Premium
A calculation method of generation probability of indoor activity sound in daily life
Author(s) -
Tanaka Motoshi
Publication year - 2019
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.23016
Subject(s) - sound (geography) , mel frequency cepstrum , cluster analysis , abnormality , feature (linguistics) , cepstrum , computer science , speech recognition , acoustics , artificial intelligence , feature extraction , psychology , physics , social psychology , linguistics , philosophy
To develop a detection system of abnormality (such as accidents) in daily life for persons living alone, a stochastic modeling of indoor daily activity sound is investigated with clustering spectral flux and Mel‐Frequency Cepstrum Coefficients extracted from the sound for 12 h as feature vectors. Then, the generation probability of the sound is calculated. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.