Detection of unusual human behavior in intelligent house

K. Hara1, T. Omori2, R. Ueno3
1Yokogama Electric Corporation, Musashino, Tokyo, Japan
2Graduate School of Engineering, Hokkaido University, Sapporo, Japan
3Coroporate Software Development Division, Corporate R&D Division, MEI, Matsushita Elecrric Indusrrial Company Limited, Kadoma, Osaka, Japan

Tóm tắt

This paper describes a model, based on a Markov process model, of daily human behavior in an intelligent house where human behavior is observed with small motion detectors. The number of sensor states is reduced to a few dozen by a vector quantization method, and transitions within this reduced set of states are observed. Then, the state transition probability and the transition duration time distribution are used as the templates of daily human activity. The validity of those templates is evaluated by detecting unusual human behavior in three sets of different human behavior data. Successful detection of unusual behavior without any a priori knowledge shows the effectiveness of probabilistic human behavior description in the intelligent house.

Từ khóa

#Humans #Intelligent sensors #Home appliances #Vector quantization #Infrared detectors #Motion detection #Programming #Computer industry #Research and development #Cities and towns

Tài liệu tham khảo

armitage, 1951, The statistical theory of bacterial populations subject to mutation, J R Statist Soc B, 14, 1 0 10.1109/18.133248 ashley, 1987, A linear bound for sliding-block decoder window size, IBM Research Report 10.1111/j.1467-8640.1992.tb00382.x kohonen, 1997, Self-Organizing Maps, 10.1007/978-3-642-97966-8 10.1109/MIS.1999.757623 sakamura, 1999, TRON DESIGN, Personal Med