Title :
Detection of unusual human behavior in intelligent house
Author :
Hara, Kosuke ; Omori, Takashi ; Ueno, Reiko
Author_Institution :
Yokogawa Electr. Corp., Musashino, Japan
Abstract :
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.
Keywords :
Markov processes; building management systems; home automation; human factors; pattern classification; vector quantisation; Markov process; daily human activity; intelligent house; motion detectors; pattern classification; sensor states; unusual human behavior detection; vector quantization; Cities and towns; Computer industry; Home appliances; Humans; Infrared detectors; Intelligent sensors; Motion detection; Programming; Research and development; Vector quantization;
Conference_Titel :
Neural Networks for Signal Processing, 2002. Proceedings of the 2002 12th IEEE Workshop on
Print_ISBN :
0-7803-7616-1
DOI :
10.1109/NNSP.2002.1030081