Navegación

Búsqueda

Búsqueda avanzada

El autor Sergio Ilarri ha publicado 9 artículo(s):

1 - A First Step Towards Keyword-Based Searching for Recommendation Systems

Due to the high availability of data, users are frequently overloaded with a huge amount of alternatives when they need to choose a particular item. This has motivated an increased interest in research on recommendation systems, which filter the options and provide users with suggestions about specific elements (e.g., movies, restaurants, hotels, news, etc.) that are estimated to be potentially relevant for the user. Recommendation systems are still an active area of research, and particularly in the last years the concept of context-aware recommendation systems has started to be popular, due to the interest of considering the context of the user in the recommendation process. In this paper, we describe our work-in-progress concerning pull-based recommendations (i.e., recommendations about certain types of items that are explicitly requested by the user). In particular, we focus on the problem of detecting the type of item the user is interested in. Due to its popularity, we consider a keyword-based user interface: the user types a few keywords and the system must determine what the user is searching for. Whereas there is extensive work in the field of keyword-based search, which is still a very active research area, keyword searching has not been applied so far in most recommendation contexts.

Autores: María del Carmen Rodríguez-Hernández / Francesco Guerra / Sergio Ilarri / Raquel Trillo / 
Palabras Clave: keyword-based search - mobile computing - recommendation systems

2 - Simulating Mobile Agents in Vehicular Networks

In the next years, vehicular ad hoc networks (VANETs) are expected to become a reality and a great number of interesting applications for drivers and passengers will be developed (related to safety, comfort, and entertainment). In all these applications, the acquisition, management and an efficient and effective exchange of data will be key issues. Therefore, significant data management challenges arise in this context. We argue that mobile agent technology could play an important role as a middleware for the development of applications for vehicular networks, as they naturally support disconnected operations and distributed data management. Overall, a development of solutions based on agents that autonomously take decisions may be promising. A significant problem arises when we need to evaluate a data management approach for vehicular networks. Deploying it in the real-world in order to evaluate the proposal with real cars is impractical and very expensive, and so field tests are limited to very small-scale and controlled scenarios, mainly as a proof of concept. Instead, simulators are usually used for experimental evaluation. However, existing simulators for vehicular networks do not directly support testing data management techniques based on the use of mobile agents. In this paper, we present a simulator that offers interesting functionalities for that context. The simulator has been developed in a quite generic and extensible way, in order to facilitate its use in a variety of scenarios to test different data management approaches.

Autores: Oscar Urra / Sergio Ilarri / Eduardo López / 
Palabras Clave: mobile ad-hoc networks - mobile agents - mobile computing - simulations - vehicular networks

3 - Context-Aware Recommendations in Mobile Environments

Traditional recommendation systems offer relevant items (e.g., books, movies, music, etc.) to users, but they are not designed for mobile environments. In those environments, the context (e.g., the location, the time, the weather, the presence of other people, etc.) and the movements of the users may be important factors to obtain relevant and helpful recommendations. The emergence of context-aware recommendation systems has prompted the growth of recommendation algorithms that incorporate context information. However, most existing research in this field considers only static context information, despite the fact that exploiting dynamic context information would be very helpful in mobile computing scenarios. Moreover, the design and implementation of generic frameworks to support an easy development of context-aware recommendation systems has been relatively unexplored. In this paper, we present our ongoing work to develop a context-aware recommendation framework for distributed and mobile environments, which will allow suggesting relevant items to mobile users.

Autores: María del Carmen Rodríguez-Hernández / Sergio Ilarri / 
Palabras Clave: context-awareness - mobile computing - recommendation systems

4 - NASS: A Semantic Annotation Tool for Media

Nowadays media companies have serious difficulties for managing large amounts of news from agencies and self-made articles. Journalists and documentalists must face categorization tasks every day. There is also an additional difficulty due to the usual large size of the list of words in a thesaurus, which is the typical tool used to tag news in the media. In this paper, we present a new method to tackle the problem of information extraction over a set of texts where the annotation must be composed by thesaurus elements. The method consists of applying lemmatization, obtaining keywords, and finally using a combination of Support Vector Machines (SVM), ontologies and heuristics to deduce appropriate tags for the annotation. We carried out a detailed evaluation of our method with a real set of changing news and we compared out tagging with the annotation performed by a real documentation department, obtaining really promising results.

Autores: Angel L. Garrido / Oscar Gómez / Sergio Ilarri / Eduardo Mena / 
Palabras Clave: Semantic tagging and classification; Information Extraction; NLP; SVM; Ontologies; Text classification; Media; News

5 - Definiendo un Caso de Estudio para Recomendaciones Dinámicas Móviles

Los denominados sistemas de recomendación permiten aliviar la sobrecarga de información de los usuarios, al ofrecer sugerencias específicas acerca de ítems concretos (películas, libros, actividades, puntos de interés, etc.) que pueden resultar de interés para el usuario. En los últimos años se está realizando una intensa investigación en el desarrollo de sistemas de recomendación sensibles al contexto, ya que tener en cuenta el contexto del usuario (posición geográfica, tiempo atmosférico, estado de ánimo, etc.) permite ofrecer recomendaciones más apropiadas. En entornos de computación móvil uno de los elementos clave del contexto del usuario es su localización, siendo relevante ofrecer sugerencias al usuario de forma proactiva (sin peticiones expresas por parte del usuario) y teniendo en cuenta su trayectoria. En este artículo, describimos nuestro trabajo en progreso relacionado con las recomendaciones dinámicas sensibles al contexto en entornos móviles. Debido a la dificultad de evaluación de estos sistemas de recomendación en el mundo real, nos centramos en el desarrollo de un caso de estudio que simulará un escenario para recomendaciones dinámicas para los visitantes de un museo.

Autores: María Del Carmen Rodríguez-Hernández / Sergio Ilarri / Ramon Hermoso / Raquel Trillo-Lado / 
Palabras Clave: computación móvil - Contexto - recomendaciones dinámicas

6 - An approach driven by mobile agents for data management in vehicular networks

In the last years, and thanks to improvements on computing and communications technologies, wireless networks formed by vehicles (called vehicular networks) have emerged as a key topic of interest. In these networks, the vehicles can exchange data by using short-range radio signals in order to get useful information related to traffic conditions, road safety, and other aspects. The availability of different types of sensors can be exploited by the vehicles to measure many parameters from their surroundings. These data can then be shared with other drivers who, on the other side, could also explicitly submit queries to retrieve information available in the network. This can be a challenging task, since the data is scattered among the vehicles belonging to the network and the communication links among them have usually a short life due to their constant movement. In this paper, we use mobile agent technology to help to accomplish these tasks, since mobile agents have a number of features that are very well suited for mobile environments, such as autonomy, mobility, and intelligence. Specifically, we analyze the benefits that mobile agents can bring to vehicular networks and the potential difficulties for their adoption. Moreover, we describe a query processing approach based on the use of mobile agents. We focus on range queries that retrieve interesting information from the vehicles located within a geographic area, and perform an extensive experimental evaluation that shows the feasibility and the interest of the proposal.

Autores: Oscar Urra / Sergio Ilarri / Raquel Trillo-Lado / 
Palabras Clave: data management - mobile agents - query processing - vehicular ad hoc networks

7 - (Trabajo relevante) Handling location uncertainty in probabilistic location-dependent queries

Este artículo se presenta a JISBD como trabajo relevante y ha sido publicado en la revista Information Sciences en el año 2017.Los datos del artículo son: – Autores: Jorge Bernad, Carlos Bobed, Sergio Ilarri, Eduardo Mena – Título: Handling location uncertainty in probabilistic location-dependent queries – Revista: Information Sciences – Volumen: 388-389 – Páginas: 154-171 – Año: 2017 – DOI: http://dx.doi.org/10.1016/j.ins.2017.01.029Indicios de calidad: la revista tiene un JCR en el año 2016 de 4.832. Dentro la categoría «Computer Science, Information Systems» está situada dentro 5% de las mejores revistas (7/146), y pertenece al cuartil Q1.

Autores: Jorge Bernad / Carlos Bobed / Sergio Ilarri / Eduardo Mena / 
Palabras Clave: Location-dependent queries - Probabilistic range queries - Uncertainty management

8 - DataGenCARS: A generator of synthetic data for the evaluation of context-aware recommendation systems

Este artículo se presenta a JISBD como trabajo relevante y ha sido publicado en la revista Pervasive and Mobile Computing en el año 2017.María del Carmen Rodríguez-Hernández, Sergio Ilarri, Ramón Hermoso, Raquel Trillo-Lado, «DataGenCARS: A Generator of Synthetic Data for the Evaluation of Context-Aware Recommendation Systems», Pervasive and Mobile Computing, ISSN 1574-1192, volume 38, part 2, pp. 516-541, Elsevier, July 2017. Special Issue on Context-aware Mobile Recommender Systems.DOI: 10.1016/j.pmcj.2016.09.020.JCR 2016 (última edición del JCR publicada): factor de impacto: 2,349; 53/146 en Computer Science, Information Systems (Q2, T2); 34/89 en Telecommunications (Q2, T2). Revista en el top 36,3% (considerando la mejor categoría del JCR).

Autores: María Del Carmen Rodríguez Hernández / Sergio Ilarri / Ramon Hermoso / Raquel Trillo-Lado / 
Palabras Clave: Context-aware recommendation systems - Dataset generation - Evaluation - Mobile recommendations

9 - Proyecto TRAFAIR: Generación y publicación de datos de calidad del aire en las ciudades de Zaragoza y Santiago de Compostela

En este artículo se describen brevemente los trabajos en marcha relacionados con la generación y publicación de datos acerca de la calidad del aire en el ámbito del proyecto Europeo TRAFAIR. En concreto, se describe la solución adoptada para la adquisición de datos de sensores, los estándares utilizados para la publicación de datos en abierto y las aplicaciones de usuario final que serán desarrolladas, concluyendo el artículo con la identificación de retos técnicos relacionados con la heterogeneidad de los datos y con la generalización de soluciones basada en la asunción de modelos de datos estandarizados.

Autores: José R.R. Viqueira / Raquel Trillo-Lado / Sebastián Villarroya / Lorena Marrodán / José M. Cotos / Sergio Ilarri / José A. Taboada / Enrique Torres-Moreno / 
Palabras Clave: calidad del aire - datos abiertos - datos de sensores - Datos geoespaciales - Modelado ambiental