DIT - GAST - Artículos de Revistas

Permanent URI for this collection

http://dspace.uc3m.es/handle/10016/13076

Browse

Now showing 1 - 20 of 209

A new RNN based machine learning model to forecast COVID-19 incidence, enhanced by the use of mobility data from the bike-sharing service in Madrid
(Elsevier, 2023-06-01) Muñoz Organero, Mario; Callejo Pinardo, Patricia; Hombrados Herrera, Miguel Ángel; Agencia Estatal de Investigación (España); Ministerio de Ciencia e Innovación (España)
As a respiratory virus, COVID-19 propagates based on human-to-human interactions with positive COVID-19 cases. The temporal evolution of new COVID-19 infections depends on the existing number of COVID-19 infections and the people's mobility. This article proposes a new model to predict upcoming COVID-19 incidence values that combines both current and near-past incidence values together with mobility data. The model is applied to the city of Madrid (Spain). The city is divided into districts. The weekly COVID-19 incidence data per district is used jointly with a mobility estimation based on the number of rides reported by the bike-sharing service in the city of Madrid (BiciMAD). The model employs a Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) to detect temporal patterns for COVID-19 infections and mobility data, and combines the output of the LSTM layers into a dense layer that can learn the spatial patterns (the spread of the virus between districts). A baseline model that employs a similar RNN but only based on the COVID-19 confirmed cases with no mobility data is presented and used to estimate the model gain when adding mobility data. The results show that using the bike-sharing mobility estimation the proposed model increases the accuracy by 11.7% compared with the baseline model.
Technologies for Data-Driven Interventions in Smart Learning Environments [Editorial]
(IEEE, 2023-06-01) Hernández-Leo, Davinia; Muñoz Merino, Pedro José; Bote Lorenzo, Miguel L.; Gasevic, Dragan; Jarvela, Sanna; Ministerio de Ciencia e Innovación (España)
Smart Learning environments (SLEs) are defined [1] as learning ecologies where students engage in learning activities, or where teachers facilitate such activities with the support of tools and technology. SLEs can encompass physical or virtual spaces in which a system senses the learning context and process by collecting data, analyzes the data, and consequently reacts with customized interventions that aim at improving learning [1]. In this way, SLEs may collect data about learners and educators’ actions and interactions related to their participation in learning activities as well as about different aspects of the formal or informal context in which they can be carried out. Sources from these data may include learning management systems, handheld devices, computers, cameras, microphones, wearables, and environmental sensors. These data can then be transformed and analyzed using different computational and visualization techniques to obtain actionable information that can trigger a wide range of automatic, human-mediated, or hybrid interventions, which involve learners and teachers in the decision making behind the interventions.
Prototyping low-cost and flexible vehicle diagnostic systems
(Ediciones Universidad de Salamanca, 2016-12-01) García Valls, María Soledad; Ministerio de Economía y Competitividad (España)
Diagnostic systems are software and hardware-based equipment that interoperate with an external monitored system. Traditionally, they have been expensive equipment running test algorithms to monitor physical properties of, e.g., vehicles, or civil infrastructure equipment, among others. As computer hardware is increasingly powerful (whereas its cost and size is decreasing) and communication software becomes easier to program and more run-time efficient, new scenarios are enabled that yield to lower cost monitoring solutions. This paper presents a low cost approach towards the development of a diagnostic systems relying on a modular component-based approach and running on a resource limited embedded computer. Results on a prototype implementation are shown that validate the presented design, its flexibility, performance, and communication latency.
Planning and performance challenges in power line communications networks for Smart Grids
(SAGE Journals, 2016-03) Seijo Simo, Miguel; López López, Gregorio Ignacio; Matanza, Javier; Moreno Novella, José Ignacio; Ministerio de Economía y Competitividad (España)
The Smart Grid represents a revolution especially at distribution and customer levels, bringing monitoring and control capabilities, traditionally available up to the primary substations, down to the secondary substations, and beyond. Machine-to-Machine (M2M) communications networks are key to enable managing the huge number of sensors and actuators distributed all over the low voltage and medium voltage networks. Such M2M communications networks must meet demanding requirements from the technical perspective (e.g., low latency, high availability), since eventually the stability of the grid may rely on them, and from the economic perspective (e.g., low deployment and operational costs), due to the huge volume of devices to be monitored and controlled. Thus, Power Line Communications (PLC) technologies are winning momentum in these scenarios because they represent a great trade-off between both perspectives. However, electrical networks also represent a harsh communications medium, mainly because they are not designed for data communications, but for power transmission. Consequently, although much research has been carried out on this topic recently, PLC networks still present technological problems and challenges. This paper highlights some of the most relevant challenges in this area and presents a set of cutting-edge software tools which are being developed to overcome them, facilitating the planning, deployment, and operation of this kind of networks.
Analysis of secure TCP/IP profile in 61850 based substation automation system for smart grids
(SAGE Journals, 2016-04) Khaled, Omar; Marín López, Andrés; Almenares Mendoza, Florina; Arias, Patricia; Díaz Sánchez, Daniel; Ministerio de Economía y Competitividad (España)
Smart grid is the term used to describe modern power grids. It aims at achieving efficient, sustainable, economic, and secure delivery of electricity supplies. In order to achieve these goals, communication between different components within the grid and control centers is required. In a rapidly growing world, the demands for substation automation are increasing. Recently, two trends have been changing Substation Automation Systems: IEC 61850 and the need for cybersecurity. IEC 61850 specifies very strict performance requirements for message transfer time. The security for the smart grid must be designed to satisfy both performance and reliability requirements. In this paper, we address a study about secure communication in the substation real-time environment, complying with the IEC 61850 specifications. We mainly focus on analyzing the proposed Secure TCP/IP profile for MMS, testing different cipher suite combinations and examining whether by applying TLS we can still achieve the strict performance requirements of IEC 61850 or not. As a result of the study, we propose a list of cipher suite combinations that should be used. The importance of this study lies mainly on future scenarios, because IEC 61850 is thought to support smart metering communications.
Achievements and challenges in learning analytics in Spain: The view of SNOLA
(UNED, 2020-07-01) Martínez Monés, Alejandra; Dimitriadis Damoulis, Yannis; Acquila-Natale, Emiliano; Álvarez, Ainhoa; Caeiro Rodriguez, Manuel; Cobos Pérez, Ruth; Conde González, Miguel Ángel; Garcia Peñalvo, Francisco Jose; Hernández Leo, Davinia; Menchaca Sierra, Iratxe; Muñoz Merino, Pedro José; Ros, Salvador; Sancho Vinuesa, Teresa; Comunidad de Madrid; Ministerio de Ciencia, Innovación y Universidades (España)
As in other research fields, the development of learning analytics is influenced by the networks of researchers that contribute to it. This paper describes one of such networks: the Spanish Network of Learning Analytics (SNOLA). The paper presents the research lines of the members of SNOLA, as well as the main challenges that learning analytics has to address in the next few years as perceived by these researchers. This analysis is based on SNOLA's archival data and on a survey carried out to the current members of the network. Although this approach does not cover all the activity related to learning analytics in Spain, the results provide a representative overview of the current state of research related to learning analytics in this context. The paper describes these trends and the main challenges, among which we can point out the need to adopt an ethical commitment with data, to develop systems that respond to the requirements of the end users, and to reach a wider institutional impact.
Specification and unattended deployment of home networks at the edge of the network
(IEEE, 2020-11) Bernabé Sánchez, Iván; Díaz Sánchez, Daniel; Muñoz Organero, Mario; Comunidad de Madrid; Agencia Estatal de Investigación (España)
Consumer devices continue to expand their capabilities by connecting to digital services and other devices to form information-sharing ecosystems. This is complex and requires meeting connection requirements and minimal processing capabilities to ensure communication. The emergence of new services, and the evolution of current technologies, constantly redefine the rules of the game by opening up new possibilities and increasing competition among service providers. Paradigms such as edge computing, softwarization of physical devices, self-configuration mechanisms, definition of software as a code and interoperability between devices, define design principles to be taken into account in future service infrastructures. This work analyzes these principles and presents a programmable architecture in which services and virtual devices are instantiated in any computing infrastructure, as cloud or edge computing, upon request according to the needs specified by service providers or users. Considering that the target computing infrastructures are heterogeneous, the solution defines network elements and provides network templates to ensure it can be deployed on different infrastructures irrespectively of the vendor. A prototype has been developed and tested on a virtualized cloud-based home network relying on open source solutions.
Guest editorial learning analytics in Iberoamerica
(IEEE, 2022-08) Muñoz Merino, Pedro José; Pérez Sanagustín, María del Mar; Zúñiga Prieto, Miguel Ángel; Ministerio de Ciencia e Innovación (España); Agencia Estatal de Investigación (España)
Learning analytics is a key knowledge area for the improvement of education that proposes the use of educational data to improve decision making. In the last years, the Iberoamerican region has made a lot of efforts to introduce learning analytics and take advantage of its advantages. In this Special Issue, a set of proposals of learning analytics in this region are presented. The Special Issue includes four articles that cover a wide range of topics of this area, including adoption at the institutional level, analytics applied to academic improvement, video analysis, or visual analytics in learning management systems.
The Effects of the COVID-19 Pandemic on the Digital Competence of Educators
(MDPI, 2023-01) García Gutiérrez, Boni; Alario-Hoyos, Carlos; Pérez Sanagustín, Mar; Morales, Miguel; Jerez, Óscar; European Commission
The COVID-19 pandemic is having an undeniable impact on all aspects of society. Regarding teaching and learning activities, most educational institutions suspended in-person instruction and moved to remote emergency teaching during the lockdown of March and April 2020. Although many countries progressively re-opened their educational systems, online and hybrid education became a common practice aimed at reducing the spread of the COVID-19 disease. This disruption has caused an unprecedented acceleration in the digitalization of teaching and learning. Teaching professionals have been forced to develop their digital competence quickly, achieving mastery in the management of information, creation of audiovisual content, and use of technology to keep their students engaged. This Special Issue (SI) presents contributions regarding adopting distance learning strategies, experiences, or lessons learned in this domain.
Enhancing Web Applications Observability through Instrumented Automated Browsers
(Elsevier, 2023-09) García Gutiérrez, Boni; Ricca, Filippo; Alamo, Jose M. Del; Leotta, Maurizio; Comunidad de Madrid; Agencia Estatal de Investigación (España)
In software engineering, observability is the ability to determine the current state of a software system based on its external outputs or signals such as metrics, logs, or traces. Web engineers rely on the web browser console as the primary tool to monitor the client-side of web applications during end-to-end tests. However, this is a manual and time-consuming task due to the different browsers available. This paper presents BrowserWatcher, an open-source browser extension providing cross-browser capabilities to observe web applications and automatically gather browser console logs in different browsers (e.g., Chrome, Firefox, or Edge). We have leveraged this extension to conduct an empirical study analyzing the browser console of the top-50 public websites manually and automatically. The results show that BrowserWatcher gathers all the well-known log categories such as console or error traces. It also reveals that each web browser additionally includes other types of logs, which differ among browsers, thus providing distinct pieces of information for the same website.
Space-Distributed Traffic-Enhanced LSTM-Based Machine Learning Model for COVID-19 Incidence Forecasting
(Hindawi, 2022-11-18) Muñoz Organero, Mario
The COVID-19 virus continues to generate waves of infections around the world. With major areas in developing countries still lagging behind in vaccination campaigns, the risk of new variants that can cause re-infections worldwide makes the monitoring and forecasting of the evolution of the virus a high priority. Having accurate models able to forecast the incidence of the spread of the virus provides help to policymakers and health professionals in managing the scarce resources in an optimal way. In this paper, a new machine learning model is proposed to forecast the spread of the virus one-week ahead in a geographic area which combines mobility and COVID-19 incidence data. The area is divided into zones or districts according to the location of the COVID-19 measuring points. A traffic-driven mobility estimate among adjacent districts is proposed to capture the spatial spread of the virus. Traffic-driven mobility in adjacent districts will be used together with COVID-19 incidence data to feed a new deep learning LSTM-based model which will extract patterns from mobility-modulated COVID-19 incidence spatiotemporal data in order to optimize one-week ahead estimations. The model is trained and validated with open data available for the city of Madrid (Spain) for 3 different validation scenarios. A baseline model based on previous literature able to extract temporal patterns in COVID-19 incidence time series is also trained with the same dataset. The results show that the proposed model, based on the combination of traffic and COVID-19 incidence data, is able to outperform the baseline model in all the validation scenarios.
Security perspective of wireless sensor networks
(Universidad Industrial de Santander, 2021) Gutiérrez-Portela, Fernando; Almenares Mendoza, Florina; Calderón-Benavides, Liliana; Romero-Riaño, Efren
In Wireless Sensor Networks (WSN), nodes are vulnerable to security attacks because they are installed in a harsh environment with limited power and memory, low processing power, and medium broadcast transmission.Therefore, identifying threats, challenges, and solutions of security and privacy is a talkingtopic today. This article analyzes the research work that has been carried out on the security mechanisms for the protection of WSN against threats and attacks, as well as the trends that emerge in other countries combined with future research lines. From the methodological point of view, this analysis is shown through the visualization and study of works indexed in databases such as IEEE, ACM, Scopus,and Springer, with a range of 7 years as an observation window, from 2013 to 2019. A total of 4,728 publications were obtained, with a high rate of collaborationbetween China and India. The research raised developments, such as advances in security principles and defense mechanisms, which have led to the design of countermeasures in intrusion detection. Finally, the results show the interest of the scientific andbusiness community in the use of artificial intelligence and machine learning (ML) to optimize performance measurements.
TLS/PKI Challenges and Certificate Pinning Techniques for IoT and M2M Secure Communications
(IEEE, 2019-11) Díaz Sánchez, Daniel; Marín López, Andrés; Almenares Mendoza, Florina; Arias Cabarcos, Patricia; Sherratt, R. Simon; Comunidad de Madrid; Ministerio de Economía y Competitividad (España)
Transport layer security (TLS) is becoming the de facto standard to provide end-to-end security in the current Internet. IoT and M2M scenarios are not an exception since TLS is also being adopted there. The ability of TLS for negotiating any security parameter, its flexibility and extensibility are responsible for its wide adoption but also for several attacks. Moreover, as it relies on public key infrastructure (PKI) for authentication, it is also affected by PKI problems. Considering the advent of IoT/M2M scenarios and their particularities, it is necessary to have a closer look at TLS history to evaluate the potential challenges of using TLS and PKI in these scenarios. According to this, this paper provides a deep revision of several security aspects of TLS and PKI, with a particular focus on current certificate pinning solutions in order to illustrate the potential problems that should be addressed.
Fostering the use of online learning resources: results of using a mobile collaboration tool based on gamification in a blended course
(Taylor & Francis, 2021-03-05) Ramírez Donoso, Luis; Pérez Sanagustín, Mar; Neyem, Andrés; Alario-Hoyos, Carlos; Hilliger, Isabel; Rojos, Felipe; Comunidad de Madrid; Agencia Estatal de Investigación (España)
Over the past years, higher education institutions have been exploring different mechanisms to adapt their learning and teaching practices to increase students’ engagement. One of the proposals has been to reuse Massive Online Open Courses (MOOCs) as Small Online Private Courses (SPOCs), or as complementary resources in traditional courses through blended learning practices, such as flipped classroom. However, the integration of online courses as a complement to face-to-face courses poses some challenges. First, students are not used to such blended learning approaches and it is generally difficult for teachers to motivate them to access online resources for the preparation of face-to-face sessions. Second, students are not used to the dynamics of blended learning scenarios, which are less teacher-centered and require their active participation. We propose the use of the mobile application MyMOOCSpace (MMS) to meet these challenges and increase students’ motivation and use of learning resources in blended learning courses that use SPOCs as a complement. MMS is a mobile learning application based on gamification mechanisms to promote collaboration and motivation of students in the use of digital resources as a complement to blended learning courses. In this paper, we present the results of a quasi-experiment in a blended course with 294 students that uses a SPOC as a complement, with the aim to assess the effect of MMS on students’ motivation and learning resources consumption. In particular, the behavior of two groups of students with the main digital resources of the SPOC (videos and formative assessments) was analyzed: one using the MMS (GTest group), and the other not using MMS (GTrad group). The results suggest that the use of MMS had a positive correlation with the videos consumption, besides increasing student’ interaction with assessment exercises in the SPOC.
Special Issue on Advanced Technologies in Lifelong Learning [Editorial]
(MDPI, 2022-08-01) Alario-Hoyos, Carlos
Designing your first MOOC from scratch: recommendations after teaching "Digital Education of the Future"
(Open Education Europa, 2014-03) Alario-Hoyos, Carlos; Pérez Sanagustín, Mar; Delgado Kloos, Carlos; Gutiérrez Rojas, Israel; Leony Arreaga, Derick Antonio; Parada Gélvez, Hugo Alexer; Comunidad de Madrid; Ministerio de Economía y Competitividad (España)
Massive Open Online Courses (MOOCs) have been a very promising innovation in higher education for the last few months. Many institutions are currently asking their staff to run high quality MOOCs in a race to gain visibility in an education market that is beginning to be full of choices. Nevertheless, designing and running a MOOC from scratch is not an easy task and requires a high workload. This workload should be shared among those generating contents, those fostering discussion in the community around the MOOC, those supporting the recording and subtitling of audiovisual materials, and those advertising the MOOC, among others. Sometimes the teaching staff has to assume all these tasks (and consequently the associated workload) due to the lack of adequate resources in the institution. This is just one example of the many problems that teachers need to be aware of before riding the MOOC wave. This paper offers a set of recommendations that are expected to be useful for those inexperienced teachers that now face the challenge of designing and running MOOCs. Most of these recommendations come from the lessons learned after teaching a nine-week MOOC on educational technologies, called “Digital Education of the Future”, at the Universidad Carlos III in Madrid, Spain.
Finite-blocklength results for the A-channel: applications to unsourced random access and group testing
(IEEE, 2022-09-27) Lancho Serrano, Alejandro; Fengler, Alexander; Polyanskiy, Yury; European Commission
We present finite-blocklength achievability bounds for the unsourced A-channel. In this multiple-access channel, users noiselessly transmit codewords picked from a common codebook with entries generated from a q -ary alphabet. At each channel use, the receiver observes the set of different transmitted symbols but not their multiplicity. We show that the A-channel finds applications in unsourced random-access (URA) and group testing. Leveraging the insights provided by the finite-blocklength bounds and the connection between URA and non-adaptive group testing through the A-channel, we propose improved decoding methods for state-of-the-art A-channel codes and we showcase how A-channel codes provide a new class of structured group testing matrices. The developed bounds allow to evaluate the achievable error probabilities of group testing matrices based on random A-channel codes for arbitrary numbers of tests, items and defectives. We show that such a construction asymptotically achieves the optimal number of tests. In addition, every efficiently decodable A-channel code can be used to construct a group testing matrix with sub-linear recovery time.
A finite-blocklength analysis for URLLC with Massive MIMO
(IEEE, 2021-06-14) Lancho Serrano, Alejandro; Östman, Johan; Giuseppe, Durisi; Sanguinetti, Luca
This paper presents a rigorous finite-blocklength framework for the characterization and the numerical evaluation of the packet error probability achievable in the uplink and downlink of Massive MIMO for ultra-reliable low-latency communications (URLLC). The framework encompasses imperfect channel-state information, pilot contamination, spatially correlated channels, and arbitrary linear signal processing. For a practical URLLC network setup involving base stations with M = 100 antennas, we show by means of numerical results that a target error probability of 10 −5 can be achieved with MMSE channel estimation and multicell MMSE signal processing, uniformly over each cell, only if orthogonal pilot sequences are assigned to all the users in the network. For the same setting, an alternative solution with lower computational complexity, based on least-squares channel estimation and regularized zero-forcing signal processing, does not suffice unless M is increased significantly.
SEEK-AT-WD: A social-semantic infrastructure to sustain educational ICT tool descriptions in the web of data
(International Forum of Educational Technology and Society, 2014-04) Ruiz-Calleja, Adolfo; Vega-Gorgojo, Guillermo; Asensio-Perez, Juan I.; Gómez-Sánchez, Eduardo; Bote-Lorenzo, Miguel L.; Alario-Hoyos, Carlos; Ministerio de Economía y Competitividad (España)
There are several Information and Communication Technology (ICT) tool registries that support educators when searching ICT tools for their classrooms. A common problem in these registries is how their data is sustained, since educational descriptions of ICT tools are hard to create and maintain updated. This paper proposes SEEK-AT-WD, an infrastructure that aims at sustaining an educational ICT tool registry in the Web of Data following a social-semantic approach. Its key idea is to take advantage of the data already published in the Web to sustain a collection of ICT tool descriptions, as well as to enable the community of educators to enrich this collection sharing their experience using ICT tools. Following this approach, 6760 descriptions of educational ICT tools have been retrieved from the Web of Data to build an initial dataset. Moreover, the descriptions obtained from the Web are automatically updated without human intervention while more than a hundred tool descriptions have been enriched by educators. Finally, a search system and an annotation tool are presented to illustrate that educational applications can take advantage of SEEK-AT-WD.
A competency framework for teaching and learning innovation centers for the 21st century: anticipating the post-COVID-19 age
(MDPI, 2022-02-01) Pérez Sanagustín, Mar; Kotorov, Louri; Teixeira, António; Mansilla, Fernanda; Broisin, Julien; Alario-Hoyos, Carlos; Jerez, Óscar; Teixeira Pinto, Maria Do Carmo; García Gutiérrez, Boni; Delgado Kloos, Carlos; Morales, Miguel; Solarte, Mario; Oliva-Córdova, Luis Magdiel; Gonzalez Lopez, Astrid Helena
During the COVID-19 pandemic, most Higher Education Institutions (HEIs) across the globe moved towards “emergency online education”, experiencing a metamorphosis that advanced their capacities and competencies as never before. Teaching and Learning Centers (TLCs), the internal units that promote sustainable transformations, can play a key role in making this metamorphosis last. Existing models for TLCs have defined the competencies that they could help develop, focusing on teachers’, students’, and managers’ development, but have mislead aspects such as leadership, organizational processes, and infrastructures. This paper evaluates the PROF-XXI framework, which offers a holistic perspective on the competencies that TLCs should develop for supporting deep and sustainable transformations of HEIs. The framework was evaluated with 83 participants from four Latin American institutions and used for analyzing the transformation of their teaching and learning practices during the pandemic lockdown. The result of the analysis shows that the PROF-XXI framework was useful for identifying the teaching and learning competencies addressed by the institutions, their deficiencies, and their strategic changes. Specifically, this study shows that most institutions counted with training plans for teachers before this period, mainly in the competencies of digital technologies and pedagogical quality, but that other initiatives were created to reinforce them, including students’ support actions.

Browse

Recent Submissions