Audio-based Event Recognition System for Smart Homes

Date

2017

Advisors

Journal Title

Journal ISSN

ISSN

DOI

Volume Title

Publisher

IEEE

Type

Conference

Peer reviewed

Yes

Abstract

Building an acoustic-based event recognition system for smart homes is a challenging task due to the lack of high-level structures in environmental sounds. In particular, the selection of effective features is still an open problem. We make an important step toward this goal by showing that the combination of Mel-Frequency Cepstral Coefficients, Zero- Crossing Rate, and Discrete Wavelet Transform features can achieve an F1 score of 96.5% and a recognition accuracy of 97.8% with a gradient boosting classifier for ambient sounds recorded in a kitchen environment.

Description

Keywords

Smart homes, Assisted living, Activity recognition, Audio feature extraction, Classification

Citation

Vafeiadis, A., Votis, K., Giakoumis, D., Tzovaras, D., Chen, L., Hamzaoui, R. (2017) Audio-based event recognition system for smart homes. In: Proc. 14th IEEE International Conference on Ubiquitous Intelligence and Computing, San Francisco, CA, Aug. 2017.

Rights

Research Institute

Cyber Technology Institute (CTI)
Institute of Artificial Intelligence (IAI)
Institute of Engineering Sciences (IES)