Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks
Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks
Author(s): Ahmad Ihsan Yassin, Khairul Khaizi Mohd Shariff, Mustapha Awang Kechik, Adli Md Ali, Megat Syahirul Megat AminSubject(s): Electronic information storage and retrieval, Social Informatics
Published by: UIKTEN - Association for Information Communication Technology Education and Science
Keywords: Acoustic vehicle classification; long short-term memory (LSTM); acoustic traffic noise; mel-cepstral frequency features (MFCC); Machine learning
Summary/Abstract: Monitoring vehicle traffic at a large scale is a challenging task for authorities, particularly considering the high cost of traffic sensors such as vision cameras. To meet the growing demand for more accurate traffic monitoring, the use of traffic sounds has become a popular approach, as it provides insight into the types of traffic present. This paper reports on an approach to vehicle classification based on acoustic signals, using the Mel-Frequency Cepstral Coefficients (MFCC) and the Long Short-Term Memory (LSTM) networks. This study exhibited classification accuracy scores of 82-86.2% across four vehicle categories: motorcycle, car, truck, and no traffic. The results demonstrated that large-scale, low-cost acoustic processing can be effectively used for vehicle monitoring.
Journal: TEM Journal
- Issue Year: 12/2023
- Issue No: 3
- Page Range: 1490-1496
- Page Count: 7
- Language: English
