A method to monitor and detect unusual or atypical behaviors compared to previous stored data is presented, as part of a system to automatically monitor the behaviors of people living alone. The system uses a discrete event oriented framework, where data from cameras and other sensors is automatically analyzed to get information about the status of the person (defined by his location inside the house, his position, and the intensity of movement), information about the room status, (the number of persons in the room, the status of windows, doors, lights and other appliances, the room temperature and humidity, etc.) and information about external status (external humidity, external temperature). Every two seconds all the information is mapped to discrete set variables that take a reduced number of values, and stored in a system state database . An agent based approach is used to define agents that use the information from this data base, and build models to characterize the person typical behavior. Monitor agents that use this characterization to detect atypical behaviors when the system state is updated, are also defined. The approach is demonstrated with a simple prototype to monitor the time spent in each of the rooms of a small apartment.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com