Automatic human life summarization system in sensory living space

Author

Mori, Taketoshi ; Takada, Aritoki ; Iwamura, Y. ; Sato, Tomomasa

Author_Institution

Dept. of Mechano-Informatics, Tokyo Univ., Japan

Volume

2

fYear

2004

fDate

10-13 Oct. 2004

Firstpage

1583

Abstract

This paper proposes a human life summarization system for understanding and describing daily life in a short time. The system consists of two processes. One is a human life clustering process, in which time-series data of human life are divided into some behavior-based clusters. The other is a display process, in which the time-series segments are displayed instantly recognizable along with the time. The experimental results show that the system can divide human life record into apprehensible segments on time series. The paper also described a prototype of the summarization system and proved that people can comprehend overview of the life with it.

Keywords

behavioural sciences computing; hidden Markov models; intelligent sensors; pattern clustering; time series; automatic human life summarization system; hidden Markov model; human life clustering process; sensory living space; sequential data clustering; time-series data; Anthropometry; Cameras; Computer displays; Extraterrestrial measurements; Floors; Hidden Markov models; Humans; Refrigeration; Sensor systems; TV;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2004 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-8566-7

Type

conf

DOI

10.1109/ICSMC.2004.1399857

Filename

1399857