic features represented as spare and dense vectors have emerged. However, although such methods of named entity recognition (NER) employ a broad set of features, they are limited to existing pretrained models for a specific domain or language. Objective: As a fundamental subsystem of any information extraction pipeline, a system for cross-lingual and domain-independent negation and speculation detection was introduced with special focus on the biomedical scientific literature and clinical narrative. In this work, detection of negation and speculation was considered as a sequence-labeling task where cues and the scopes of both phenomena are recognized as a sequence of nested labels recognized in a single step. Methods: We proposed the following two approaches for negation and speculation detection: (1) bidirectional long short-term memory (Bi-LSTM) and conditional random field using character, word, and sense embeddings to deal with the extraction of semantic, syntactic, and contextual patterns and (2) bidirectional encoder representations for transformers (BERT) with fine tuning for NER. Results: The approach was evaluated for English and Spanish languages on biomedical and review text, particularly with the BioScope corpus, IULA corpus, and SFU Spanish Review corpus, with F-measures of 86.6%, 85.0%, and 88.1%, respectively, for NeuroNER and 86.4%, 80.8%, and 91.7%, respectively, for BERT. Conclusions: These results show that these architectures perform considerably better than the previous rule-based and conventional machine learning-based systems. Moreover, our analysis results show that pretrained word embedding and particularly contextualized embedding for biomedical corpora help to understand complexities inherent to biomedical text.
NetVote: A strict-coercion resistance re-voting based internet voting scheme with linear filtering
(MDPI, 2020-09) Querejeta Azurmendi, Íñigo; Arroyo Guardeño, David; López Hernández Ardieta, Jorge; Hernández Encinas, Luis; Comunidad de Madrid; Ministerio de Economía y Competitividad (España)
This paper proposes NetVote, an internet voting protocol where usability and ease in deployment are a priority. We introduce the notion of strict coercion resistance, to distinguish between vote-buying and coercion resistance. We propose a protocol with ballot secrecy, practical everlasting privacy, verifiability and strict coercion resistance in the re-voting setting. Coercion is mitigated via a random dummy vote padding strategy to hide voting patterns and make re-voting deniable. This allows us to build a filtering phase with linear complexity, based on zero knowledge proofs to ensure correctness while maintaining privacy of the process. Voting tokens are formed by anonymous credentials and pseudorandom identifiers, achieving practical everlasting privacy, where even if dealing with a future computationally unbounded adversary, vote intention is still hidden. It is not assumed for voters to own cryptographic keys prior to the election, nor store cryptographic material during the election. This property allows voters not only to vote multiple times, but also from different devices each time, granting the voter a vote-from-anywhere experience. This paper builds on top of the paper published in CISIS'19. In this version, we modify the filtering. Moreover, we formally define the padding technique, which allows us to perform the linear filtering scheme. Similarly we provide more details on the protocol itself and include a section of the security analysis, where we include the formal definitions of strict coercion resistance and a game based definition of practical everlasting privacy. Finally, we prove that NetVote satisfies them all.
Image-based model parameter optimization using model-assisted generative adversarial networks
(IEEE, 2020-12) Alonso-Monsalve, Saúl; Whitehead, Leigh H.
We propose and demonstrate the use of a model-assisted generative adversarial network (GAN) to produce fake images that accurately match true images through the variation of the parameters of the model that describes the features of the images. The generator learns the model parameter values that produce fake images that best match the true images. Two case studies show excellent agreement between the generated best match parameters and the true parameters. The best match model parameter values can be used to retune the default simulation to minimize any bias when applying image recognition techniques to fake and true images. In the case of a real-world experiment, the true images are experimental data with unknown true model parameter values, and the fake images are produced by a simulation that takes the model parameters as input. The model-assisted GAN uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast fake-image production.

Browse

Recent Submissions