Traffic information extraction of vehicle acoustic signal based on neural networks

Zhen Shan Li; Jian Qun Wang; Guo Zhong Yao; Xue Jun Ran

doi:10.1109/CMCE.2010.5610175

Traffic information extraction of vehicle acoustic signal based on neural networks

Zhen Shan Li^*, Jian Qun Wang, Guo Zhong Yao, Xue Jun Ran

^*Corresponding author for this work

School of Mechanical Engineering

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

A method for traffic information extraction of vehicle acoustic signal based on neural networks is proposed. At first, a method of pre-processing and feature extraction of the vehicle acoustic signals is explained, and the Melfrequency cepstral coefficients are selected as the characteristic parameters of the vehicle signals. Next, the basic theory of the current most widely used neural networks - BP network (Back-Propagation Network) is introduced, and aiming the shortcoming of the BP network, the improvement method to reduce the training time of the network is proposed. At last, the experimental data is used as the sample to train the network, and the target data is recognized. The traffic information is extracted from the target data and the recognized rate can reach 90%.

Original language	English
Title of host publication	2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010
Pages	484-487
Number of pages	4
DOIs	https://doi.org/10.1109/CMCE.2010.5610175
Publication status	Published - 2010
Event	2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010 - Changchun, China Duration: 24 Aug 2010 → 26 Aug 2010

Publication series

Name	2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010
Volume	2

Conference

Conference	2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010
Country/Territory	China
City	Changchun
Period	24/08/10 → 26/08/10

Keywords

Mel-frequency cepstral coefficients
Neural networks
Traffic information extraction
Vehicle acoustic signal

Access to Document

10.1109/CMCE.2010.5610175

Cite this

Li, Z. S., Wang, J. Q., Yao, G. Z., & Ran, X. J. (2010). Traffic information extraction of vehicle acoustic signal based on neural networks. In 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010 (pp. 484-487). Article 5610175 (2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010; Vol. 2). https://doi.org/10.1109/CMCE.2010.5610175

@inproceedings{e7051afa2d004976a8b846278ed31b2c,

title = "Traffic information extraction of vehicle acoustic signal based on neural networks",

abstract = "A method for traffic information extraction of vehicle acoustic signal based on neural networks is proposed. At first, a method of pre-processing and feature extraction of the vehicle acoustic signals is explained, and the Melfrequency cepstral coefficients are selected as the characteristic parameters of the vehicle signals. Next, the basic theory of the current most widely used neural networks - BP network (Back-Propagation Network) is introduced, and aiming the shortcoming of the BP network, the improvement method to reduce the training time of the network is proposed. At last, the experimental data is used as the sample to train the network, and the target data is recognized. The traffic information is extracted from the target data and the recognized rate can reach 90%.",

keywords = "Mel-frequency cepstral coefficients, Neural networks, Traffic information extraction, Vehicle acoustic signal",

author = "Li, {Zhen Shan} and Wang, {Jian Qun} and Yao, {Guo Zhong} and Ran, {Xue Jun}",

year = "2010",

doi = "10.1109/CMCE.2010.5610175",

language = "English",

isbn = "9781424479566",

series = "2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010",

pages = "484--487",

booktitle = "2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010",

note = "2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010 ; Conference date: 24-08-2010 Through 26-08-2010",

}

Li, ZS, Wang, JQ, Yao, GZ & Ran, XJ 2010, Traffic information extraction of vehicle acoustic signal based on neural networks. in 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010., 5610175, 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, vol. 2, pp. 484-487, 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, Changchun, China, 24/08/10. https://doi.org/10.1109/CMCE.2010.5610175

Traffic information extraction of vehicle acoustic signal based on neural networks. / Li, Zhen Shan; Wang, Jian Qun; Yao, Guo Zhong et al.
2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010. 2010. p. 484-487 5610175 (2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Traffic information extraction of vehicle acoustic signal based on neural networks

AU - Li, Zhen Shan

AU - Wang, Jian Qun

AU - Yao, Guo Zhong

AU - Ran, Xue Jun

PY - 2010

Y1 - 2010

N2 - A method for traffic information extraction of vehicle acoustic signal based on neural networks is proposed. At first, a method of pre-processing and feature extraction of the vehicle acoustic signals is explained, and the Melfrequency cepstral coefficients are selected as the characteristic parameters of the vehicle signals. Next, the basic theory of the current most widely used neural networks - BP network (Back-Propagation Network) is introduced, and aiming the shortcoming of the BP network, the improvement method to reduce the training time of the network is proposed. At last, the experimental data is used as the sample to train the network, and the target data is recognized. The traffic information is extracted from the target data and the recognized rate can reach 90%.

AB - A method for traffic information extraction of vehicle acoustic signal based on neural networks is proposed. At first, a method of pre-processing and feature extraction of the vehicle acoustic signals is explained, and the Melfrequency cepstral coefficients are selected as the characteristic parameters of the vehicle signals. Next, the basic theory of the current most widely used neural networks - BP network (Back-Propagation Network) is introduced, and aiming the shortcoming of the BP network, the improvement method to reduce the training time of the network is proposed. At last, the experimental data is used as the sample to train the network, and the target data is recognized. The traffic information is extracted from the target data and the recognized rate can reach 90%.

KW - Mel-frequency cepstral coefficients

KW - Neural networks

KW - Traffic information extraction

KW - Vehicle acoustic signal

UR - http://www.scopus.com/inward/record.url?scp=78649988317&partnerID=8YFLogxK

U2 - 10.1109/CMCE.2010.5610175

DO - 10.1109/CMCE.2010.5610175

M3 - Conference contribution

AN - SCOPUS:78649988317

SN - 9781424479566

T3 - 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010

SP - 484

EP - 487

BT - 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010

T2 - 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010

Y2 - 24 August 2010 through 26 August 2010

ER -

Li ZS, Wang JQ, Yao GZ, Ran XJ. Traffic information extraction of vehicle acoustic signal based on neural networks. In 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010. 2010. p. 484-487. 5610175. (2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010). doi: 10.1109/CMCE.2010.5610175

Traffic information extraction of vehicle acoustic signal based on neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this