×

A new classification method of infrasound events using Hilbert-Huang transform and support vector machine. (English) Zbl 1407.94040

Summary: Infrasound is a type of low frequency signal that occurs in nature and results from man-made events, typically ranging in frequency from 0.01Hz to 20Hz. In this paper, a classification method based on Hilbert-Huang transform (HHT) and support vector machine (SVM) is proposed to discriminate between three different natural events. The frequency spectrum characteristics of infrasound signals produced by different events, such as volcanoes, are unique, which lays the foundation for infrasound signal classification. First, the HHT method was used to extract the feature vectors of several kinds of infrasound events from the Hilbert marginal spectrum. Then, the feature vectors were classified by the SVM method. Finally, the present of classification and identification accuracy are given. The simulation results show that the recognition rate is above 97.7%, and that approach is effective for classifying event types for small samples.

MSC:

94A12 Signal theory (characterization, reconstruction, filtering, etc.)
62H30 Classification and discrimination; cluster analysis (statistical aspects)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Cannata, A.; Montalto, P.; Aliotta, M.; Cassisi, C.; Pulvirenti, A.; Privitera, E.; Patanè, D., Clustering and classification of infrasonic events at Mount Etna using pattern recognition techniques, Geophysical Journal International, 185, 1, 253-264 (2011) · doi:10.1111/j.1365-246X.2011.04951.x
[2] Bedard, A. J.; Georges, T. M., Atmospheric infrasound, Physics Today, 53, 3, 32-37 (2000)
[3] Assink, J. D.; Evers, L. G.; Holleman, I.; Paulssen, H., Characterization of infrasound from lightning, Geophysical Research Letters, 35, 15 (2008) · doi:10.1029/2008GL034193
[4] Mutschlecner, J. P.; Whitaker, R. W., Infrasound from earthquakes, Journal of Geophysical Research: Atmospheres, 110, 1108-1118 (2005)
[5] Zhang, R. R., Characterizing and quantifying earthquake-induced site nonlinearity, Soil Dynamics and Earthquake Engineering, 26, 8, 799-812 (2006) · doi:10.1016/j.soildyn.2005.03.004
[6] Le Pichon, A.; Herry, P.; Mialle, P.; Vergoz, J.; Brachet, N.; Garcés, M.; Drob, D.; Ceranna, L., Infrasound associated with 2004-2005 large Sumatra earthquakes and tsunami, Geophysical Research Letters, 32, 19, 1-5 (2005) · doi:10.1029/2005GL023893
[7] Cárdenas-Peña, D.; Orozco-Alzate, M.; Castellanos-Dominguez, G., Selection of time-variant features for earthquake classification at the Nevado-del-Ruiz volcano, Computers & Geosciences, 51, 293-304 (2013) · doi:10.1016/j.cageo.2012.08.012
[8] Johnson, J. B.; Ripepe, M., Volcano infrasound: a review, Journal of Volcanology and Geothermal Research, 206, 3-4, 61-69 (2011) · doi:10.1016/j.jvolgeores.2011.06.006
[9] Kim, T. S.; Hayward, C.; Stump, B., Local infrasound signals from the Tokachi-Oki earthquake, Geophysical Research Letters, 31, 20 (2004) · doi:10.1029/2004GL021178
[10] Tsybul’skaya, N. D.; Kulichkov, S. N.; Chulichkov, A. I., Studying possibilities for the classification of infrasonic signals from different sources, Izvestiya—Atmospheric and Ocean Physics, 48, 4, 384-390 (2012) · doi:10.1134/S0001433812040147
[11] Wang, W., The Study of Feature Extraction for Fishes Acoustic Signal (2009), Harbin, China: Harbin Egineering University, Harbin, China
[12] Li, X. X., A Research of Ships and Whales Acoustic Signal Feature Extraction and Classification Recognition (2012), Harbin, China: Harbin Engineering University, Harbin, China
[13] Ham, F. M.; Rekab, K.; Acharyya, R.; Lee, Y. C., Infrasound signal classification using parallel RBF Neural Networks, International Journal of Signal and Imaging Systems Engineering, 1, 155-167 (2008)
[14] Ham, F. M.; Iyengar, I.; Hambebo, B. M.; Garces, M.; Deaton, J.; Perttu, A.; Williams, B., A neurocomputing approach for monitoring plinian volcanic eruptions using infrasound, Procedia Computer Science, 13, 7-17 (2012) · doi:10.1016/j.procs.2012.09.109
[15] Deal, G. E.; Ham, F. M., Speaker recognition using parallel neural network modules, Neural, Parallel & Scientific Computations, 17, 3-4, 215-238 (2009)
[16] Park, S.; Ham, F. M.; Lowrie, C. G., Discrimination of infrasound events using parallel neural network classification banks, Nonlinear Analysis: Theory, Methods & Applications, 63, 5-7, e859-e865 (2005) · Zbl 1222.62140 · doi:10.1016/j.na.2005.02.016
[17] Chilo, J.; Lindblad, T.; Olsson, R.; Hansen, S. E., Comparison of three featrue extraction techniques to distinguish between different infrasound signal, Progress in Pattern Recognition, 75-82 (2007), Springer
[18] Chilo, J.; Jabor, A.; Liszka, L.; Eide, Å. J.; Lindblad, T.; Bergkvist, L. P. N.; Ståhlsten, T.; Andersson, B. L.; Karasalo, I.; Cederholm, A., Filtering and extracting features from infrasound data, Proceedings of the 14th IEEE-NPSS Real Time Conference · doi:10.1109/RTC.2005.1547494
[19] Huang, N. E.; Wu, Z., A review on Hilbert-Huang transform: method and its applications to geophysical studies, Reviews of Geophysics, 46, 2 (2008) · doi:10.1029/2007RG000228
[20] Huang, N. E.; Shen, Z.; Long, S. R.; Wu, M. C.; Shih, H. H.; Zheng, Q.; Yen, N.; Tung, C. C.; Liu, H. H., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 454, 1971, 903-995 (1998) · Zbl 0945.62093 · doi:10.1098/rspa.1998.0193
[21] Huang, N. E.; Shen, S. P., Hilbert-Huang Transform and Its Applications (2005), Singapore: World Scientific, Singapore · Zbl 1087.62500
[22] Cortes, C.; Vapnik, V., Support—vector networks, Machine Learning, 20, 3, 273-297 (1995) · Zbl 0831.68098 · doi:10.1007/BF00994018
[23] Saravanan, N.; Kumar Siddabattuni, V. N. S.; Ramachandran, K. I., A comparative study on classification of features by SVM and PSVM extracted using Morlet wavelet for fault diagnosis of spur bevel gear box, Expert Systems with Applications, 35, 3, 1351-1366 (2008) · doi:10.1016/j.eswa.2007.08.026
[24] Wang, R. H., AdaBoost for feature selection, classification and its relation with SVM, a review, Physics Procedia, 25, 800-807 (2012) · doi:10.1016/j.phpro.2012.03.160
[25] Li, S.; Zhou, W.; Yuan, Q.; Geng, S.; Cai, D., Feature extraction and recognition of ictal EEG using EMD and SVM, Computers in Biology and Medicine, 43, 7, 807-816 (2013) · doi:10.1016/j.compbiomed.2013.04.002
[26] Liu, Q.; Chen, C.; Zhang, Y.; Hu, Z., Feature selection for support vector machines with RBF kernel, Artificial Intelligence Review, 36, 2, 99-115 (2011) · doi:10.1007/s10462-011-9205-2
[27] Smola, A. J., Learning with Kernels (1998), Berlin, Germany: Technical University of Berlin, Berlin, Germany
[28] Su, C. T.; Yang, C. H., Feature selection for the SVM: an application to hypertension diagnosis, Expert Systems with Applications, 34, 1, 754-763 (2008) · doi:10.1016/j.eswa.2006.10.010
[29] Wang, F.; He, K.; Liu, Y.; Li, L.; Hu, X., Research on the selection of kernel function in SVM based facial expression recognition, Proceedings of the 8th IEEE Conference on Industrial Electronics and Applications (ICIEA ’13) · doi:10.1109/ICIEA.2013.6566586
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.