簡易檢索 / 詳目顯示

研究生: 鄭期傑
Chi-Chieh Tseng
論文名稱: 以主成份分析實現地震偵測
Earthquake Detection By Principal Component Analysis
指導教授: 金台齡
Tai-Lin Chin
口試委員: 鄧惟中
Wei-Chung Teng
吳逸民
Yih-Min Wu
學位類別: 碩士
Master
系所名稱: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
論文出版年: 2016
畢業學年度: 104
語文別: 英文
論文頁數: 118
中文關鍵詞: 主成份分析大數據感測器網路感測器資料統整P波預警儀地震預警
外文關鍵詞: Principal Component Analysis, Big Data, Sensor Network, Sensor Fusion, Palert, Earthquake Early Warning
相關次數: 點閱:409下載:6
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

地震是在許多國家都會發生的重大災難,有時甚至可能會對生命和財產造成毀滅性的影響。
雖然許多研究者希望如同預測天氣一般預測地震,但目前尚未能建立出可靠的地震預測系統。因此,研究人員把注意力轉向在地震發生時盡快偵測地震事件的出現,這就是被稱為地震預警的概念。在本論文中,我們提出一個方法,利用主成分分析這個統計方法來偵測地震,並將我們的系統實作在台灣的Palert地震感測器網絡之上。通過對整個網絡在平常時的行為建立統計模型,我們可以更好的了解感測器網絡在沒有地震時的行為,使我們能夠從不斷發生的假警報中偵測到地震事件。實驗結果與數據顯示,我們的方法可以在不增加誤報率且不減少偵測率的情況下更早的偵測到地震,確保系統的可靠性和實用性。我們的系統已經可以在現實世界被實際利用,並有可能挽救生命和防止地震所造成的財產損失。


Earthquake is a major disaster in many countries, and its effect can be devastating. Due to the challenges in predicting earthquakes, researchers have turned their attention to detecting the occurrence of an earthquake as soon as possible, a concept known as earthquake early warning (EEW). In this paper, we propose a novel method for detecting earthquakes based on Principal Component Analysis (PCA), built upon the Palert seismic sensor network in Taiwan. By building statistical models for the behavior of the network, we can better understand the behavior during of the noise, allowing us to separate an earthquake from the constant false alarms. Experiment results with real world data show that our method can detect earthquakes earlier than existing methods without increase in false alarm rate or decrease in detection rate, which is pivotal in ensuring the credibility and effectiveness of the system. Our system is ready for real world deployment, and can potentially save lives and prevent property damage caused by earthquakes.

Chapter 1: Introduction 1.1 Background 1.2 Motivation 1.3 Methods 1.4 Contributions 1.5 Overview Chapter 2: Literature Review 2.1 Earthquake Detection 2.2 Principal Component Analysis Chapter 3: Methods 3.1 Principal Component Analysis (PCA) 3.1.1 Notations 3.1.2 Derivation 3.1.3 Applications 3.1.4 Finding the Principal Components 3.1.5 Singular Value Decomposition (SVD) 3.1.6 Randomized Matrix Approximation 3.2 Anomaly Detection by PCA 3.2.1 PC1 Projection Metric 3.2.2 Mahalanobis Distance Metric 3.2.3 Reconstruction Residual Metric 3.3 Detection Algorithm 3.4 Compared Method 3.4.1 STA/LTA 3.4.2 Zero-Crossing 3.4.3 Signal-to-Noise Ratio 3.4.4 Sensor Fusion Chapter 4: Experimental Results 4.1 Data Acquisition 4.2 Visualizing the Seismic Data with PCA 4.2.1 Visualizing the Seismic Data in Two and Three Dimensions 4.2.2 Visualizing the Change of First PC Over Time 4.3 Parameter Selection 4.3.1 Selecting Window Size 4.3.2 Selecting Threshold 4.4 Comparison Between Our Method and the VSN System Chapter 5: Conclusion Chapter 6: Future Work 6.1 Interpreting Principal Components 6.2 Database of Principal Components 6.3 Human-Machine Cooperation Appendix 1: Detection Results For Mahalanobis Distance Metric with W=1000, K=167 and T=7 Appendix 2: Detection Results For Mahalanobis Distance Metric with W=1000, K=167 and T=8 Appendix 3: Detection Results For Mahalanobis Distance Metric with W=3000, K=253 and T=8 Appendix 4: Detection Results For Mahalanobis Distance Metric with W=3000, K=253 and T=9 Appendix 5: Detection Results For Reconstruction Residual Metric with W=1000, K=167 and T=60 Appendix 6: Detection Results For Reconstruction Residual Metric with W=3000, K=253 and T=60 Appendix 7: Detection Results For PC1 Projection Metric with W=1000, K=1 and T=12 Appendix 8: ROC Statistics For Mahalanobis Distance Metric with W=1000 Appendix 9: ROC Statistics For Mahalanobis Distance Metric with W=3000 Appendix 10: ROC Statistics For Reconstruction Residual Metric with W=1000 Appendix 11: ROC Statistics For Reconstruction Residual Metric with W=3000 Appendix 12: ROC Statistics For PC1 Projection Metric with W=1000 Appendix 13: ROC Statistics For PC1 Projection Metric with W=3000

[1] List of natural disasters by death toll, https://en.wikipedia.org/wiki/List_of_natural_disasters_by_death_toll#52_deadliest_earthquakes
[2] The World Bank Group, http://data.worldbank.org/indicator/SP.POP.TOTL
[3] Pacific Northwest Seismic Network, http://pnsn.org/outreach/earthquakehazards/fire
[4] Product specification at the Sanlien website, http://www.sanlien.com/web/homepage.nsf/foundationview/E7884512E2261FE2482578D3002BCF8A
[5] Seismic wave, https://en.wikipedia.org/wiki/Seismic_wave
[6] Confusion Matrix, https://en.wikipedia.org/wiki/Confusion_matrix
[7] Grid Center of Academia Sinica, http://palert.grid.sinica.edu.tw:9999/
[8] Earthquake event archive at National Taiwan University, ftp://140.112.65.220:2121/
[9] Seismological Lab of the Department of Geophysics of National Taiwan University, http://seismology.gl.ntu.edu.tw/main.htm
[10] PCA-Based Anomaly Detection of the Microsoft Azure Documentation, https://msdn.microsoft.com/en-us/library/azure/dn913102.aspx
[11] Earthworm Central, http://www.earthwormcentral.org/
[12] Search for Extraterrestial Intellegence, http://www.seti.org/
[13] Y.-M. Wu, and H. Kanamori, "Experiment on an onsite early warning method for the Taiwan early warning system," Bulletin of the Seismological Society of America, vol. 95, no. 1, pp. 347-353, Feb. 2005.
[14] Y. Nakamura, "UrEDAS, urgent earthquake detection and alarm system, now and future," Proceedings of the 13th world conference on earthquake engineering, 2004.
[15] S. Horiuchi, H. Negishi, K. Abe, A. Kamimura, and Y. Fujinawa, "An automatic processing system for broadcasting earthquake alarms," Bulletin of the Seismological Society of America, vol. 95, no. 2, pp. 708-718, Apr. 2005.
[16] T. Odaka, K. Ashiya, S. Y. Tsukada, S. Sato, K. Ohtake, and D. Nozaka, "A new method of quickly estimating epicentral distance and magnitude from a single seismic record," Bulletin of the Seismological Society of America, vol. 93,
no. 1, pp. 526 532, Feb. 2003.
[17] Y.-M. Wu, and H. Kanamori, "Exploring the feasibility of on-site earthquake early warning using close-in records of the 2007 Noto Hanto earthquake," Earth Planets and Space, vol. 60, no. 2, pp. 155, 2008.
[18] Y.-M. Wu, H. Kanamori, R. Allen, and E. Hauksson, "Determination of earthquake early warning parameters, c and Pd, for southern California," Geophysical Journal International, vol. 170, no. 2, pp. 711-717, 2007.
[19] Y.-M. Wu, H.-Y. Yen, L. Zhao, B.-S. Huang, and W.-T. Liang, "Magnitude determination using initial P waves: A singlestation approach," Geophysical Research Letters, vol. 33, no. 5, 2006.
[20] C.E. Johnson, A. Bittenbinder, B. Bogaert, L. Dietz, and W. Kohler, "Earthworm: A exible approach to seismic network processing," Iris newsletter, vol. 14, no. 2, pp. 1-4, 1995.
[21] Y.-M. Wu, D.-Y. Chen, T.-L. Lin, C.-Y. Hsieh, T.-L. Chin, W.-Y. Chang, W.-S. Li, and S.-H. Ker, "A HighDensity Seismic Network for Earthquake Early Warning in Taiwan Based on Low Cost Sensors," Seismological Research Letters, vol. 84, no. 6, pp. 1048-1054, Nov. 2013.
[22] Y.-M. Wu, and T.-L. Lin, "A test of earthquake early warning system using low cost accelerometer in Hualien, Taiwan," Early Warning for Geological Disasters, pp. 253-261, 2014.
[23] Y. Fujinawa, Y. Rokugo, Y. Noda, Y. Mizui, M. Kobatashi, and E. Mizutani, "Efforts of earthquake disaster mitigation using earthquake early warning in Japan," The 14th world conference on earthquake engineering, 2008.
[24] J.M. Aranda, A. Jimenez, G. Ibarrola, F. Alcantar, A. Aguilat, M. Inostroza, and S. Maldonado, "Mexico City seismic alert system," Seismological Research Letters, vol. 66, no. 6, pp. 42-53, 1995.
[25] N.-C. Hsiao, Y.-M. Wu, T.-C. Shin, L. Zhao, and T.-L. Teng, "Development of earthquake early warning system in Taiwan," Geophysical research letters, vol. 36, no. 5, 2009.
[26] K.-S. Liu, T.-C. Shin, and Y.-B. Tsai, "A freefield strong motion network in Taiwan: TSMIP," TAO, vol. 10, no. 2, pp. 377-396, Jun.1999.
[27] Y.-M. Wu, T.-C. Shin, C.-C. Chen, Y.-B. Tsai, W. H. K. Lee, and T.-L. Teng, "Taiwan rapid earthquake information release system," Seismological Research Letters, vol. 68, no. 6, pp. 931-943, Nov. 1997.
[28] Y.-M. Wu, W. H. K. Lee, C.-C. Chen, T.-C. Shin, T.-L. Teng, and Y.-B. Tsai, "Performance of the Taiwan rapid earthquake information release system (RTD) during the 1999 Chi-Chi (Taiwan) earthquake," Seismological Research Letters, vol. 71, no. 3, pp. 338-343, May 1997.
[29] W.H.K. Lee, T.-C. Shin, and T.-L. Teng, "Design and implementation of earthquake early warning systems in Taiwan," Proc. 11th World Conference on Earthquake Engineering, 1996.
[30] Y.-M. Wu, T.-C. Shin, and Y.B. Tsai, "Quick and reliable determination of magnitude for seismic early warning," Bulletin of the Seismological Society of America, vol. 88, no. 5, pp. 1254-1259, Oct. 1998.
[31] Y.-M.Wu, J.-K. Chung, T.-C. Shin, N.-C. Hsiao, Y.-B. Tsai, W. H. K. Lee, and T.-L. Teng, "Development of an integrated earthquake early warning system in Taiwan-Case for the Hualien area earthquakes," TAO, vol. 10, no. 4, pp. 719-736, Dec.1999.
[32] R. Allen, "Automatic earthquake recognition and timing from single traces," Bulletin of the Seismological Society of America, vol. 68, no. 5, pp. 1521-1532, Oct. 1978.
[33] R. Allen, "Automatic phase pickers: their present use and future prospects," Bulletin of the Seismological Society of America, vol. 72, no. 6b, pp. s225-s242, Dec. 1982.
[34] R. Allen, and H. Kanamori, "The potential for earthquake early warning in southern California," Science, vol. 300, no. 5620, pp. 786-789, Sep. 2003.
[35] Y. Nakamura, "On the urgent earthquake detection and alarm system (UrE-DAS)," Proc. of the 9th World Conference on Earthquake Engineering, vol. 7, pp. 673-678, Aug. 1988.
[36] H. Kanamori, "Real-time seismology and earthquake damage mitigation," Annu. Rev. Earth Planet. Sci., vol. 33, pp. 195-214, Dec. 2004.
[37] Y.-M. Wu, and H. Kanamori, "Development of an earthquake early warning system using real-time strong motion signals," Sensors, vol. 8, no. 1, pp. 1-9, 2008.
[38] L. Geiger, "Probability method for the determination of earthquake epicenters from the arrival time only," Bulletin of St. Louis University, vol. 8, no. 1, pp. 56-71, 1912.
[39] S. Satriano, A. Lomax, and A. Zollo, "Real-time evolutionary earthquake location for seismic early warning," Bulletin of the Seismological Society of America, vol. 98, no. 3, pp. 1482-1494, Jun. 2008.
[40] F. Aurenhammer, "Voronoi diagrams a survey of a fundamental geometric data structure," ACM Computing Surveys, vol. 23, no. 3, pp. 345-405, Sep. 1991.
[41] K.R. Anderson, "Epicentral location using arrival time order," Bulletin of the Seismological Society of America, vol. 71, no. 2, pp. 541-545, Apr. 1981.
[42] D.P. Scha , and D. Waldhauser, "Waveform cross-correlation-based differential travel-time measurements at the Northern California Seismic Network," Bulletin of the Seismological Society of America, vol. 95, no. 6, pp. 2446-2461, Dec.
2005.
[43] P.M. Shearer, "Improving local earthquake locations using the L1 norm and waveform cross correlation: Application to the Whittier Narrows, California, aftershock sequence," Journal of Geophysical Research: Solid Earth, vol. 102,
no. b4, pp. 8269-8283, Apr. 1997.
[44] T. Sakaki, M. Okazaki, and Y. Matsuo, "Earthquake shakes Twitter users: real-time event detection by social sensors," Proceedings of the 19th international conference on World wide web, pp. 851-860, Apr. 2010.
[45] T. Sakaki, M. Okazaki, and Y. Matsuo, "Tweet analysis for real-time event detection and earthquake reporting system development," IEEE Transactions on Knowledge and Data Engineering, vol. 25, no. 4, pp. 919-931, Apr. 2013.
[46] I.V. Rodriguez, "Automatic Time-picking of Micro seismic Data Combining STA/LTA and the Stationary Discrete Wavelet Transform," CSPG CSEG CWLS Convention, convention abstracts, 2011.
[47] S.W. Stewart, "Principles and applications of micro earthquake networks," Academic Press , vol. 2, 1981.
[48] D.-Y. Chen, N.-C. Hsiao, and Y.-M. Wu, "The Earthworm Based Earthquake Alarm Reporting System in Taiwan," Bulletin of the Seismological Society of America, Vol. 105, No. 2a, April 2015
[49] C. Panagiotakis, E. Kokinou, and F. Vallianatos, "Automatic P-Phase Picking Based on Local-Maxima Distribution," IEEE Transactions On Geoscience and Remote Sensing, vol. 46, no. 8, August 2008
[50] D. Spallarossa, G. Ferretti, D. Scafidi, C. Turino, and M. Pasta, "Performance of the RSNI-Picker," Seismological Research Letters, vol 85, 2014
[51] C. Baillard,W. C. Crawford, V. Ballu, C. Hibert, and A. Mangeney, "An Automatic Kurtosis-Based P- and S-Phase Picker Designed for Local Seismic Networks," Bulletin of the Seismological Society of America, Vol. 104, No. 1, pp. 394 409, February 2014
[52] H. Zhang, C. Thurber, and C. Rowe, "Automatic P-Wave Arrival Detection and Picking with Multiscale Wavelet Analysis for Single-Component Recordings," Bulletin of the Seismological Society of America, Vol. 93, No. 5, pp. 1904-1912, October 2003
[53] Y.-M. Wu and, T.-L. Teng, "A Virtual Subnetwork Approach to Earthquake Early Warning," Bulletin of the Seismological Society of America, vol. 92, no. 5, pp. 2008-2018, June. 2002.
[54] J. Springer, "Principal Component Analysis," Springer Series in Statistics, 2002
[55] R.W. Preisendorfer and C.D. Mobley, "Principal Component Analysis in Meteorology and Oceanography," Amsterdam: Elsevier, 1988
[56] E. Beltrami, "Sulle funzioni bilineari," Giornale di Mathematiche di Battaglini, vol. 11, pp. 98 106, 1873
[57] M.C. Jordan, "Memoire sur les Formes Bilineaires," J. Math. Pures Appl, vol. 19, pp 35 54, 1874
[58] R.A. Fisher and W.A. Mackenzie, "Studies in crop variation II," The manurial response of di erent potato varieties, J. Agri. Sci., vol. 13, pp 311 320, 1923
[59] K. Pearson, "On lines and planes of closest t to systems of points in space," Phil. Mag. (6), vol. 2, pp 559 572, 1901
[60] H. Hotelling, "Analysis of a complex of statistical variables into principal components," J. Educ. Psychol., vol. 24, pp 417 441, pp 498-520, 1933
[61] E.H. Bryant and W.R. Atchley, "Multivariate Statistical Methods: Within Group Covariation," Stroudsberg: Halsted Press, 1975
[62] C.R. Rao, "The use and interpretation of principal component analysis in applied research," Sankhya A, vol. 26, pp 329-358, 1964
[63] R Frisch, "Correlation and scatter in statistical variables," Nordic Statist. J, vol. 8, pp 36-102, 1929
[64] L.L. Thurstone, "Multiple factor analysis," Psychol. Rev., vol. 38, pp 406-427, 1931
[65] H. Hotelling, "Simplified calculation of principal components," Psychometrika, vol. 1, pp 27-35, 1936
[66] M.A. Girshick, "Principal components," J. Amer. Statist. Assoc., vol. 31, pp 519-528, 1936
[67] M.A. Girshick, "On the sampling theory of roots of determinantal equations," Ann. Math. Statist., vol. 10, pp 203-224, 1939
[68] T.W. Anderson, "Asymptotic theory for principal component analysis," Ann. Math. Statist., vol. 34, pp 122-148, 1963
[69] J.C. Gower, "Some distance properties of latent root and vector methods used in multivariate analysis," Biometrika, vol. 53, pp 325 338, 1966
[70] J.N.R. Je ers, "Two case studies in the application of principal component analysis," Appl. Statist., vol. 16, pp 225-236, 1967
[71] R.W. Preisendorfer and C.D. Mobley, "Principal Component Analysis in Meteorology and Oceanography", Amsterdam: Elsevier, 1988
[72] M. Shyu, S. Chen, K. Sarinnapakorn, and L. Chang, "A Novel Anomaly Detection Scheme Based on Principal Component Classifier," in Proceedings of the IEEE Foundations and New Directions of Data Mining Workshop, in conjunction with the Third IEEE International Conference on Data Mining (ICDM '03), Melbourne, Florida, USA, November 2003, pp. 172 179.
[73] K. Ramah, H. Ayari, and F. Kamoun, "Tra c Anomaly Detection and Characterization in the Tunisian National University Network," in Networking 2006, Cobimbra, Portugal, May 2006, pp. 136-147.
[74] Knowlege Discovery and Data Mining Cup 1999 Data. [Online]. Available: http://www.ics.uci.edu/ kdd/databases/kddcup99/kddcup99.html
[75] L. Malagon-Borja, O. Fuentes, Object detection using image reconstruction with PCA, Image Vis. Comput. (2007), doi:10.1016/j.imavis.2007.03.004
[76] R. Gnanadesikan and J. R. Kettenring, "Robust Estimates, Residuals, and Outlier Detection with Multiresponse Data," Biometrics, Vol. 28, No. 1, Special Multivariate Issue, pp. 81-12, March 1972
[77] H. Hassani, "Singular Spectrum Analysis: Methodology and Comparison," Journal of Data Science 5, pp. 239-257, March 2007
[78] N. Halko, P.-G. Martinsson, J. A. Tropp, "Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions," SIAM Rev., Survey and Review section, Vol. 53, num. 2, pp. 217-288, June 2011

QR CODE