Automatic discrimination of earthquakes and quarry blasts using wavelet filter bank and support vector machine
- 69 Downloads
False discrimination between earthquakes and quarry blasts may lead to an unrealistic characterization of the natural seismicity of a region. The similarity in seismograms between earthquakes and quarry blasts is the primary reason for incorrect discrimination. Therefore, in this paper, we propose a discriminative algorithm utilizing wavelet filter bank to extract unique features between earthquakes and quarry blasts. The discriminative features are found to be in the first five seconds after the onset time. The proposed algorithm is divided into two stages: first, wavelet filter bank extracts the features of the seismic signals; then, support vector machine classifies the event based on these extracted features. The proposed algorithm achieves a discrimination accuracy of 98.5% when applied to 900 earthquakes and quarry blast waveforms.
KeywordsSeismic data classification Wavelet filter bank Particle swarm optimization Support vector machine
We would like to thank Egypt-Japan University of Science and Technology (E-JUST) for the continuous support. Also, we would like to thank the National Research Institute of Astronomy and Geophysics (NRIAG) for providing the seismic data used in this paper.
This work received funding from the Egyptian Ministry of Higher Education.
- Bai Q (2010) Analysis of particle swarm optimization algorithm. Comput Inf Sci 3(1):180Google Scholar
- Catanzaro B, Sundaram N, Keutzer K (2008) Fast support vector machine training and classification on graphics processors. In: Proceedings of the 25th international conference on machine learning, ACM, pp 104–111Google Scholar
- Farahani JV (2015) Discrimination of quarry blasts and microearthquakes using adaptive neuro-fuzzy inference systems in the T ehran region. Episodes 38(3):162–168Google Scholar
- Hassan R, Cohanim B, De Weck O, Venter G (2005) A comparison of particle swarm optimization and the genetic algorithm. In: Proceedings of the 1st AIAA multidisciplinary design optimization specialist conference, vol 18, p e21Google Scholar
- Kekovalı K, Kalafat D, Deniz P (2012) Spectral discrimination between mining blasts and natural earthquakes: application to the vicinity of tunbilek mining area, western T urkey. Int J Phys Sci 7 (35):5339–5352Google Scholar
- Kennedy J (2011) Particle swarm optimization. In: Encyclopedia of machine learning, Springer, pp 760–766Google Scholar
- Percival DB, Walden AT (2006) Wavelet methods for time series analysis, vol 4. Cambridge University Press, CambridgeGoogle Scholar
- Schölkopf B, Burges CJ, Smola AJ (1999) Advances in kernel methods: support vector learning. MIT Press, CambridgeGoogle Scholar
- Selvi V, Umarani DR (2010) Comparative analysis of ant colony and particle swarm optimization techniques. Int J Comput Appl 5(4):0975–8887Google Scholar
- Shi Y, Eberhart RC (1999) Empirical study of particle swarm optimization. In: Proceedings of the 1999 congress on evolutionary computation, 1999. CEC 99. IEEE, vol 3, pp 1945-1950Google Scholar
- Strang G, Nguyen T (1996) Wavelets and filter banks. SIAM, PhiladelphiaGoogle Scholar
- Taylor SR, Denny MD, Vergino ES, Glaser RE (1989) Regional discrimination between nts explosions and western us earthquakes. Bull Seismol Soc Am 79(4):1142–1176Google Scholar
- Tong S, Chang E (2001) Support vector machine active learning for image retrieval. In: Proceedings of the ninth ACM international conference on multimedia, ACM, pp 107–118Google Scholar