Cavitation noise classification based on spectral statistic features and PCA algorithm

Xiangdong Jiang; Qiang Wang; Xiangyang Zeng

doi:10.1109/ICCSNT.2013.6967148

Cavitation noise classification based on spectral statistic features and PCA algorithm

Xiangdong Jiang, Qiang Wang, Xiangyang Zeng

School of Marine Science and Technology

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

4 Scopus citations

Abstract

Small amount of training data confines the performance of auto noise classification system, especially when the dimensions of features are in a large scale. In this paper, 26-dimensional features are extracted from cavitation noise spectrum and line spectrum from three classes of cavitation noises. Principal component analysis (PCA) based method is applied to deal with the high-dimensional features which may lead to a high risk of over-fitting. Experiments using noise signals indicated that feature extracting method proposed in this paper performs well, and PCA processing is efficient to deal with the high-dimensional problem and can achieve a high recognition rate under the cases such as auto classification when the amount of training data is limited.

Original language	English
Title of host publication	Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	438-441
Number of pages	4
ISBN (Electronic)	9781479905614
DOIs	https://doi.org/10.1109/ICCSNT.2013.6967148
State	Published - 25 Nov 2014
Event	2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013 - Dalian, China Duration: 12 Oct 2013 → 13 Oct 2013

Publication series

Name	Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013

Conference

Conference	2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013
Country/Territory	China
City	Dalian
Period	12/10/13 → 13/10/13

Keywords

Cavitation noise Spectrum
High-dimensional Problem
Noise target Classification
PCA

Access to Document

10.1109/ICCSNT.2013.6967148

Cite this

Jiang, X., Wang, Q., & Zeng, X. (2014). Cavitation noise classification based on spectral statistic features and PCA algorithm. In Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013 (pp. 438-441). Article 6967148 (Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCSNT.2013.6967148

Jiang, Xiangdong ; Wang, Qiang ; Zeng, Xiangyang. / Cavitation noise classification based on spectral statistic features and PCA algorithm. Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 438-441 (Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013).

@inproceedings{ffd05f57ece04e3b90ad5c1527c6b3ed,

title = "Cavitation noise classification based on spectral statistic features and PCA algorithm",

abstract = "Small amount of training data confines the performance of auto noise classification system, especially when the dimensions of features are in a large scale. In this paper, 26-dimensional features are extracted from cavitation noise spectrum and line spectrum from three classes of cavitation noises. Principal component analysis (PCA) based method is applied to deal with the high-dimensional features which may lead to a high risk of over-fitting. Experiments using noise signals indicated that feature extracting method proposed in this paper performs well, and PCA processing is efficient to deal with the high-dimensional problem and can achieve a high recognition rate under the cases such as auto classification when the amount of training data is limited.",

keywords = "Cavitation noise Spectrum, High-dimensional Problem, Noise target Classification, PCA",

author = "Xiangdong Jiang and Qiang Wang and Xiangyang Zeng",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.; 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013 ; Conference date: 12-10-2013 Through 13-10-2013",

year = "2014",

month = nov,

day = "25",

doi = "10.1109/ICCSNT.2013.6967148",

language = "英语",

series = "Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "438--441",

booktitle = "Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013",

}

Jiang, X, Wang, Q & Zeng, X 2014, Cavitation noise classification based on spectral statistic features and PCA algorithm. in Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013., 6967148, Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013, Institute of Electrical and Electronics Engineers Inc., pp. 438-441, 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013, Dalian, China, 12/10/13. https://doi.org/10.1109/ICCSNT.2013.6967148

Cavitation noise classification based on spectral statistic features and PCA algorithm. / Jiang, Xiangdong; Wang, Qiang; Zeng, Xiangyang.
Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013. Institute of Electrical and Electronics Engineers Inc., 2014. p. 438-441 6967148 (Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013).

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

TY - GEN

T1 - Cavitation noise classification based on spectral statistic features and PCA algorithm

AU - Jiang, Xiangdong

AU - Wang, Qiang

AU - Zeng, Xiangyang

PY - 2014/11/25

Y1 - 2014/11/25

N2 - Small amount of training data confines the performance of auto noise classification system, especially when the dimensions of features are in a large scale. In this paper, 26-dimensional features are extracted from cavitation noise spectrum and line spectrum from three classes of cavitation noises. Principal component analysis (PCA) based method is applied to deal with the high-dimensional features which may lead to a high risk of over-fitting. Experiments using noise signals indicated that feature extracting method proposed in this paper performs well, and PCA processing is efficient to deal with the high-dimensional problem and can achieve a high recognition rate under the cases such as auto classification when the amount of training data is limited.

AB - Small amount of training data confines the performance of auto noise classification system, especially when the dimensions of features are in a large scale. In this paper, 26-dimensional features are extracted from cavitation noise spectrum and line spectrum from three classes of cavitation noises. Principal component analysis (PCA) based method is applied to deal with the high-dimensional features which may lead to a high risk of over-fitting. Experiments using noise signals indicated that feature extracting method proposed in this paper performs well, and PCA processing is efficient to deal with the high-dimensional problem and can achieve a high recognition rate under the cases such as auto classification when the amount of training data is limited.

KW - Cavitation noise Spectrum

KW - High-dimensional Problem

KW - Noise target Classification

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=84919446383&partnerID=8YFLogxK

U2 - 10.1109/ICCSNT.2013.6967148

DO - 10.1109/ICCSNT.2013.6967148

M3 - 会议稿件

AN - SCOPUS:84919446383

T3 - Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013

SP - 438

EP - 441

BT - Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013

Y2 - 12 October 2013 through 13 October 2013

ER -

Jiang X, Wang Q, Zeng X. Cavitation noise classification based on spectral statistic features and PCA algorithm. In Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013. Institute of Electrical and Electronics Engineers Inc. 2014. p. 438-441. 6967148. (Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013). doi: 10.1109/ICCSNT.2013.6967148

Cavitation noise classification based on spectral statistic features and PCA algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this