Ph.D. from the University of Oviedo in Computer Engineering. Master in Software Engineering from the Pontifical University of Salamanca and B.S. in Computer Science from Autonomous University of Santo Domingo. He has participated in several research projects, He has taught computer science at various schools and universities and has worked in software development companies and IT Consulting for many years. He has published several articles in international journals and conferences. Currently working as Assistant Professor at the University of Oviedo in Spain. His research interests include Software Engineering, Object-Oriented technology, Web Engineering, Recommendation Systems, Modeling Software with DSL and MDA.
Ponencia de la conferencia "17th International Conference on New Trends in Intelligent Softw... more Ponencia de la conferencia "17th International Conference on New Trends in Intelligent Software Methodology Tools and Techniques, SoMeT 2018; Granada; Spain; 26 September 2018 through 28 September 2018"
El proyecto consiste en la realización de una plataforma digital que permite la realización autom... more El proyecto consiste en la realización de una plataforma digital que permite la realización automática de actas de coordinación de asignaturas a partir de los hilos de las conversaciones establecidas en los envíos de correos electrónicos por parte de los diferentes equipos docentes participantes en dichas asignaturas. Las actas pueden generarse a partir de las conversaciones de los docentes, así como de la comunicación entre alumnos y docentes. Este trabajo se motiva en que las reuniones realizadas de forma virtual raramente van acompañadas de un acta donde se deja constancia de los participantes, de sus declaraciones, de las fechas en las que se realizaron las mismas y de las conclusiones a las que se llegaron. El principal objetivo es de dejar constancia de todos los trabajos de coordinación realizados de una forma sencilla, sin que para ello los intervinientes tengan que realizar ninguna tarea adicional, a partir de los correos enviados entre profesores alumnos de una asignatura....
El proyecto consiste en la realización de una plataforma digital que permite la realización autom... more El proyecto consiste en la realización de una plataforma digital que permite la realización automática de actas de coordinación de asignaturas a partir de los hilos de las conversaciones establecidas en los envíos de correos electrónicos por parte de los diferentes equipos docentes participantes en dichas asignaturas. Las actas pueden generarse a partir de las conversaciones de los docentes, así como de la comunicación entre alumnos y docentes. Este trabajo se motiva en que las reuniones realizadas de forma virtual raramente van acompañadas de un acta donde se deja constancia de los participantes, de sus declaraciones, de las fechas en las que se realizaron las mismas y de las conclusiones a las que se llegaron. El principal objetivo es de dejar constancia de todos los trabajos de coordinación realizados de una forma sencilla, sin que para ello los intervinientes tengan que realizar ninguna tarea adicional, a partir de los correos enviados entre profesores alumnos de una asignatura....
Abstract Social media generate a massive amount of information each day. This information is usua... more Abstract Social media generate a massive amount of information each day. This information is usually generated by people and may be used for many studies. Social media mining is a growing discipline inside data mining, and the results have proven to be quite revealing. Getting the data to work with might seem to be the easiest task in the process, but it can be very challenging for people without programming knowledge. Thus, there are numerous ways to extract information from social media, such as to use the network API, a Web scraper or specialized libraries. Using a straightforward and a cross social media query language we can hide the complexity of those mechanisms and gather information in a more efficient and easier way. This is because many social media share common elements, so we can create and unify queries to search, find and extract information from those platforms. In this paper, we propose a domain-specific query language, specially designed to allow developers or domain experts to extract data from different social media. With this language we unify and simplify the mechanisms of data extraction from social networks such as Twitter and Facebook.
Monte Carlo Tree Search is one of the main search methods studied presently. It has demonstrated ... more Monte Carlo Tree Search is one of the main search methods studied presently. It has demonstrated its efficiency in the resolution of many games such as Go or Settlers of Catan and other different problems. There are several optimizations of Monte Carlo, but most of them need heuristics or some domain language at some point, making very difficult its application to other problems. We propose a general and optimized implementation of Monte Carlo Tree Search using neural networks without extra knowledge of the problem. As an example of our proposal, we made use of the Dots and Boxes game. We tested it against other Monte Carlo system which implements specific knowledge for this problem. Our approach improves accuracy, reaching a winning rate of 81% over previous research but the generalization penalizes performance.
Social networks are an inexhaustible source of knowledge. One of its main uses is to express opin... more Social networks are an inexhaustible source of knowledge. One of its main uses is to express opinions about a particular product or service. Thus, users usually write opinions about places or so-called points of interest. That is a valuable knowledge for other users and especially for users who know and trust the opinions of the writers. In this work, we present an overview of a platform to capture opinions related to places and generate a positive or a negative recommendation for users based on both the global use of Twitter as well as the comments made by trusted people on the network.
Artificial intelligence allows computer systems to make decisions similar to those of humans. How... more Artificial intelligence allows computer systems to make decisions similar to those of humans. However, the expert knowledge that artificial intelligence systems have is rarely used to teach non-expert humans in a specific knowledge domain. In this paper, we want to explore this possibility by proposing a tool which presents and explains recommendations for playing board games generated by a Monte Carlo Tree Search algorithm combined with Neural Networks. The aim of the aforementioned tool is to showcase the information in an easily interpretable way and to effectively transfer knowledge: in this case, which movements should be avoided, and which action is recommended. Our system displays the state of the game in the form of a tree, showing all the movements available from the current state and a set of their successors. To convince and try to teach people, the tool offers a series of queries and all information available about every possible movement. In addition, it produces a brie...
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2020
Monte-Carlo methods are the basis for solving many computational problems using repeated random s... more Monte-Carlo methods are the basis for solving many computational problems using repeated random sampling in scenarios that may have a deterministic but very complex solution from a computational point of view. In recent years, researchers are using the same idea to solve many problems through the so-called Monte-Carlo Tree Search family of algorithms, which provide the possibility of storing and reusing previously calculated results to improve precision in the calculation of future outcomes. However, developers and researchers working in this area tend to have to carry out software developments from scratch to use their designs or improve designs previously created by other researchers. This makes it difficult to see improvements in current algorithms as it takes a lot of hard work. This work presents JGraphs, a toolset implemented in the Java programming language that will allow researchers to avoid having to reinvent the wheel when working with Monte-Carlo Tree Search. In addition...
Email services nowadays are flooded by spam and phishing attacks. Email service providers build t... more Email services nowadays are flooded by spam and phishing attacks. Email service providers build their own email filters to protect the final users from such attacks resulting in an overall better experience. However, the attacks come mainly from the same problem in the email protocols, i.e., the lack of authentication mechanism. In this work, we attempt to minimize some of the most common problems identified in email services such as spam, phishing, spoofing, lack of encryption, repudiation and centralization by implementing a smart contract over the Ethereum protocol. The proposal involves a decentralized system, a smart contract, a file system and two applications used as proof of concept.
Big data and artificial intelligence are currently two of the most important and trending pieces ... more Big data and artificial intelligence are currently two of the most important and trending pieces for innovation and predictive analytics in healthcare, leading the digital healthcare transformation. Keralty organization is already working on developing an intelligent big data analytic platform based on machine learning and data integration principles. We discuss how this platform is the new pillar for the organization to improve population health management, value-based care, and new upcoming challenges in healthcare. The benefits of using this new data platform for community and population health include better healthcare outcomes, improvement of clinical operations, reducing costs of care, and generation of accurate medical information. Several machine learning algorithms implemented by the authors can use the large standardized datasets integrated into the platform to improve the effectiveness of public health interventions, improving diagnosis, and clinical decision support. The...
Ponencia de la conferencia "17th International Conference on New Trends in Intelligent Softw... more Ponencia de la conferencia "17th International Conference on New Trends in Intelligent Software Methodology Tools and Techniques, SoMeT 2018; Granada; Spain; 26 September 2018 through 28 September 2018"
El proyecto consiste en la realización de una plataforma digital que permite la realización autom... more El proyecto consiste en la realización de una plataforma digital que permite la realización automática de actas de coordinación de asignaturas a partir de los hilos de las conversaciones establecidas en los envíos de correos electrónicos por parte de los diferentes equipos docentes participantes en dichas asignaturas. Las actas pueden generarse a partir de las conversaciones de los docentes, así como de la comunicación entre alumnos y docentes. Este trabajo se motiva en que las reuniones realizadas de forma virtual raramente van acompañadas de un acta donde se deja constancia de los participantes, de sus declaraciones, de las fechas en las que se realizaron las mismas y de las conclusiones a las que se llegaron. El principal objetivo es de dejar constancia de todos los trabajos de coordinación realizados de una forma sencilla, sin que para ello los intervinientes tengan que realizar ninguna tarea adicional, a partir de los correos enviados entre profesores alumnos de una asignatura....
El proyecto consiste en la realización de una plataforma digital que permite la realización autom... more El proyecto consiste en la realización de una plataforma digital que permite la realización automática de actas de coordinación de asignaturas a partir de los hilos de las conversaciones establecidas en los envíos de correos electrónicos por parte de los diferentes equipos docentes participantes en dichas asignaturas. Las actas pueden generarse a partir de las conversaciones de los docentes, así como de la comunicación entre alumnos y docentes. Este trabajo se motiva en que las reuniones realizadas de forma virtual raramente van acompañadas de un acta donde se deja constancia de los participantes, de sus declaraciones, de las fechas en las que se realizaron las mismas y de las conclusiones a las que se llegaron. El principal objetivo es de dejar constancia de todos los trabajos de coordinación realizados de una forma sencilla, sin que para ello los intervinientes tengan que realizar ninguna tarea adicional, a partir de los correos enviados entre profesores alumnos de una asignatura....
Abstract Social media generate a massive amount of information each day. This information is usua... more Abstract Social media generate a massive amount of information each day. This information is usually generated by people and may be used for many studies. Social media mining is a growing discipline inside data mining, and the results have proven to be quite revealing. Getting the data to work with might seem to be the easiest task in the process, but it can be very challenging for people without programming knowledge. Thus, there are numerous ways to extract information from social media, such as to use the network API, a Web scraper or specialized libraries. Using a straightforward and a cross social media query language we can hide the complexity of those mechanisms and gather information in a more efficient and easier way. This is because many social media share common elements, so we can create and unify queries to search, find and extract information from those platforms. In this paper, we propose a domain-specific query language, specially designed to allow developers or domain experts to extract data from different social media. With this language we unify and simplify the mechanisms of data extraction from social networks such as Twitter and Facebook.
Monte Carlo Tree Search is one of the main search methods studied presently. It has demonstrated ... more Monte Carlo Tree Search is one of the main search methods studied presently. It has demonstrated its efficiency in the resolution of many games such as Go or Settlers of Catan and other different problems. There are several optimizations of Monte Carlo, but most of them need heuristics or some domain language at some point, making very difficult its application to other problems. We propose a general and optimized implementation of Monte Carlo Tree Search using neural networks without extra knowledge of the problem. As an example of our proposal, we made use of the Dots and Boxes game. We tested it against other Monte Carlo system which implements specific knowledge for this problem. Our approach improves accuracy, reaching a winning rate of 81% over previous research but the generalization penalizes performance.
Social networks are an inexhaustible source of knowledge. One of its main uses is to express opin... more Social networks are an inexhaustible source of knowledge. One of its main uses is to express opinions about a particular product or service. Thus, users usually write opinions about places or so-called points of interest. That is a valuable knowledge for other users and especially for users who know and trust the opinions of the writers. In this work, we present an overview of a platform to capture opinions related to places and generate a positive or a negative recommendation for users based on both the global use of Twitter as well as the comments made by trusted people on the network.
Artificial intelligence allows computer systems to make decisions similar to those of humans. How... more Artificial intelligence allows computer systems to make decisions similar to those of humans. However, the expert knowledge that artificial intelligence systems have is rarely used to teach non-expert humans in a specific knowledge domain. In this paper, we want to explore this possibility by proposing a tool which presents and explains recommendations for playing board games generated by a Monte Carlo Tree Search algorithm combined with Neural Networks. The aim of the aforementioned tool is to showcase the information in an easily interpretable way and to effectively transfer knowledge: in this case, which movements should be avoided, and which action is recommended. Our system displays the state of the game in the form of a tree, showing all the movements available from the current state and a set of their successors. To convince and try to teach people, the tool offers a series of queries and all information available about every possible movement. In addition, it produces a brie...
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2020
Monte-Carlo methods are the basis for solving many computational problems using repeated random s... more Monte-Carlo methods are the basis for solving many computational problems using repeated random sampling in scenarios that may have a deterministic but very complex solution from a computational point of view. In recent years, researchers are using the same idea to solve many problems through the so-called Monte-Carlo Tree Search family of algorithms, which provide the possibility of storing and reusing previously calculated results to improve precision in the calculation of future outcomes. However, developers and researchers working in this area tend to have to carry out software developments from scratch to use their designs or improve designs previously created by other researchers. This makes it difficult to see improvements in current algorithms as it takes a lot of hard work. This work presents JGraphs, a toolset implemented in the Java programming language that will allow researchers to avoid having to reinvent the wheel when working with Monte-Carlo Tree Search. In addition...
Email services nowadays are flooded by spam and phishing attacks. Email service providers build t... more Email services nowadays are flooded by spam and phishing attacks. Email service providers build their own email filters to protect the final users from such attacks resulting in an overall better experience. However, the attacks come mainly from the same problem in the email protocols, i.e., the lack of authentication mechanism. In this work, we attempt to minimize some of the most common problems identified in email services such as spam, phishing, spoofing, lack of encryption, repudiation and centralization by implementing a smart contract over the Ethereum protocol. The proposal involves a decentralized system, a smart contract, a file system and two applications used as proof of concept.
Big data and artificial intelligence are currently two of the most important and trending pieces ... more Big data and artificial intelligence are currently two of the most important and trending pieces for innovation and predictive analytics in healthcare, leading the digital healthcare transformation. Keralty organization is already working on developing an intelligent big data analytic platform based on machine learning and data integration principles. We discuss how this platform is the new pillar for the organization to improve population health management, value-based care, and new upcoming challenges in healthcare. The benefits of using this new data platform for community and population health include better healthcare outcomes, improvement of clinical operations, reducing costs of care, and generation of accurate medical information. Several machine learning algorithms implemented by the authors can use the large standardized datasets integrated into the platform to improve the effectiveness of public health interventions, improving diagnosis, and clinical decision support. The...
A great number of people have Smart Objects in
their daily life: Smartphones, cars, tablets, comp... more A great number of people have Smart Objects in their daily life: Smartphones, cars, tablets, computers, Smart TVs or micro-controllers. Furthermore, these objects have Internet connection. A great number of these objects have various sensors: accelerometers, GPS, pressure, light, temperature, gravity or proximity. The essence of the concept of Internet of Things is to interconnect all these heterogeneous and ubiquitous objects among them. Some Smart Cities or Smart Homes allow a part of this concept. But this has a problem, the software that an object needs to be interconnected with the IoT platform. To create this software users need to develop the application and need developer skills. In this paper we propose a solution to this problem. We propose a graphical Domain-Specific Language for creating the necessary software for interconnecting any object with an IoT platform. For this proposal we will use the IoT Midgar platform.
Uploads
their daily life: Smartphones, cars, tablets, computers, Smart
TVs or micro-controllers. Furthermore, these objects have
Internet connection. A great number of these objects have
various sensors: accelerometers, GPS, pressure, light,
temperature, gravity or proximity. The essence of the
concept of Internet of Things is to interconnect all these
heterogeneous and ubiquitous objects among them. Some
Smart Cities or Smart Homes allow a part of this concept.
But this has a problem, the software that an object needs to
be interconnected with the IoT platform. To create this
software users need to develop the application and need
developer skills. In this paper we propose a solution to this
problem. We propose a graphical Domain-Specific
Language for creating the necessary software for
interconnecting any object with an IoT platform. For this
proposal we will use the IoT Midgar platform.