臺灣博碩士論文加值系統

本篇的論文目的在於探討資料分群的結果，特别地，我們想要研究fuzzy c-means (FCM)和possibilistic c-means(PCM)的影響，並且組合他們，在基於樣板的shell clustering上。基於樣板的shell clustering是執行特殊幾何形狀偵測的叢集演算法。使用在shell clustering上的FCM和PCM曾發表過許多研究。然而，FCM和PCM有他們的缺點。例如， FCM的結果容易被雜訊影響，而PCM易於產生重疊的群。
我們特別感興趣的，即是在探討將FCM和PCM演算法組合過後，是否能對shell clustering的分群達到更好的成果。在此我們引用了兩個文獻上的組合演算法，possibilistic fuzzy c-means (PFCM) 和improved possibilistic c-means (IPCM)。在實驗結果中，發現到混合性的叢集演算法PFCM和IPCM套用在樣板理念上後，在偵測複雜圖形或是雜訊資料時，較FCM和PCM來的有益，我們也發現到不同的混合性叢集演算法含有不同的特性，在做叢集分群時能夠更有幫助。

This goal of this thesis is to investigate the results of data clustering. Specifically, we want to study the effect of fuzzy c-means (FCM) and possibilistic c-means (PCM), as well as their combinations, in template-based shell clustering. Template-based shell clustering is the process of detecting clusters of particular geometrical shapes through clustering algorithms. The use of FCM and PCM in shell clustering has appeared in many research. However, both FCM and PCM have their shortcomings. For example, the results of FCM are highly affected by noise, and PCM tends to produce overlapping clusters.
We are particularly interested in whether the combination of FCM and PCM algorithms can improve the results of shell clustering. Here we use two combinational algorithms in the literature, possibilistic fuzzy c-means (PFCM) and improved possibilistic c-means (IPCM). Our results indicate that IPCM and PFCM have better shape detection results than FCM and PCM when used with template-based shell clustering of complex or noisy data. We also discover that different combination methods have different properties that are helpful in clustering.

摘要.............................................................................................................................................i
Abstract......................................................................................................................................ii
誌謝...........................................................................................................................................iii
目錄...........................................................................................................................................iv
圖例...........................................................................................................................................vi
表格..........................................................................................................................................vii
第一章 簡介..............................................................................................................................1
1.1 研究動機.....................................................................................................................1
1.2 論文結構.....................................................................................................................3
第二章 文獻縱覽......................................................................................................................4
第三章 將各類演算法套用至樣板理念..................................................................................7
3.1 點為雛形的C-means叢集演算法...............................................................................7
3.1.1 FCM和PCM......................................................................................................7
3.1.2 混合性叢集演算法..........................................................................................9
3.2 基於樣板的shell clustering.......................................................................................10
3.3 將樣板套用至FCM、PCM、PFCM和IPCM上.......................................................12
第四章 混合性叢集演算法的分析........................................................................................16
4.1 雜訊的影響(noise)....................................................................................................18
4.2 可能重複偵測的實驗...............................................................................................23
4.3 叢集個數與偵測效率...............................................................................................27
4.4 η值的分析..................................................................................................................37
第五章 結論............................................................................................................................45
參考文獻..................................................................................................................................47

[1] R.O. Duda and P.E. Hart, Pattern Classification and Scene Analysis, New York: John Wiley & Sons, 1973.
[2] A.K. Jain and R.C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, N.J.: Prentice Hall, 1988.
[3] R.N.Dave and S.Bhamidipati, "Application of fuzzy shell-clustering algorithm to recognize circular shapes in digital images", Proc. Third Annual IFSA World Congress, pp. 238-241, 1989.
[4] R.N. Dave, "Fuzzy shell-clustering and application to circle detection in digital images", Int’l J. Gen. Syst., vol. 16, pp. 343-355, 1990.
[5] R. N. Dave and K. J. Patel, “Fuzzy ellipsodial-shell clustering algorithm and detection of ellipsoidal shapes,” Proc. SPIE Conf: Intelligent Robots and Computer Esion IX: Algorithms and Techniques, vol. 1381, pp. 320-333, 1990
[6] R.N. Dave and K. Bhaswan, "Adaptive fuzzy C-shells clustering and detection of ellipses", IEEE Trans. Neural Networks, vol. 3, pp. 643-662, 1992.
[7] F. Hoeppner, "Fuzzy shell clustering algorithms in image processing: fuzzy c-rectangular and 2-rectangular shells", IEEE Trans. Fuzzy Systems, vol. 5, pp. 599-613, 1997.
[8] X.-B. Gao,W.-X. Xie, J.-Z. Liu, and J. Li, "Template based fuzzy c-shells clustering algorithm and its fast implementation", Proc. IEEE Int'l Conf. Signal Processing, pp. 1269-1272, 1996.
[9] Wang, T, "Possibilistic Shell Clustering of Template-Based Shapes", IEEE Trans. Fuzzy Systems, vol. 17, pp. 777-793, 2009
[10] J.C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithms, New York: Plenum, 1981.
[11] R. Krishnapurum and J.M. Keller, "A possibilistic approach toclustering", IEEE. Trans. Fuzzy Systems, vol. 1, pp. 98-110, 1993.
[12] N.R. Pal, K. Pal, J.M. Keller, and J.C. Bezdek, "A possibilistic fuzzy c-means", IEEE Trans. Fuzzy Systems, vol. 13, pp. 517-530, 2005.
[13] J. Zhang and Y. Leung, “Improved possibilistic C-means clustering algorithms,” IEEE Trans. Fuzzy Systems., vol. 12, pp. 209–217, 2004.
[14] I. Gath and D. Hoory, "Fuzzy clustering of elliptic ring-shaped clusters", Pattern Recognition Letters, vol. 16, pp. 727-741, 1995.
[15] N. R. Pal, K. Pal, and J. C. Bezdek, “A mixed c-means clustering model,” IEEE Int’l Conf. Fuzzy Systems, Spain, pp. 11–21, 1997.
[16] R. Krishnapurum, O. Nasraoui, and H. Frigui, "The fuzzy c spherical shells algorithm: A new approach", IEEE Trans. Neural Networks, vol. 3, pp. 663-671, 1992.
[17] I. Gath and D. Hoory, "Detection of elliptic shells using fuzzy clustering: application to MRI images", Proc. Int'l Conf. Pattern Recognition, vol. 2, pp. 251-255, 1994.
[18] X.-H. Wu and J.-J. Zhou, “Possibilistic fuzzy c-means clustering model using kernel methods,” Proc. Int’l Conf. Comput. Intell. Model., Control Autom., pp. 465–470, 2005.
[19] A. Guill’en, I. Rojas, J. Gonz’alez, H. Pomares, L.J. Herrera, O. Valenzuela, and A. Prieto. "A Possibilistic Approach to RBFN Centers Initialization." Lecture Notes in Computer Science, vol. 3624, pp. 174–183, 2005.
[20] D. Chen, D.-W. Cui, and C.-X. Wang, "Weighted Fuzzy C-Means Clustering Based on Double Coding Genetic Algorithm," Lecture Notes in Computer Science, vol. 4113, pp. 622 – 633, 2006.