Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by CRACS

2008

Revising first-order logic theories from examples through stochastic local search

Authors
Paes, A; Zaverucha, G; Costa, VS;

Publication
INDUCTIVE LOGIC PROGRAMMING

Abstract
First-Order Theory Revision from Examples is the process of improving user-defined or automatically generated First-Order Logic (FOL) theories, given a set of examples. So far, the usefulness of Theory Revision systems has been limited by the cost of searching the huge search spaces they generate. This is a general difficulty when learning FOL theories but recent work showed that Stochastic Local Search (SLS) techniques may be effective, at least when learning FOL theories from scratch. Motivated by these results, we propose novel SLS based search strategies for First-Order Theory Revision from Examples. Experimental results show that introducing stochastic search significantly speeds up the runtime performance and improve accuracy.

2008

RUSE-WARMR: Rule Selection for Classifier Induction in Multi-Relational Data-Sets

Authors
Ferreira, CA; Gama, J; Costa, VS;

Publication
20TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, VOL 1, PROCEEDINGS

Abstract
One of the major challenges in knowledge discovery is how to extract meaningful and useful knowledge from the complex structured data that one finds in Scientific and Technological applications. One approach is to explore the logic relations in the database and using, say, an Inductive Logic Programming (ILP) algorithm find descriptive and expressive patterns. These patterns can then be used as features to characterize the target concept, The effectiveness of these algorithms depends both upon the algorithm we use to generate the patterns and upon the classifier Rule mining provides an excellent framework for efficiently mining the interesting patterns that are relevant. We propose a novel method to select discriminative patterns and evaluate the effectiveness of this method on a complex discovery application of practical interest.

2008

RL-based Scheduling Strategies in Actual Grid Environments

Authors
Costa, B; Dutra, I; Mattoso, M;

Publication
PROCEEDINGS OF THE 2008 INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS

Abstract
In this work, we study the behaviour of different resource scheduling strategies when doing job orchestration in grid environments. We empirically demonstrate that scheduling strategies based on Reinforcement Learning are a good choice to improve the overall performance of grid applications and resource utilization.

2008

Personal Autonomic Desktop Manager with a circulatory computing approach

Authors
Kopiler, AA; Dutra, ID; Franca, FMG;

Publication
PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL WORKSHOP ON ENGINEERING OF AUTONOMIC & AUTONOMOUS SYSTEMS (EASE 2008)

Abstract
In this paper we present the architecture for the Personal Autonomic Desktop Manager, a self managing application designed to act on behalf of the user in several aspects: protection, healing, optimization and configuration. The overall goal of this research is to improve the correlation of the autonomic self* properties and doing so also enhance the overall self-management capacity of the desktop (autonomicity). We introduce the Circulatory Computing (CC) model, a self-managing system initiative based on the biological metaphor of the cardiovascular system, and use its concepts in the design and implementation of the architecture.

2008

ACCESS AND PRIVACY RIGHTS USING WEB SECURITY STANDARDS TO INCREASE PATIENT EMPOWERMENT

Authors
Falcao Reis, F; Costa Pereira, A; Correia, ME;

Publication
MEDICAL AND CARE COMPUNETICS 5

Abstract
Electronic Health Record (EHR) systems are becoming more and more sophisticated and include nowadays numerous applications, which are not only accessed by medical professionals, but also by accounting and administrative personnel. This could represent a problem concerning basic rights such as privacy and confidentiality. The principles, guidelines and recommendations compiled by the OECD protection of privacy and trans-border flow of personal data are described and considered within health information system development. Granting access to an Elf R should be dependent upon the owner of the record; the patient: he must be entitled to define who is allowed to access his EHRs, besides the access control scheme each health organization may have implemented. In this way, it's not only up to health professionals to decide who have access to what, but the patient himself Implementing such a policy is walking towards patient empowerment which society should encourage and governments should promote. The paper then introduces a technical solution based on web security standards. This would give patients the ability to monitor and control which entities have access to their personal EHRs, thus empowering them with the knowledge of how much of his medical history is known and by whom. It is necessary to create standard data access protocols, mechanisms and policies to protect the privacy rights and furthermore, to enable patients, to automatically track the movement (flow) of their personal data and information in the context of health information systems. This solution must be functional and, above all, user-friendly and the interface should take in consideration some heuristics of usability in order to provide the user with the best tools. The current official standards on confidentiality and privacy in health care, currently being developed within the EU, are explained, in order to achieve a consensual idea of the guidelines that all member states should follow to transfer such principles into national laws. A perspective is given on the state of the art concerning web security standards, which can be used to easily engineer health information systems complying with the patient empowering goals. In conclusion health systems with the characteristics thus described are technically feasible and should be generally implemented and deployed.

2008

SECURING A HEALTH INFORMATION SYSTEM WITH A GOVERNMENT ISSUED DIGITAL IDENTIFICATION CARD

Authors
Santos, R; Correia, ME; Antunes, L;

Publication
42ND ANNUAL 2008 IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY, PROCEEDINGS

Abstract
Health Information Systems (HIS) are often deployed with inadequate security mechanisms and with users being generally pointed out as the weakest link. The launch of the Portuguese digital national identification smart card, the Citizen Card (CC), with strong authentication and digital signing capabilities, represents a new and viable economic opportunity for securing a HIS and at the same time foster the creation of a much more secure national health information infrastructure. Smart cards are being deployed in healthcare in several places around the world with highly encouraging results. Major programs have already been deployed with great success, although there are some well identified issues that need to be addressed. The CC is a versatile and secure card, with the latest in encryption and tamper resistance technologies, with standard support for a Public Key Infrastructure (PKI). We present the advantages and enumerate some of the problems of using a smart card in a HIS, as well as the CC possible contributions in this area, namely as an easy, inexpensive, widely deployed way of using current technology to protect HIS security, and ultimately patient information, while at the same time fostering the expansion and deployment of inter operable HIS. Issues are identified that will need to be resolved and a detailed plan for further work to assess the level of impact the CC can have on the national HIS is indicated.

  • 161
  • 192