本論文提出了兩個不同的支持向量選擇機制，並藉此機制發展了以支持向量為基礎的群聚演算法。在第一個支持向量的選擇方法中，可以表現出資料在高維空間分佈的特徵如高維空間中點與點之間的距離，各點於特徵向量的映射距離，及空間重心與點之間的夾角等均被考量進來，同時此方法也參考了點與點之間的相關係數。雖然支持向量的選擇結果較佳，但運算複雜度卻未能大幅度降低。因此，本論文發展了另一套改良後的支持向量選擇機制。改良後的方法僅運用了點與點在高維空間中的相關係數及距離。無論是初步提出的方法或是改良後的方法，都是以去除內部點為首要目標，一旦去除內部點，外部點即可視為邊界點去建構出各群集的輪廓線。本論文中，三組標竿資料被用來檢視所提出方法的有效性，經由模擬結果可以發現，本論文提出的方法在支持向量選擇上的結果是良好的，而且運算時間相較於原始支持向量群聚演算法來得短許多。本論文最後以生醫訊號做為實際應用，可以看出提出方法的有效性，也歸納出一些在生醫訊號或是其他實際生活中於分類問題上會遇到的困難。

This thesis presents two support vector selection schemes for clustering analysis. In the preliminary approach, many perspectives on observing mapped data distribution in the feature space are considered. These include feature distances and eigen-mapped distances of data points, and the included angle and cross-correlation coefficient of each data vector in the feature space. Although the clustering results for benchmark datasets are acceptable, its computational time cost is still far from satisfaction. Reducing computational complexity is the main goal of this study. An efficient support vector selection scheme has been developed to achieve such an objective. In the proposed support vector selection algorithm, cross-correlation coefficients and feature distances are employed for eliminating interior points. In the proposed algorithm, eliminating as much as interior points is the prior task to conquer. After data point elimination, the remaining points are considered as the support vectors for constructing cluster contours. In the simulation results on benchmark datasets, support vector selection results are satisfactory, and computation time is much less than that of SVC. Finally, the performance of the proposed support-vector-based clustering algorithm is evaluated by an application on sleep stage classification. The experimental results have not only validated the effectiveness of the proposed algorithm, but also revealed some challenges that are usually encountered in real-world applications.

[1] R. Agarwal, and J. Gotman, “Computer-assisted sleep staging,” IEEE Transactions on Biomedical Engineering, vol. 48, pp.1412-1423, 2001.
[2] M. Ankerst, M. Breunig, H. P. Kriegel, and J. Sander, “OPTICS: Odering points to identify the clustering structure,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1999, pp. 49–60.
[3] T. Ban and S. Abe, “Spatially chunking support vector clustering algorithm,” Proc. of 2004 IEEE International Joint Conference on Neural Networks, 2004, pp.413-418.
[4] L. Bao and S. S. Intille, “Activity Recognition from User-annotated Acceleration Data,” Springer, Pervasive Computing, vol. 3001, pp. 1-17, 2004.
[5] G. Baudat and F. Anouar, “Generalized discriminant analysis using a kernel approach,” Neural Computation, vol. 12, no. 10, pp. 2385-2404, 2000.
[6] M. Belkin, and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Computation, vol. 15, pp. 1373-1396, 2003.
[7] A. Ben-Hur, D. Horn, H. T. Siegelmann, and V. Vapnik, “A support vector clustering method,” in Proc. of Int. Conf. on Pattern Recognition, vol. 2, pp. 724-727, 2000.
[8] A. Ben-Hur, D. Horn, H. T. Siegelmann, and V. Vapnik, “Support vector clustering,” J. Machine Learning Research, vol. 2, pp. 125-137, 2001.
[9] J. Caffarel, G. J. Gibson, J. P. Harrison, C. J. Griffiths and M. J. Drinnan, “Comparison of manual sleep staging with automated neural network-based analysis in clinical,” Medical and Biological Engineering and Computing, vol. 44, pp. 105-110, 2006
[10] J.-H. Chiang and P.-Y. Hao, “A new kernel-based fuzzy clustering approach: Support vector clustering with cell growing,” IEEE Trans. on Fuzzy Systems, vol. 11, no. 4, 2003.
[11] E. K. P. Chong and S. H. Żak, An Introduction to optimization, Second Edition, New York: John Wiley & Sons, Inc. (Wiley-Interscience Series), 2001.
[12] C. Cortes and V. Vapnik, “Support-vector network,” Machine Learning, vol. 20, pp. 273–297, 1995.
[13] I. S. Dhillon, Y. Guan, B. Kulis, “Kernel k-means: spectral clustering and normalized cuts,” in Proc. of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2004, pp. 551-556.
[14] I. Dhillon, Y. Guan, and B. Kulis, “A unified view of kernel k-means, spectral clustering and graph cuts,” Technical Report TR-04-25, Univ. of Texas at Austin, 2005.
[15] L. G. Doroshenkov, V. A. Konyshev, and S. V. Selishchev, “Classification of human sleep stages based on EEG processing using hidden Markov models,” Biomedical Engineering, vol. 41, no. 1, pp. 25-28, 2007.
[16] S. Guha, R. Rastogi, and K. Shim, “ROCK: A robust clustering algorithms for categorical attributes,” in Proc. of IEEE Conf. on Data Engineering, 1999, pp.512–521.
[17] H Hotelling, “Analysis of a complex of statistical variables into principal components,” Journal of Educational Psychology, vol. 24, pp. 417, 1933.
[18] C. Iber, S. Ancoli-Israel, A. Chesson, and S. F. Quan, The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, 1st ed: Westchester, IL: American Academy of Sleep Medicine, 2007.
[19] A. K. Jain, R. P.W. Duin, and J. Mao, “Statistical pattern recognition: A review,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 4-37, 2000.
[20] J.-M. Jolion, P. Meer, and S. Bataouche, “Robust clustering with applications in computer vision,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 13, pp. 791-802, 1991.
[21] D.-W. Kim, K. Y. Lee, D. Lee, and K. H. Lee, “Evaluation of the performance of clustering algorithms in kernel-induced feature space,” Pattern Recognition, vol. 38, no. 4, pp. 607-611, 2005.
[22] R. Krishnapuram and C. P. Freg, “Fitting an unknown number of lines and planes to image data through compatible cluster merging,” Pattern Recognition, vol. 25, pp. 385-400, 1992.
[23] M.H. Kryger, T. Roth, W.C. Dement, Principles and Practice of Sleep Medicine, 2nd ed., 1994.
[24] S.-H. Lee and K. M. Daniels, “Gaussian kernel width generator for support vector clustering,” Advances in Bioinformatics and its applications, 2004, pp. 151-162.
[25] J. Lee and D. Lee “An improved cluster labeling method for support vector clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, pp. 461-464, 2005.
[26] J. Lee, “Dynamic characterization of cluster structures for robust and inductive support vector clustering,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 28, pp. 1869-1874, 2006.
[27] S.-H. Lee and K. M. Daniels, “Cone cluster labeling for support vector clustering,” in Proc. of the 6th SIAM Conference on Data Mining, 2006, pp. 484-488.
[28] K.-R. Muller, S. Mika, G. Ratsch, K. Tsuda, and B. Scholkopf, “An introduction to kernel-based learning algorithms,” IEEE Trans. Neural Networks, vol. 12, no.2, pp. 181-201, 2001.
[29] J. Saketha Nath and S. K. Shevade, “An efficient clustering scheme using support vector methods,” Pattern Recognition, vol. 39, no. 8, pp. 1473–1480, 2006.
[30] E. Oropesa, C. Hans, J. Marc, “Sleep stage classification using wavelet transform and neural network,” International Computer Science Institute, 1999.
[31] S. R. Pandi-Perumal, L. K. Seils, L. Kayumov, M. R. Ralph, A. Lowe, H. Moller, and D. F. Swaab, “Senescence, sleep, and circadian rhythms” Ageing Research Reviews, vol. 1, no. 3, pp. 559–604, 2002.
[32] J. Park, X. Ji, H. Zha, and R. Kasturi, “Support vector clustering combined with spectral graph partitioning,” in Proc. of the 17th International Conference on Pattern Recognition, vol. 4, 2004, pp. 581-584.
[33] M. R. Widyanto and H. Hartono, “Angle decrement based gaussian kernel width generator for support vector clustering,” Asian Journal of Information Technology, vol. 7, no. 8, pp. 388-393, 2008.
[34] A. Rechtschaffen, A. Kales, “A manual of standardized terminology and scoring system for sleep stages of human sleep,” University of California, LA: Brain Information Service/Brain Research Institute, 1968.
[35] B. Schölkopf, A. Smola, and K.-R. Müller, “Nonlinear component analysis as a kernel eigenvalue problem,” Neural Computation, vol. 10, pp. 1299-1319, 1998.
[36] B. Schölkopf, S. Mika, C. J. C. Burges, P. Knirsch, K.-R. Müller, G. Ratsch, and A. J. Smola, “Input space versus feature space in kernel-based methods” IEEE Trans. Neural Network, vol. 10, no. 5, pp. 1000-1017, 1999.
[37] P. E. Shrout and J. L. Fleiss, “Intraclass correlations: Uses in assessing rater reliability,” Psychological Bulletin, vol. 86, no. 2, pp. 420-428, 1979.
[38] P. B. Simpson, S. Mehotra, G. D. Lange, and J. T. Russell, “High density distribution of endoplasmic reticulum proteins and mitochondria at specialized Ca2+ release sites in oligodendrocyte processes,” The Journal of Biological Chemistry, vol. 272, no. 36, pp. 22654-22661, 1997.
[39] B.-Y Sun and D.-S. Huang, “Support vector clustering for multiclass classification problems,” The Congress on Evolutionary Computation, 2003, pp.1480-1485.
[40] D. Tax and R. Duin, “Support vector domain description,” Pattern Recognition Letters, vol. 20, pp. 1191-1199, 1999.
[41] M. G. Terzano, and P. Liborio, “Origin and significance of the cyclic alternating pattern (CAP),” Sleep Medicine Reviews, vol. 4, no. 1, pp. 101-123, 2000.
[42] S Wang, J Yang, N Chen, X Chen, and Q Zhang, “Human Activity Recognition with User-free Accelerometers in the Sensor Networks,” IEEE Int. Conf. Neural Networks and Brain, vol. 2, pp. 1212- 1217, 2005.
[43] J.-S. Wang, and J.-C. Chiang, “A cluster validity measure with a hybrid parameter search method for support vector clustering algorithm,” Pattern Recognition, vol. 41, no. 2, pp. 506-520, 2008.
[44] L. C. Young, B. G. Campling, T. Voskoglou-Nomikos, S. P. C. Cole, R. G. Deeley, and J. H. Gerlach, “Expression of Multidrug Resistance Protein-related Genes in Lung Cancer: Correlation with Drug Response,” Clinical Cancer Research, vol. 5, pp. 673–680, 1999.
[45] T. Zhang, R. Ramakrishnan, and M. Linvy, “BIRCH: An efficient data clustering method for very large databases,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1996, pp.103–114.
[46] D.-Q. Zhang and S.-C. Chen, “A novel kernelized fuzzy C-means algorithm with application in medical image segmentation,” Artificial Intelligence in Medicine, vol. 32, pp. 37-50, 2004.