Human Activity Recognition in Intelligent Home Environments: An Evolving Approach

In this paper, we propose an automated approach to track and recognize daily activities. Any activity is represented in this research as a sequence of raw sensors data. These sequences are treated using statistical methods in order to discover activity patterns. However, as the way to perform an activity is usually not fixed but it changes and evolves, we propose an activity recognition method based on Evolving Systems.

• Type: Conference
• Year: 2010
• Where: ECAI
• Authors: José Antonio Iglesias, Plamen P. Angelov, Agapito Ledezma, Araceli Sanchís
• Keywords: Activity Patterns, Activity Recognition Method, Artificial Intelligence, ECAI 2010, Raw Sensors Data