Wavelet Packet Analysis Based Feature Extraction of Vehicular Acoustic Signal

Abstract:

In this paper, an approach based on wavelet packet analysis is proposed to deal with the problem that acoustic signal of moving vehicle is easily influenced by environmental noise in vehicle type classification. Wavelet packet analysis is applied to extract local and detail feature information of acoustic signal in the time-frequency domain. Firstly, raw acoustic signal is decomposed into different frequency bands by wavelet packet analysis, and then decomposition coefficients are reconstructed. The energy of every frequency band component is used to form the feature vector. Finally, vehicle type classification is implemented by RBF neural network on the basis of these feature vectors. Experimental results show that the proposed method is feasible and effective.

• Periodical: Applied Mechanics and Materials (Volumes 55-57)
• Pages: 1593-1598
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.55-57.1593
• Online since: May 2011
• Authors: Xiao Xuan Qi, Jian Wei Ji, Xiao Wei Han, Zhong Hu Yuan
• Keywords: Acoustic Signal, Feature Extraction, Vehicle Type Classification, Wavelet Packet (WP)

References

[1] Y. Seung S., K. Yoon G., and H. Choi: Distributed and efficient classifiers for wireless audio-sensor networks [C], in 5th International Conference on Volume, Apr., (2008).

[2] LI Ping, LIU Ning, SU Jing-liang, ZHENG Xue-bing: Composite Method of Acoustic Signal of Target in Battlefield [J]. Journal of Detection & Control, 2002, 24(1): 29-32.

[3] Yang Jin, Wen Yumei, Li Ping: Feature extraction and identification of leak acoustic signal in water distribution pipelines using correlation analysis and approximate entropy [J]. Chinese Journal of Scientific Instrument, 2009, 30(2): 272-279.

DOI: 10.1109/wcica.2008.4594487

[4] CHEN Dan, LI Jing-hua, HUANG Gen-quan: XU Jin-dong. Research on Recognition of Passive Acoustic Multitarget Based on Evidence Theory [J]. Journal of System Simulation, 2007, 19(6): 1323-1325.

[5] Geng Senlin, Shang Zhiyuan: Research progress and prospects of stored grain insect sound detection technology [J]. Transactions of the CSAE, 2006, 22(4): 204-207.

[6] WU FengQi, MENG Guang, SUN Xu, Jing JianPing: Feature extraction based on acoustic signal's 3-D spectrum analysis in rotor malfuncions [J]. Journal of Mechanical Strength, 2006, 28(3): 424-428.

[7] Z. Chen: Wavelet analysis algorithm and application. Xian: Xian Jiaotong University Press, (1998).

[8] Li Wushen, Di Xinjie, and Bai Shiwu, et al.: Feature Analysis of Metal Magnetic Memory Signals for Welding Crack based on Wavelet Energy Spectrum, INSIGHT: Non-Destructive Testing and Condition Monitoring, The British Institute of Non-Destructive Testing, Northampton, UK, 2006, vol(48): 426-429.

DOI: 10.1784/insi.2006.48.7.426

[9] Jamshed N. Patel, Ashfaq A. Khokhar, Leah H. Jamieson: On the Scalability of 2-D Wavelet Transform Algorithms on Fine-grained Parallel Machines [C]. in 1996 International Conference on Parallel Processing, Ⅱ24-Ⅱ28.

DOI: 10.1109/icpp.1996.537377

[10] LIAO Wei, SI Juanning, Yi Liu: Fault Diagnosis for Turbine Generator Based on Wavelet Packet PCA-SVM [C]. in 2nd International Conference on Future Computer and Communication, 2010, V1-90: V1-94.

DOI: 10.1109/icfcc.2010.5497831