Eloisa Vargiu

Information Retrieval and Mining in Distributed Environments

Recommender systems are important tools that provide information items to users, by adapting to their characteristics and preferences. Usually items are recommended to individuals, but there are contexts in which people operate in groups. To support the recommendation process in social activities, group recommender systems were developed. Since different types of groups exist, group recommendation should adapt to them, managing heterogeneity of groups. This chapter will present a survey of the state-of-the-art in group recommendation, focusing on the type of group each system aims to. A new approach for group recommendation is also presented, able to adapt to technological constraints (e.g., bandwidth limitations), by automatically identifying groups of users with similar interests.

Studying the Impact of Text Summarization on Contextual Advertising

Web advertising, one of the major sources of income for a large number of Web sites, is aimed at suggesting products and services to the ever growing population of Internet users. A significant part of Web advertising consists of textual ads, the ubiquitous short text messages usually marked as sponsored links. There are two primary channels for distributing ads: Sponsored Search (or Paid Search Advertising) and Content Match (or Contextual Advertising). In this paper, we concentrate on the latter, which is devoted to display commercial ads within the content of third-party Web pages. In the literature, several approaches estimated the ad relevance based on co-occurrence of the same words or phrases within the ad and within the page. However, targeting mechanisms based solely on phrases found within the text of the page can lead to problems. In order to solve these problems, matching mechanisms that combine a semantic phase with the traditional syntactic phase have been proposed. We are mainly interested in studying the impact of the syntactic phase on contextual advertising. In particular, we perform a comparative study on text summarization in contextual advertising. Results show that implementing effective text summarization techniques may help to improve the corresponding contextual advertising system.

Improving contextual advertising by adopting collaborative filtering

Contextual advertising can be viewed as an information filtering task aimed at selecting suitable ads to be suggested to the final “user”, that is, the Web page in hand. Starting from this insight, in this article we propose a novel system, which adopts a collaborative filtering approach to perform contextual advertising. In particular, given a Web page, the system relies on collaborative filtering to classify the page content and to suggest suitable ads accordingly. Useful information is extracted from “inlinks”, that is, similar pages that link to the Web page in hand. In so doing, collaborative filtering is used in a content-based setting, giving rise to a hybrid contextual advertising system. After being implemented, the system has been experimented with about 15000 Web pages extracted from the Open Directory Project. Comparative experiments with a content-based system have been performed. The corresponding results highlight that the proposed system performs better. A suitable case study is also provided to enable the reader to better understand how the system works and its effectiveness.

Literature Retrieval and Mining in Bioinformatics: State of the Art and Challenges

The world has widely changed in terms of communicating, acquiring, and storing information. Hundreds of millions of people are involved in information retrieval tasks on a daily basis, in particular while using a Web search engine or searching their e-mail, making such field the dominant form of information access, overtaking traditional database-style searching. How to handle this huge amount of information has now become a challenging issue. In this paper, after recalling the main topics concerning information retrieval, we present a survey on the main works on literature retrieval and mining in bioinformatics. While claiming that information retrieval approaches are useful in bioinformatics tasks, we discuss some challenges aimed at showing the effectiveness of these approaches applied therein.

Context-Aware Based Quality of Life Telemonitoring

Telemonitoring Quality of Life of individuals is the base for current and future telemedicine and teleassistance solutions which will become paramount in the sustainability and effectiveness of healthcare systems. In the framework of the BackHome European R&D project, which aims to provide a telemonitoring and home support system using Brain Computer Interfaces and other assistive technologies to improve autonomy and quality of life of disabled people, we propose a methodology to assess and telemonitor quality of life of individuals based on the awareness of user context. This methodology holds a generic approach to be applied to other eHealth use cases and is based on the acquisition, fusion and processing of heterogeneous data coming from sensors, devices, and user interaction, and the knowledge inferred from the correlation of this processed data and the input coming from our proposed questionnaires mapped to standard taxonomies. The proposed methodology is very ambitious and although we are presenting preliminary validation, it will have to be formally validated and enhanced with the study of representative user data which will be acquired within BackHome and other related projects.

A recommender system based on a generic contextual advertising approach

Contextual advertising and automatic recommendation are emerging fields deeply studied by researchers in information retrieval. So far, these fields have been separately investigated and several solutions have been independently proposed in the literature. Nevertheless, in our view, there are common issues that drive us to think that systems devised to solve one of the task above could be simply re-adapted to solve the other. In this paper, we propose a novel recommendation system based on a generic solution typically adopted to solve contextual advertising tasks. Experimental results highlight the effectiveness of the proposed approach.

A P300 BCI for e - inclusion, cognitive rehabilitation and smart home control

We implemented an easy-to-use P300 BCI system that allows users to control a variety of applications for communication, creative expression, training of cognitive abilities and environmental control. In this paper we present an evaluation of the following four applications: a speller, two games that can be used for cognitive rehabilitation or entertainment, twitter (via web browser) and a webcam. All fourteen healthy participants had control over the BCI and reached high accuracies (>85%). The results of the evaluation informed the development of the next prototype. With a user-centered approach we aim to further improve the prototype and ultimately provide end users with a multifunctional system that can be used as assistive technology in a home environment.

Improving Activity Monitoring Through a Hierarchical Approach.

Performance of sensor-based telemonitoring and home support systems depends, among other characteristics, on the reliability of the adopted sensors. Although binary sensors are quite used in the literature and also in commercial solutions to identify user’s activities, they are prone to noise and errors. In this paper, we present a hierarchical approach, based on machine learning techniques, aimed at reducing error from the sensors. The proposed approach is aimed at improving the classification accuracy in detecting if a user is at home, away, alone or with some visits. It has been integrated in a sensor-based telemonitoring and home support system. Results show an overall improvement of 15% in accuracy with respect to a rule-based approach. The system is part of the BackHome project and is currently running in 2-healthy-users’ home in Barcelona and in 3-end-users’ home in Belfast.

An Agent Architecture for Planning in a Dynamic Environment

This paper briefly describes a scalable architecture for implementing autonomous agents that act in a virtual world created for a computer game and must interact with it by suitably planning and executing actions in a dynamic and not-completely accessible environment. In particular, we are experimenting a two-pass vertically layered architecture that allows supporting an agent behavior through a clean hierarchical organization.

A Multifunctional Brain-Computer Interface Intended for Home Use: An Evaluation with Healthy Participants and Potential End Users with Dry and Gel-Based Electrodes

Current brain-computer interface (BCIs) software is often tailored to the needs of scientists and technicians and therefore complex to allow for versatile use. To facilitate home use of BCIs a multifunctional P300 BCI with a graphical user interface intended for non-expert set-up and control was designed and implemented. The system includes applications for spelling, web access, entertainment, artistic expression and environmental control. In addition to new software, it also includes new hardware for the recording of electroencephalogram (EEG) signals. The EEG system consists of a small and wireless amplifier attached to a cap that can be equipped with gel-based or dry contact electrodes. The system was systematically evaluated with a healthy sample, and targeted end users of BCI technology, i.e., people with a varying degree of motor impairment tested the BCI in a series of individual case studies. Usability was assessed in terms of effectiveness, efficiency and satisfaction. Feedback of users was gathered with structured questionnaires. Two groups of healthy participants completed an experimental protocol with the gel-based and the dry contact electrodes (N = 10 each). The results demonstrated that all healthy participants gained control over the system and achieved satisfactory to high accuracies with both gel-based and dry electrodes (average error rates of 6 and 13%). Average satisfaction ratings were high, but certain aspects of the system such as the wearing comfort of the dry electrodes and design of the cap, and speed (in both groups) were criticized by some participants. Six potential end users tested the system during supervised sessions. The achieved accuracies varied greatly from no control to high control with accuracies comparable to that of healthy volunteers. Satisfaction ratings of the two end-users that gained control of the system were lower as compared to healthy participants. The advantages and disadvantages of the BCI and its applications are discussed and suggestions are presented for improvements to pave the way for user friendly BCIs intended to be used as assistive technology by persons with severe paralysis.