Showing papers by "Yolanda Blanco-Fernández published in 2008"

A flexible semantic inference methodology to reason about user preferences in knowledge-based recommender systems

Abstract: Recommender systems arose with the goal of helping users search in overloaded information domains (like e-commerce, e-learning or Digital TV). These tools automatically select items (commercial products, educational courses, TV programs, etc.) that may be appealing to each user taking into account his/her personal preferences. The personalization strategies used to compare these preferences with the available items suffer from well-known deficiencies that reduce the quality of the recommendations. Most of the limitations arise from using syntactic matching techniques because they miss a lot of useful knowledge during the recommendation process. In this paper, we propose a personalization strategy that overcomes these drawbacks by applying inference techniques borrowed from the Semantic Web. Our approach reasons about the semantics of items and user preferences to discover complex associations between them. These semantic associations provide additional knowledge about the user preferences, and permit the recommender system to compare them with the available items in a more effective way. The proposed strategy is flexible enough to be applied in many recommender systems, regardless of their application domain. Here, we illustrate its use in AVATAR, a tool that selects appealing audiovisual programs from among the myriad available in Digital TV.

Provision of distance learning services over Interactive Digital TV with MHP

Abstract: E-learning technologies have developed greatly in recent years, with considerable success. However, there is increasing evidence that web-based learning is not reaching the social sectors which are more reluctant to contact with the new technologies, thus leading to inequalities in the access to education and knowledge in the Information Society. By hiding the intricacies of computers behind the familiarity of household equipment, Interactive Digital TV (IDTV) is considered to play a key role in addressing this problem, and the term t-learning has been recently coined to mean TV-based interactive learning. Despite several approaches to t-learning have been proposed, works are missing that conceive it as a whole, delimit its scope in comparison with web-based learning and analyze the influence of the normalization of IDTV as a services platform. This paper addresses these issues, and introduces a framework for the development and deployment of t-learning services that promotes interoperability and reuse while taking into account the characteristic features of the IDTV medium.

Monitoring medicine intake in the networked home: The iCabiNET solution

Abstract: We introduce an intelligent medicine cabinet as a new element of a residential network, acting as a secure place to store sensitive health information, and therefrom access a range of interactive health care applications. This paper describes the functionalities related to monitoring the intake of prescription and over-the-counter drugs, harnessing recent advances in smart medicine packaging and home networking. Compared to previous systems, ours helps reducing the risk of medicine misuse, featuring higher precision and enhanced interactive facilities that reach in and out of home. This contributes to solving a problem that impinges heavily on the well-being of people and the economics of public health systems.

Semantic reasoning: a path to new possibilities of personalization

Abstract: Recommender systems face up to current information overload by selecting automatically items that match the personal preferences of each user. The so-called content-based recommenders suggest items similar to those the user liked in the past, by resorting to syntactic matching mechanisms. The rigid nature of such mechanisms leads to recommend only items that bear a strong resemblance to those the user already knows. In this paper, we propose a novel content-based strategy that diversifies the offered recommendations by employing reasoning mechanisms borrowed from the SemanticWeb. These mechanisms discover extra knowledge about the user's preferences, thus favoring more accurate and flexible personalization processes. Our approach is generic enough to be used in a wide variety of personalization applications and services, in diverse domains and recommender systems. The proposed reasoning-based strategy has been empirically evaluated with a set of real users. The obtained results evidence computational feasibility and significant increases in recommendation accuracy w.r.t. existing approaches where our reasoning capabilities are disregarded.

An MHP framework to provide intelligent personalized recommendations about digital TV contents

Abstract: Digital Television will bring a significant increase in the amount of channels and programs available to end users, with many more difficulties to find contents appealing to them among a myriad of irrelevant information. Thus, automatic content recommenders should receive special attention in the following years to improve their assistance to users. The current content recommenders have important deficiencies that hamper their wide acceptance. In this paper, we present a new approach for automatic content recommendation that significantly reduces those deficiencies. This approach, based on Semantic Web technologies, has been implemented in the AdVAnced Telematic search of Audiovisual contents by semantic Reasoning tool, a hybrid content recommender that makes extensive use of well-known standards, such as Multimedia Home Platform, TV-Anytime and OWL. Also, we have carried out an experimental evaluation, the results of which show that our proposal performs better than other existing approaches. Copyright © 2007 John Wiley & Sons, Ltd.

Qualitative assessment of approaches to coordinate activities of mobile hosts in ad hoc networks

Abstract: This article deals with the validation of approaches to coordinating activities in mobile ad hoc networks. Previous studies relied on simulations that paid little attention to how well these networks perform the tasks for which they can be deployed. Indeed, many authors employed random mobility models, although the hosts rarely move at random in real applications. Here, we assess the main ideas in the coordination literature in the context of extinguishing forest fires, with movements driven by application-level concerns and an eye on overall performance. The results reveal strengths and weaknesses of the most recent trend in coordination, knowledge exploitation.

A SMART MEDICINE MANAGER DELIVERING HEALTH CARE TO THE NETWORKED HOME AND BEYOND - An Overview of the iCabiNET System

Abstract: Misuse of prescription and over-the-counter drugs is a growing problem that impinges heavily on the wellbeing of people and the economics of public health systems. Most commonly, misuses arise from forgetfulness or lack of information about drugs and their interactions, hence there is much place for solutions to automatically monitor medicine intake, issue reminders and deliver medical advice. This paper presents a system that accomplishes these tasks by harnessing recent advances in smart medicine packaging, residential networks and semantic reasoning. Such a combination yields a medicine manager featuring great precision in drug monitoring, plus unprecedented capabilities to reach the users and provide them with valuable information.

Personalizing e-Commerce by Semantics-Enhanced Strategies and Time-Aware Recommendations

Abstract: Current e-commerce recommender systems adapt the selection of commercial items suggested to the users as their preferences evolve over time. However, this adaptation process misses the time elapsed since the user has bought an item, which is an essential parameter that affects differently to each purchased product. This results in some useless recommendations, including regularly items that the users are only willing to buy sporadically. In this paper, we explore a new recommendation strategy that offers time-aware suggestions to e-commerce users, by enhancing reasoning techniques from the Semantic Web with item-dependent time functions. This combination leads to suggestions adapted to the particular needs of each user at any given moment.

ZapTV: Personalized User-Generated Content for Handheld Devices in DVB-H Mobile Networks

Abstract: During the last years, we had witnessed the boom of the digital market due to proliferation of emergent audiovisual services and increasing number of broadband networks. In this scenario, users insistently demand for innovative services for exchanging and sharing their own audiovisual contents and productions. In order to meet these needs, in this paper we propose the ZapTV system. Broadly speaking, this tool broadcasts user-generated audiovisual contents for handheld devices in a mobile network based on the DVB-H broadcasting standard. ZapTV offers diverse added-value services to these new active users, such as: (i) multi modal access (via Web and by handheld devices) to digital contents anywhere and anytime, (ii) availability of a return channel to transmit interactive contents that enhance the user's viewing experience, and (iii) annotation, sharing and personalized distribution of audiovisual contents. To achieve these goals, our system adopts both well-known technologies for broadcasting and semantic annotation of audiovisual contents (such as DVB-H and TV-Anytime), and emergent technology from the so-called Web 2.0, which permit the users to actively cooperate in tasks of generation, annotation and classification of digital contents.

On the Need for Incentives to Support Personalization Systems - Turning Users into Active Providers of Contents and Metadata.

Abstract: A furnace air filter includes a structure which has two identical rectangularly shaped grid members. The grid members are joined together at one side by a hinge, which hinge is made of the same plastic material as the grid members. The grid members and hinge are integrally formed preferably by an injection molding process. A filter media is placed between the grid members so as to form a filter unit adapted to be positioned in the filter track of a furnace air duct. The plastic grid structure is reusable, requiring the replacement of only the filter media.

MiSPOT: Enhanced Availability and Quality in Delivering Personalized M-Learning Linked to TV Programs

Abstract: The development of digital television for mobile devices brings in new possibilities for informal learning, by means of interactive educational services linked to the TV programs. Some systems exist in the m-learning literature that may automatically discover the most valuable services for each viewer at any time, matching information about his/her interests, context and needs, about the services available and about the TV programs that those services may be linked to. Most commonly, however, the reasoning process is performed by remote servers, which implies that the personalization features become unavailable in the frequent cases of sporadic or null access to a bidirectional communication channel. The alternative exists to do local reasoning in the mobile devices, but their limited computational power results in low personalization quality. In this paper, we solve these problems with a scalable approach to perform semantic reasoning in mobile devices, backed up by the bandwidth and robustness of the same broadcast networks that deliver the TV programs.