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

Marcelino, Isabel; Lopes, David; Reis, Michael; Silva, Fernando; Laza, Rosalía; Pereira, António

http://hdl.handle.net/10400.8/14405

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Using the eServices Platform for Detecting Behavior Patterns_.pdf		895.06 KB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

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.

Description

This article is part of Special Issue: Distributed Artificial Intelligence Models for Knowledge Discovery in Bioinformatics
Article number - 530828

Keywords

eServices Platform CRISP-DM methodology elderly’s behavior pattern deviations

URI

http://hdl.handle.net/10400.8/14405

Citation

Marcelino, Isabel & Lopes, David & Reis, Michael & Silva, Fernando & Laza, Rosal'ia & Pereira, António. (2015). Using the eServices Platform for Detecting Behavior Patterns Deviation in the Elderly Assisted Living: A Case Study. BioMed Research International. 2015. 10.1155/2015/530828.