Table of Contents Author Guidelines Submit a Manuscript
BioMed Research International
Volume 2015, Article ID 530828, 10 pages
http://dx.doi.org/10.1155/2015/530828
Research Article

Using the eServices Platform for Detecting Behavior Patterns Deviation in the Elderly Assisted Living: A Case Study

1Higher Technical School of Computer Engineering, University of Vigo, Polytechnic Building, Campus Universitario As Lagoas s/n, 32004 Ourense, Spain
2INOV INESC Innovation, Institute of New Technologies of Leiria, 2411-901 Leiria, Portugal
3School of Technology and Management, Computer Science and Communications Research Centre, Polytechnic Institute of Leiria, 2411-901 Leiria, Portugal

Received 20 August 2014; Revised 11 October 2014; Accepted 29 October 2014

Academic Editor: Juan F. De Paz

Copyright © 2015 Isabel Marcelino et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

World’s aging population is rising and the elderly are increasingly isolated socially and geographically. As a consequence, in many situations, they need assistance that is not granted in time. In this paper, we present a solution that follows the CRISP-DM methodology to detect the elderly’s behavior pattern deviations that may indicate possible risk situations. To obtain these patterns, many variables are aggregated to ensure the alert system reliability and minimize eventual false positive alert situations. These variables comprehend information provided by body area network (BAN), by environment sensors, and also by the elderly’s interaction in a service provider platform, called eServices—Elderly Support Service Platform. eServices is a scalable platform aggregating a service ecosystem developed specially for elderly people. This pattern recognition will further activate the adequate response. With the system evolution, it will learn to predict potential danger situations for a specified user, acting preventively and ensuring the elderly’s safety and well-being. As the eServices platform is still in development, synthetic data, based on real data sample and empiric knowledge, is being used to populate the initial dataset. The presented work is a proof of concept of knowledge extraction using the eServices platform information. Regardless of not using real data, this work proves to be an asset, achieving a good performance in preventing alert situations.