An Automatic Pipeline Monitoring System Based on PCA and SVM
This paper proposes a novel system for monitoring the
health of underground pipelines. Some of these pipelines transport
dangerous contents and any damage incurred might have catastrophic
consequences. However, most of these damage are unintentional and
usually a result of surrounding construction activities. In order to
prevent these potential damages, monitoring systems are
indispensable. This paper focuses on acoustically recognizing road
cutters since they prelude most construction activities in modern
cities. Acoustic recognition can be easily achieved by installing a
distributed computing sensor network along the pipelines and using
smart sensors to “listen" for potential threat; if there is a real threat,
raise some form of alarm. For efficient pipeline monitoring, a novel
monitoring approach is proposed. Principal Component Analysis
(PCA) was studied and applied. Eigenvalues were regarded as the
special signature that could characterize a sound sample, and were
thus used for the feature vector for sound recognition. The denoising
ability of PCA could make it robust to noise interference. One class
SVM was used for classifier. On-site experiment results show that the
proposed PCA and SVM based acoustic recognition system will be
very effective with a low tendency for raising false alarms.
[1] R.J Eiber, R.J.; D.J. Jones, G.S.Kramer, "Outside force causes most
natural gas pipeline failures", Oil and Gas Journal, vol.85, issue 11,
pp.52-57, March 1987.
[2] D. Hausamann, et.al, "Monitoring of gas transmission pipelines-A
customer driven civil UAV application", ODAS Conference, 2003.
[3] JE. Huebler, "Detection of Unauthorized Construction Equipment in
Pipeline Right-of-Ways", Technical Report of Gas Technology Institute,
2004.
[4] C. Wan, A. Mita and T.Kume, "An automatic pipeline monitoring system
using sound information", Structural Control and Health Monitoring, to
be published ; published inially within the online version of the Structual
Control and Health Monitoring. DOI : 10.1002/stc.295.
[5] C. Wan and A. Mita, " Recognition of potential danger to buried pipelines
based on sounds ", Structural Control and Health Monitoring, to be
published.
[6] L. Ma, B. Milner and D. Smith, "Acoustic environment classification",
ACM TSLP, vol.3, issue.2, pp.1-22, July 2006.
[7] L. Lu, S.Z. Li, H.J. Zhang, "Content-based audio segmentation using
support vector machines", IEEE international conference on Multimedia
and Expo, pp.956-959, 2001.
[8] P. Gaunard, C.G. Mubikangiey, C. Couvreur, V. Fontaine, "Automatic
classification of environmental noise events by hiddenMarkov model",
Proc. IEEE, vol.6, pp.3609-3612, May 1998.
[9] V. Peltonen. J. Tuomi, A. Klapuri, J. Huopaniemi and T. Sorsa,
"Computational auditory scene recognition", Proc. IEEE, vol.2,
pp.1941-1944, May 2002.
[10] L. Lu, S.Z. Li, H.J. Zhang, "Content-based audio classification and
segmentation by using support vector machines", Multimedia Systems,
vol.8, no.3, pp.482-492, 2003.
[11] Y.Toyoda, J. Huang, S. Ding and Y. Liu, "Environmental sound
recognition by multilayered neural networks", Proc. IEEE, CIT,
pp.123-127, Sep 2004.
[12] A.G. Krishna and T.V. Sreenivas, "Music instrument recognition: from
isolated notes to solo phrases", Proc. IEEE, vol.4, pp.265-268, May 2004.
[13] R.S. Goldhor, "Recognition of Environment Sounds", Proc.IEEE on
Acoustics, Speech, and Signal Processing, Vol.1, pp.149-152, Apr 1993.
[14] R. Unnthorsson, T.P. Runarsson and M.T. Jonsson, "Model selection in
one class nu-SVMs using RBF kernels", 16th Conference on Condition
Monitoring and Diagnostic, pp.1-11, April 2003.
[15] Principal Component analysis (PCA) or Empirical Orthogonal Function
(EOF), Lecture notes, Lunds University. Available:
http://aqua.tvrl.lth.se/course/VVR005F/2%20EOF.pdf
[16] Principal Component analysis, notes from Indiana University, Available:
http://cheminfo.informatics.indiana.edu/~rguha/writing/notes/stats/node
7.html
[17] Principal Components and Factor Analysis, electronic statistics textbook,
StatSoft, Inc, Available : http://www.statsoft.com/textbook/stfacan.html
[1] R.J Eiber, R.J.; D.J. Jones, G.S.Kramer, "Outside force causes most
natural gas pipeline failures", Oil and Gas Journal, vol.85, issue 11,
pp.52-57, March 1987.
[2] D. Hausamann, et.al, "Monitoring of gas transmission pipelines-A
customer driven civil UAV application", ODAS Conference, 2003.
[3] JE. Huebler, "Detection of Unauthorized Construction Equipment in
Pipeline Right-of-Ways", Technical Report of Gas Technology Institute,
2004.
[4] C. Wan, A. Mita and T.Kume, "An automatic pipeline monitoring system
using sound information", Structural Control and Health Monitoring, to
be published ; published inially within the online version of the Structual
Control and Health Monitoring. DOI : 10.1002/stc.295.
[5] C. Wan and A. Mita, " Recognition of potential danger to buried pipelines
based on sounds ", Structural Control and Health Monitoring, to be
published.
[6] L. Ma, B. Milner and D. Smith, "Acoustic environment classification",
ACM TSLP, vol.3, issue.2, pp.1-22, July 2006.
[7] L. Lu, S.Z. Li, H.J. Zhang, "Content-based audio segmentation using
support vector machines", IEEE international conference on Multimedia
and Expo, pp.956-959, 2001.
[8] P. Gaunard, C.G. Mubikangiey, C. Couvreur, V. Fontaine, "Automatic
classification of environmental noise events by hiddenMarkov model",
Proc. IEEE, vol.6, pp.3609-3612, May 1998.
[9] V. Peltonen. J. Tuomi, A. Klapuri, J. Huopaniemi and T. Sorsa,
"Computational auditory scene recognition", Proc. IEEE, vol.2,
pp.1941-1944, May 2002.
[10] L. Lu, S.Z. Li, H.J. Zhang, "Content-based audio classification and
segmentation by using support vector machines", Multimedia Systems,
vol.8, no.3, pp.482-492, 2003.
[11] Y.Toyoda, J. Huang, S. Ding and Y. Liu, "Environmental sound
recognition by multilayered neural networks", Proc. IEEE, CIT,
pp.123-127, Sep 2004.
[12] A.G. Krishna and T.V. Sreenivas, "Music instrument recognition: from
isolated notes to solo phrases", Proc. IEEE, vol.4, pp.265-268, May 2004.
[13] R.S. Goldhor, "Recognition of Environment Sounds", Proc.IEEE on
Acoustics, Speech, and Signal Processing, Vol.1, pp.149-152, Apr 1993.
[14] R. Unnthorsson, T.P. Runarsson and M.T. Jonsson, "Model selection in
one class nu-SVMs using RBF kernels", 16th Conference on Condition
Monitoring and Diagnostic, pp.1-11, April 2003.
[15] Principal Component analysis (PCA) or Empirical Orthogonal Function
(EOF), Lecture notes, Lunds University. Available:
http://aqua.tvrl.lth.se/course/VVR005F/2%20EOF.pdf
[16] Principal Component analysis, notes from Indiana University, Available:
http://cheminfo.informatics.indiana.edu/~rguha/writing/notes/stats/node
7.html
[17] Principal Components and Factor Analysis, electronic statistics textbook,
StatSoft, Inc, Available : http://www.statsoft.com/textbook/stfacan.html
@article{"International Journal of Architectural, Civil and Construction Sciences:52982", author = "C. Wan and A. Mita", title = "An Automatic Pipeline Monitoring System Based on PCA and SVM", abstract = "This paper proposes a novel system for monitoring the
health of underground pipelines. Some of these pipelines transport
dangerous contents and any damage incurred might have catastrophic
consequences. However, most of these damage are unintentional and
usually a result of surrounding construction activities. In order to
prevent these potential damages, monitoring systems are
indispensable. This paper focuses on acoustically recognizing road
cutters since they prelude most construction activities in modern
cities. Acoustic recognition can be easily achieved by installing a
distributed computing sensor network along the pipelines and using
smart sensors to “listen" for potential threat; if there is a real threat,
raise some form of alarm. For efficient pipeline monitoring, a novel
monitoring approach is proposed. Principal Component Analysis
(PCA) was studied and applied. Eigenvalues were regarded as the
special signature that could characterize a sound sample, and were
thus used for the feature vector for sound recognition. The denoising
ability of PCA could make it robust to noise interference. One class
SVM was used for classifier. On-site experiment results show that the
proposed PCA and SVM based acoustic recognition system will be
very effective with a low tendency for raising false alarms.", keywords = "One class SVM, pipeline monitoring system,
principal component analysis, sound recognition, third party damage.", volume = "2", number = "9", pages = "209-7", }