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.
| Original language | English |
|---|---|
| Title of host publication | Audio-based event recognition system for smart homes |
| Place of Publication | San Francisco, CA, USA |
| Publisher | IEEE Xplore |
| Pages | 1-8 |
| Number of pages | 8 |
| ISBN (Electronic) | 978-1-5386-0435-9 |
| ISBN (Print) | 978-1-5386-1591-1 |
| DOIs | |
| Publication status | Published (in print/issue) - 8 Aug 2017 |
| Event | 2017 IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation - San Francisco, CA Duration: 4 Aug 2017 → 8 Aug 2017 |
Conference
| Conference | 2017 IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation |
|---|---|
| Period | 4/08/17 → 8/08/17 |
Keywords
- feature extraction
- mel frequency cepstral coefficient
- discrete wavelet tranforms
- home computing
- signal classificatioin
- smart homes
- assisted living
- activity recognition
- audio feature extraction
- classification
- mel-frequency
- zero-crossing rate
- wavelets
