跳到主要內容

臺灣博碩士論文加值系統

(44.213.60.33) 您好!臺灣時間:2024/07/22 16:20
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:安範哲
研究生(外文):Fajar Abdurrahman
論文名稱:感知器的學習和一維CNN於震測圖形識別
論文名稱(外文):Perceptron learning and 1-D CNN for seismic pattern recognition
指導教授:黃國源黃國源引用關係
指導教授(外文):Huang,Kou-Yuan
口試委員:王榮華蘇豐文劉長遠
口試委員(外文):Wang, Jung-HuaSoo, Von-WunLiou,Cheng-Yuan
口試日期:2020-07-22
學位類別:碩士
校院名稱:國立交通大學
系所名稱:電機資訊國際學程
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:100
中文關鍵詞:感知器學習規則學習速率參數地震圖瑞克小波地震異常
外文關鍵詞:perceptronlearning rulelearning-rate parameterseismogramRicker waveletseismic anomaly
相關次數:
  • 被引用被引用:0
  • 點閱點閱:151
  • 評分評分:
  • 下載下載:13
  • 收藏至我的研究室書目清單書目收藏:0
感知器被採用於Ricker小波分類並檢測震測圖中的震測異常,在感知器的訓練中使用了三種學習規則來解決決策邊界,最佳學習率參數被推導出來,學習率參數的上下限也被推導出來,它可以提供當參數在範圍內時學習可以收斂,歸一化學習規則也被推導出來,結合學習規則,一種融合學習規則被提出來。在實驗中,將這些規則應用於模擬震測圖中的震測異常檢測,並比較收斂速度,融合學習規則具有最快的收斂速度,並被應用於真實震測圖,震測異常可以成功地被檢測出來。它可以改善震測解釋。
深度學習發展至今已能更準確地分辨圖形,其中一維 CNN(1-D CNN)可以被應用在辨別震測圖中的小波。文中推導了運用梯度下降法的向後傳遞的學習的數學公式 1-D CNN 被用於模擬與實際的震測圖。模型以震測訊號中兩個零點間的波形為輸入,並將其分 為 20-Hz 小波、30-Hz 小波、與雜訊這三類,分類結果顯示小波可以被分類,並且震測異常也可以被偵測出來。
Perceptron is adopted to classify the Ricker wavelets and to detect the seismic anomaly in seismogram. Three learning rules are used in the training of perceptron to solve the decision boundary. The optimal learning-rate parameter is derived. The lower and upper bounds of learning-rate parameter are derived. It can provide that the learning can converge when the parameter is within the range. Normalized learning rule is derived also. Combining learning rules, a fusion learning rule is proposed. In the experiments, these rules are applied to the detection of seismic anomaly in the simulated seismogram and to compare the convergence speed. The fusion learning rule has the fastest convergence and is applied to the real seismogram. The seismic anomaly can be detected successfully. It can improve the seismic interpretation.
Deep learning can classify the patterns more accurately in recent development. One-dimensional convolution neural network (1-D CNN) is applied to classify the wavelets in the seismogram. The mathematical formulas of backpropagation learning by gradient descent method are derived. 1-D CNN is applied to simulated and real seismograms. The input of 1-D CNN model is a waveform between two zero-crossings from the seismic signal. The input waveforms are classified into three classes: 20-Hz wavelet, 30-Hz wavelet, and noise. The results show that the wavelets can be classified successfully. The seismic anomaly can be detected.
摘 要 i
ABSTRACT ii
ACKNOWLEDGEMENT iii
TABLE OF CONTENTS iv
LIST OF TABLES vi
LIST OF FIGURES vii
CHAPTER 1 INTRODUCTION 1
1.1 Statement of the Problem 1
1.2 Generation of Simulated Seismogram 1
1.3 Proposed Methods 4
1.4 Thesis Organization 6
CHAPTER 2 SEISMIC SIGNAL CLASSIFICATION USING PERCEPTRON WITH DIFFERENT LEARNING RULES 7
Abstract 7
2.1 Introduction 7
2.2 Feature Generation in Seismic Signal 10
2.3 Perceptron Learning Rules 13
2.4 Experiments in Seismograms 21
CHAPTER 3 1-D CNN FOR WAVELET CLASSIFICATION IN SEISMOGRAM 38
Abstract 38
3.1 Introduction 38
3.2 Forward Computation in 1-D CNN 39
3.3 Backpropagation Learning in 1-D CNN 46
3.4 Experiments in Seismograms 61
CHAPTER 4 COMPARISON OF CLASSIFICATION METHODS AND CONCLUSIONS 84
4.1 Discussion of Comparison with Other Methods 84
4.2 Conclusions 89
REFERENCES 92
A. References of Chapter 1
[1] C. H. Chen, "Seismic pattern recognition," Geoexploration, vol.16, pp. 133-146, 1978.
[2] K. R Anderson, "Automatic analysis of microearthquake network data," Geoexploration, vol. 16, pp. 159-175, 1978.
[3] P. Bois, "Autoregressive patterns recognition applied to the delimitation of oil and gas reservoirs," Geophys. Prospecting, vol. 28, pp. 572-592,1980.
[4] C. H. Chen, "A review of geophysical signal analysis and recognition," Proc. of the 2nd Intl. Symp. on Computer-Aided Seismic Analysis and Discrimination, pp. 144-152, 1981.
[5] K. R Anderson, "Syntactic analysis of seismic waveforms using augmented transition network grammars," Geoexploration, vol. 20, pp. 161-182, 1982.
[6] H. H. Liu and K. S. Fu, "A syntactic approach to seismic pattern recognition," IEEE Trans. Patt. Anal. Mach. Intel., vol. PAMI-4, pp. 136-140, March, 1982.
[7] K. Y. Huang and K. S. Fu, "Decision theoretic pattern recognition for the classification of Ricker wavelets and the detection of bright spots," 52nd annual meeting of the Society of Exploration Geophysicists (SEG), Dallas, pp. 222-224, 1982.
[8] C. H. Chen, "Pattern analysis of acoustical and seismic events," IEEE Proc. of the 3rd Intl. Symp. on Computer-Aided Seismic Analysis and Discrimination, The Catholic University of America, Washington, D.C., June 15-17, pp. 114-118, 1983.
[9] P. Bois, "Some application of pattern recognition to oil and gas exploration," IEEE Trans. Geosci. Remote Sensing, vol. GE-21, pp. 416-426, 1983.
[10] K. Y. Huang and K.S. Fu, "Detection of bright spots in seismic signal using tree classifiers," Geoexploration 23, pp. 121-145, 1984.
[11] F. Aminzadeh and S. Chatterjee, “Applications of clustering in exploration seismology,” Geoexploration 23, pp. 147-159, 1984.
[12] K. Y. Huang and K. S. Fu, "Decision-theoretic approach for classification of Ricker wavelets and detection of seismic anomalies," IEEE Trans. on Geoscience and Remote Sensing, pp. 118-123, March 1987.
[13] S. Yair and I. Nathan, “Classification of seismic signals by integrating ensembles of neural networks,” IEEE Trans. on Signal Processing, vol. 46, no. 5, pp. 1194 – 1201, May 1998.
[14] K. Y. Huang, "Neural networks for seismic principal components analysis,” IEEE Trans. on Geoscience and Remote Sensing, vol.37, no.1, pp. 297-311, 1999.
[15] K. Y. Huang, K. J. Chen, J. D. You, and A. C. Tung, “Hough transform neural network for pattern detection and seismic applications,” Neurocomputing, vol. 71, pp. 3264-3274, Oct. 2008.
[16] K. J. Huang, K. Y. Huang, I. C. Chen, and L. K. Wang, “Simulated annealing for sequential pattern detection and seismic applications,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 12, pp. 4849-4859, December 2014.
[17] C. H. Chen, Ed., Handbook of Pattern Recognition and Computer Vision, 6th edition, World Scientific, April 2020.
[18] K. Y. Huang and Wen-Hsuan Hsieh, “Cellular neural network for seismic pattern recognition,” in C. H. Chen, ed., Handbook of Pattern Recognition and Computer Vision, 6th edition, Singapore: World Scientific, April 2020.
[19] M. B. Dobrin and C.H. Savit, Introduction to Geophysical Prospecting, 4th ed., New York : McGraw Hill Book Co., 1988.
[20] C. E. Payton, Ed., Seismic Stratigraphy-Applications to Hydrocarbon Exploration, AAPG Memoir 26, Tulsa, OK: Amer. Assn. Petroleum Geologists, 1977.
[21] D. E. Rumelhart, G. E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in D.E. Rumelhart and J. L. McClelland, eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Cambridge, MA.: MIT Press, pp. 318-362, 1986.
[22] D. E. Rumelhart, G. E. Hilton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, pp. 533-536, 1986.
[23] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, “Gradient-based learning applied to document recognition,” Proc. of the IEEE, vol. 86, no. 11, pp. 1-46, 1998.
[24] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
[25] N. J. Nilsson, The Mathematical Foundations of Learning Machines, California: Morgan Kaufmann Publishers Inc., 1990.
[26] K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed., Academic Press, 1990.
[27] K. S. Fu, Syntactic Pattern Recognition Application, New Jersey: Prentice-Hall, Inc., 1982.
[28] S. Haykin, Neural Networks and Learning Machines, 3rd ed., New Jersey: Pearson Education Inc., 2009.
[29] M. Basu and Q. Liang, “The fractional correction rule: a new perspective,” Neural Networks 11, pp. 1027 – 1039, April 1998.
[30] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (Adaptive Computation and Machine Learning), Cambridge, MA: MIT Press, pp. 326 – 339, 2016.
[31] Y. Liu, Y. Zhong, J. Zhao, A. Ma and Q. Qin, "Scene semantic classification based on scale invariance convolutional neural networks," 2017 IEEE Intl’ Geosci. and Remote Sensing Symposium (IGARSS), Fort Worth, TX, pp. 4754-4757, 2017, doi: 10.1109/IGARSS.2017.8128064.
[32] X. Li, W. Li, X. Xu and W. Hu, "Cell classification using convolutional neural networks in medical hyperspectral imagery," 2017 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdu, 2017, pp. 501-504, doi: 10.1109/ICIVC.2017.7984606.

B. References of Chapter 2
[1] C. H. Chen, "Seismic pattern recognition," Geoexploration, vol.16, pp. 133-146, 1978.
[2] K. R Anderson, "Automatic analysis of microearthquake network data," Geoexploration, vol. 16, pp. 159-175, 1978.
[3] P. Bois, "Autoregressive patterns recognition applied to the delimitation of oil and gas reservoirs," Geophys. Prospecting, vol. 28, pp. 572-592, 1980.
[4] C. H. Chen, "A review of geophysical signal analysis and recognition," Proc. of the 2nd Intl. Symp. on Computer-Aided Seismic Analysis and Discrimination, pp. 144-152, 1981.
[5] K. R Anderson, "Syntactic analysis of seismic waveforms using augmented transition network grammars," Geoexploration, vol. 20, pp. 161-182, 1982.
[6] H. H. Liu and K. S. Fu, "A syntactic approach to seismic pattern recognition," IEEE Trans. Patt. Anal. Mach. Intel., vol. PAMI-4, pp. 136-140, March, 1982.
[7] K. Y. Huang and K. S. Fu "Decision theoretic pattern recognition for the classification of Ricker wavelets and the detection of bright spots," 52nd annual meeting of the Society of Exploration Geophysicists (SEG), Dallas, pp. 222-224, 1982.
[8] C. H. Chen, "Pattern analysis of acoustical and seismic events," IEEE Proc. of the 3rd Intl. Symp. on Computer-Aided Seismic Analysis and Discrimination, The Catholic University of America, Washington, D.C., June 15-17, pp. 114-118, 1983.
[9] P. Bois, "Some application of pattern recognition to oil and gas exploration," IEEE Trans. Geosci. Remote Sensing, vol. GE-21, pp. 416-426, 1983.
[10] K. Y. Huang and K.S. Fu, "Detection of bright spots in seismic signal using tree classifiers," Geoexploration 23, pp. 121-145, 1984.
[11] F. Aminzadeh and S. Chatterjee, “Applications of clustering in exploration seismology,” Geoexploration 23, pp. 147-159, 1984.
[12] K. Y. Huang and K. S. Fu, "Decision-theoretic approach for classification of Ricker wavelets and detection of seismic anomalies," IEEE Trans. on Geoscience and Remote Sensing, pp. 118-123, March 1987.
[13] S. Yair and I. Nathan, “Classification of seismic signals by integrating ensembles of neural networks,” IEEE Trans. on Signal Processing, vol. 46, no. 5, pp. 1194 – 1201, May 1998.
[14] K. Y. Huang, "Neural networks for seismic principal components analysis,” IEEE Trans. on Geoscience and Remote Sensing, vol.37, no.1, pp. 297-311, 1999.
[15] K. Y. Huang, K. J. Chen, J. D. You, and A. C. Tung, “Hough transform neural network for pattern detection and seismic applications,” Neurocomputing, vol. 71, pp. 3264-3274, Oct. 2008.
[16] K. J. Huang, K. Y. Huang, I. C. Chen, and L. K. Wang, “Simulated annealing for sequential pattern detection and seismic applications,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 12, pp. 4849-4859, December 2014.
[17] C. H. Chen, Ed., Handbook of Pattern Recognition and Computer Vision, 6th edition, Singapore: World Scientific Co., April 2020.
[18] K. Y. Huang and Wen-Hsuan Hsieh, “Cellular neural network for seismic pattern recognition,” in C. H. Chen, ed., Handbook of Pattern Recognition and Computer Vision, 6th edition, Singapore: World Scientific Co., April 2020.
[19] M. B. Dobrin and C.H. Savit, Introduction to Geophysical Prospecting, 4th ed., , New York: McGraw Hill Book Co., 1988.
[20] C. E. Payton, Ed., Seismic Stratigraphy-Applications to Hydrocarbon Exploration, AAPG Memoir 26, Tulsa, OK: Amer. Assn. Petroleum Geologists, 1977.
[21] D. E. Rumelhart, G. E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in D.E. Rumelhart and J. L. McClelland, eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Cambridge, MA.: MIT Press, pp. 318-362, 1986.
[22] D. E. Rumelhart, G. E. Hilton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, pp. 533-536, 1986.
[23] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, “Gradient-based learning applied to document recognition,” Proc. of the IEEE, vol. 86, no. 11, pp. 1-46, 1998.
[24] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
[25] N. J. Nilsson, The Mathematical Foundations of Learning Machines, California: Morgan Kaufmann Publishers Inc., 1990.
[26] K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed., Academic Press, 1990.
[27] K. S. Fu, Syntactic Pattern Recognition Application, New Jersey: Prentice-Hall, Inc., 1982.
[28] S. Haykin, Neural Networks and Learning Machines, 3rd ed., New Jersey: Pearson Education Inc., 2009.
[29] M. Basu and Q. Liang, “The fractional correction rule: a new perspective,” Neural Networks 11, pp. 1027 – 1039, April 1998.
[30] M. T. Tanner, F. Koehler, and R. E. Sheriff, "Complex seismic trace analysis," Geophysics, vol. 44, pp. 1041-1063, 1979.
[31] A. Gholamy and V. Kreinovich, “Why Ricker wavelets are successful in processing seismic data,” IEEE Symposium on Computational Intelligence for Engineering Solutions, pp. 11 – 16, 2014.
[32] K. Y. Huang, J. D. You, and F. Abdurrahman, “Seismic signal classification using perceptron with different learning rules,” recommended for publication subject to revisions to IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020.

C. References of Chapter 3
[1] M. B. Dobrin and C.H. Savit, Introduction to Geophysical Prospecting, 4th ed., New York: McGraw Hill Book Co., 1988.
[2] C. E. Payton, Ed., Seismic Stratigraphy-Applications to Hydrocarbon Exploration, AAPG Memoir 26, Tulsa, OK: Amer. Assn. Petroleum Geologists, 1977.
[3] K. Y. Huang and K. S. Fu, "Decision-theoretic approach for classification of Ricker wavelets and detection of seismic anomalies," IEEE Trans. on Geoscience and Remote Sensing, pp. 118-123, March 1987.
[4] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. of IEEE, pp. 1 – 46, November 1998.
[5] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (Adaptive Computation and Machine Learning), Cambridge, MA: MIT Press, pp. 326 – 339, 2016.
[6] Y. Liu, Y. Zhong, J. Zhao, A. Ma and Q. Qin, "Scene semantic classification based on scale invariance convolutional neural networks," 2017 IEEE Intl’ Geosci. and Remote Sensing Symposium (IGARSS), Fort Worth, TX, pp. 4754-4757, 2017, doi: 10.1109/IGARSS.2017.8128064.
[7] X. Li, W. Li, X. Xu and W. Hu, "Cell classification using convolutional neural networks in medical hyperspectral imagery," 2017 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdu, 2017, pp. 501-504, doi: 10.1109/ICIVC.2017.7984606.
[8] Z. Zhang, “Derivation of backpropagation in convolutional neural network (CNN),” Technical Report: University of Tennessee, October 2016.

D. References of Chapter 4
[1] K. Y. Huang and K.S. Fu, "Detection of bright spots in seismic signal using tree classifiers," Geoexploration 23, pp. 121-145, 1984.
[2] K. Y. Huang and K. S. Fu, "Decision-theoretic approach for classification of Ricker wavelets and detection of seismic anomalies," IEEE Trans. on Geoscience and Remote Sensing, pp. 118-123, March 1987.
[3] K. Y. Huang and K. S. Fu, "Syntactic pattern recognition for the recognition of bright spots," Pattern Recognition, vol. 18, no. 6, pp. 421-428, 1985.
[4] K. Y. Huang and D. R. Leu, “Syntactic pattern recognition for wavelet clustering in seismogram,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 7, pp. 2453 – 2461, July 2019. DOI: 10.1109/JSTARS.2019.2908690
[5] V. I. Levenshtein, “Binary codes capable of correcting deletions, insertions and reversals,” Sov. Phys. Dokl. 10, pp. 707-710, 1966.
[6] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” Proc. of the Fifth Annual Workshop on Computational Learning Theory, pp. 144-152, July 1992.
[7] T. Friess, N. Cristianini, and ICG. Campbell, “The Kernel-Adatron algorithm: a fast and simple learning procedure for support vector machines,” Proc. of the Fifteenth Intl. Conference on Machine Learning (ICML), pp. 188-196, 1998.
[8] K.Y. Huang and F. Abdurrahman, “1D convolutional neural network for wavelet classification in seismogram,” The 32nd IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP), Taitung, Taiwan, Aug. 25-27, 2019.
[9] Z. Zhang, “Derivation of backpropagation in convolutional neural network (CNN),” Technical Report: University of Tennessee, October 2016.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top