在影像辨識及處理與資料分析及探勘的領域中，非監督式（unsupervised)群集技術都扮演很重要的角色。許多傳統常用的非階層式（nonhierarchical）非監督群集演算法都必須預先輸入一些參數，例如群數或起始群中心位置等，但是在應用上群集的數量常是很難事先預知的。本論文提出一個結合模糊與非階層式群集兩種方法優點的兩階段非監督式模糊及機率群集演算法，利用第一階段模糊群集的目標函數最小及資料重建後誤差值最小的概念，找出最佳模糊因子，決定群集的個數及其群中心的位置，再利用第二階段的機率(EM)群集演算法決定最佳的分類結果。根據測試資料庫的實驗結果，本論文所提出的方法測試的正確率至少都有94%以上，相較於其他方法是一個比較穩定的方法。

Unsupervised clustering is an important technique in pattern recognition, image processing, data analysis and data mining. There are many traditional nonhierarchical clustering methods have been used widely, but the most problems are that they need a priori information about the number of clusters and the best position of the initial centers. The fuzzy clustering has also been adopted in popular. In addition, the weighting exponent (fuzzifier) is another predefined variable which significantly affects the result of fuzzy clustering. In this paper, we proposed a two-stage unsupervised fuzzy and probabilistic clustering algorithm. In first stage, we use the concept of minimization of the error of the reconstructed dataset and the objective function, in order to decide the weighting exponent、the number of clusters and the position of the candidate centers. In second stage, we decide the final optimal clusters by probabilistic (EM) algorithm. According to the results for testing dataset, the accuracy of the proposed algorithm is higher than 94%, and is more stable and efficient than other traditional methods.

[1] S.S. Khan, A. Ahmad, “Cluster center initialization algorithm for K-means clustering”, Pattern Recognition Letters, Vol. 25, pp1293-1302, Aug. 2004
[2] J.C. Noordam, W.H.A.M. van den Broek, L.M.C. Buydens, “Multivariate image segmentation with cluster size insensitive Fuzzy C-means”, Chemometrics and Intelligent Laboratory System, Vol. 64, pp 65-78, Oct. 2002
[3] C.W. Tao, “Unsupervised fuzzy clustering with multi-center clusters”, Fuzzy Sets and Systems, Vol. 128, pp 305-322, June 2002
[4] F. Okeke, A. Karnieli, “Linear mixture model approach for selecting fuzzy exponent value in fuzzy c-means algorithm”, Ecological Informatics, Vol. 1, pp 117-124, 2006
[5] L. Kaufman and P.J. Rousseeuw, “Finding Groups in Data: an Introduction to Cluster Analysis”, John Wiley & Sons, 1990.
[6] M. Ester, H.P. Kriegel, J. Sander and X. Xu, “A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise”, Knowledge Discovery and Data Mining, pp.226-231, AAAI Press, 1996
[7] C.F. Chen and J.M. Lee, “The Validity Measurement of Fuzzy C-means Classifier for Remotely Sensed Images”, 22nd Asian Conference on Remote Sensing, pp 208-211, 2001
[8] J. Yu, Q. Cheng, H. Huang, “Analysis of the Weighting Exponent in the FCM”, Systems, Man and Cybernetics, Part B, IEEE Transactions on, Vol. 34, pp 634-639, Feb. 2004
[9] P.J. Deer, P. Eklund, “A Study of Parameter Values for a Mahalanobis Distance Fuzzy Classifier”, Fuzzy Sets and Systems, Vol. 137, July 2003
[10] J.B. MacQueen, “Some Methods for Classification and Analysis of Multivariate Observations”, Proceedings of 5nd Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1, Berkeley, Calif.: University of California Press, pp. 281-297, 1967
[11] J.C. Bezdek and N.R. Pal, “Some new indexes of cluster validity”, Systems, Man and Cybernetics, Part B, IEEE Transactions on, Vol. 28, pp 301-315, June 1998
[12] M. Ankerst, M. Breunig, H.P. Kriegel and J. Sander, “Optics: Approach to Spatial Data Mining”, VLDB’97, 1997
[13] W. Wang, J. Yang, R. Muntz, “STING: A statistical Information Grid Approach to Spatial Data Mining”, VLDB’97
[14] G. Sheikholeslami, S. Chatterjee and A. Zhang, “WaveCluster: A Multi-Resolution Clustering Approach for Very Large Spatial Databases”, VLDB98, 1998
[15] H. H. Muhammed, “Unsupervised Fuzzy Clustering and Image Segmentation Using Weighted Neural Networks”, Image Analysis and Processing, 2003.Proceedings. 12th International Conference on, pp 308-313, Sept. 2003
[16] G.H. Ball and D.J. Hall, “A novel method of data analysis and pattern classification”, Technical report, Stanford Research Institute, Menlo Park, CA.
[17] T. Hofmann and J. Puzicha, “Statistical models for co-occurrence data”, MIT Artificial Intelligence Lab., Technical Report
[18] 羅積玉, 多元統計分析方法與應用, 科技圖書股份有限公司