Title :
Acoustic signal based abnormal event detection system with multiclass adaboost
Author :
Younghyun Lee ; Hanseok Ko ; Han, David K.
Author_Institution :
Korea Univ., Seoul, South Korea
Abstract :
This paper addresses the problem of abnormal acoustic event detection in indoor security systems. We propose a multiclass Adaboost based acoustic context classifier for performance and speed improvements over the conventional and prominent GMM based classifiers.
Keywords :
Gaussian processes; acoustic signal detection; indoor environment; learning (artificial intelligence); security; signal classification; GMM based classifier; acoustic context classifier; acoustic signal based abnormal event detection system; indoor security system; multiclass Adaboost; Acoustics; Classification algorithms; Context; Event detection; Security; Surveillance; Training;
Conference_Titel :
Consumer Electronics (ICCE), 2013 IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4673-1361-2
DOI :
10.1109/ICCE.2013.6486911
