Title: EVENT SEQUENCE RECOGNITION AND MULTIAGENT BASED TASK ISOLATION OF HUMAN ACTIVITIES

Year of Publication: Jun - 2012
Page Numbers: 1-7
Authors: M. R. Alam, M. B. I. Reaz
Conference Name: The International Conference on Informatics and Applications (ICIA2012)
- Malaysia

Abstract:


People follow some specific patterns in their life style and recognition of human activity is thus a potential problem to develop an effective smart home. At the same time, inhabitant activity classification plays a vital role to predict smart home events. The paper proposed a novel algorithm to recognize activities of daily living of the resident by considering opposite entity states to extract the pattern of event sequence. Each extracted episodes represents a distinct task of the home user. The paper also proposed a multiagent system to track the user for task isolation. The system is composed of cooperative agents which works by sharing local views of individual agents. The developed algorithm clusters the smart home events by isolating opposite status of home appliance. Result shows that, the algorithm can successfully identify 135 unique tasks of different lengths.