跳到主要內容

臺灣博碩士論文加值系統

(100.28.0.143) 您好!臺灣時間:2024/07/18 08:15
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:楊松緯
研究生(外文):Sung-Wei Yang
論文名稱:強健分類法在模糊回歸分類模型上之應用
論文名稱(外文):APPLICATION OF ROBUST CLUSTERING TO THE FUZZY C-REGRESSION MODEL
指導教授:龔宗鈞
指導教授(外文):Chung-Chun Kung
學位類別:碩士
校院名稱:大同大學
系所名稱:電機工程研究所
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:2003
畢業學年度:91
語文別:英文
中文關鍵詞:雜訊分類法強健分類法M-估測子模糊回歸分類模型
外文關鍵詞:noise clusteringrobust clusteringM-estimatorFuzzy c-regression model
相關次數:
  • 被引用被引用:0
  • 點閱點閱:269
  • 評分評分:
  • 下載下載:18
  • 收藏至我的研究室書目清單書目收藏:0
摘要
Fuzzy c-regression model (FCRM) 在高維度資料點的分析中很有效率,但是,它有一些缺點,它們對於雜訊非常敏感,包括以下兩種雜訊:(1)模糊不清難以分類的,跟數個模型都很靠近的雜訊點(2)跟所有模型的距離都很遠的雜訊點。
一些具有強健性的分類方法,如Noise clustering (NC)演算法,Possibilistic C-Means (PCM) 演算法,以及結合了以上兩種演算法的N/PC1演算法,他們對於消除太遠的雜訊點有良好的效果。
首先,為了消除太遠的雜訊點對FCRM的影響,我們應用N/PC1演算法,但改善的效果不大。於是,我們將N/PC1演算法結合M-estimator理論,發現改善效果良多,在有很多太遠的雜訊點之狀況下,仍能找出很接近的模型,然而,用傳統的FCRM演算法,偏差已然甚矣。
另一方面,系統仍會受模糊不清,難分的點的影響,因此,我們根據PCM的觀點對上述的演算法做些調整,使估測出的模型更準確。

ABSTRACT
Fuzzy C-regression model (FCRM) is an efficient algorithm for clustering hyper-plane-shaped clusters, but it suffers from several drawbacks: they are very sensitive to the presence of noise, two type of reject have been included: (1) the ambiguity reject which concerns the data points which fit several models equally well; (2) the distance or error reject dealing with patterns that are far away from all the clusters, we usually named it outlier.
Some robust clustering method such as Noise clustering (NC) algorithm, Possibilistic C-Means (PCM) algorithm, and N/PC1 clustering algorithm combining NC and PCM method, have been shown that they have well performance to eliminate outlier.
First, to eliminate the outlier effect in FCRM, we applying N/PC1 algorithm, but, the improvement is not much, so, we apply the M-estimator to N/PC1 algorithm, then, the result is become much well. In the situation that many outliers exist, the algorithm still gets approaching model, while the conventional FCRM algorithm even out of rule.
In the other hand, ambiguity effect still exists, so, based on the viewpoint of PCM, we adjust the algorithm above to eliminate ambiguity effect and make better performance.

CONTENTS
ABSTRACT (IN CHINESE) I
ABSTRACT (IN ENGLISH) II
CONTENTS III
LIST OF FIGURES IV
LIST OF TABLES V
CHAPTER 1 INTRODUCTION 1
CHAPTER 2 NOISE CLUSTERING 4
2.1 Review of Fuzzy-C Means algorithm 4
2.2 Noise Clustering 5
2.3 Proof of the Noise Clustering Algorithm 8
2.4 Application of NC in Fuzzy-C Regression model 10
CHAPTER 3 PCM AND N/PC1 ALGORITHM 13
3.1 Possibilic C-Means 13
3.2 Bandwidth of a Cluster 14
3.3 Robust N/PC1 Algorithm 15
CHAPTER 4 N/PC1 ALGORITHM BASED M-ESTIMATOR 21
4.1 M-estimator 21
4.2 Application of M-Estimator in FCRM 24
4.3 A New Algorithm to Eliminate Ambiguity Effect 26
4.4 Illustrative Example 30
CHAPTER 5 CONCLUSION AND FURTHER RESEARCH 40
REFERENCES 41

REFERENCES
[1] R.N. Dave, “Characterization and detection of noise in clustering,” Pattern Recognit. Lett, vol. 12, no. 11, pp. 657—664, 1991.
[2] R.N. Dave, “Robust fuzzy clustering algorithms,” 2nd IEEE Int. Conf. Fuzzy Syst., vol.2, pp. 1281 —1286, Mar. 1993.
[3] R. Krishnapuram and J. M. Keller, “A possibilistic approach to clustering,” IEEE Trans. Fuzzy Syst., vol. 1, pp. 98—110, May 1993.
[4] R.J. Hathaway and J.C. Bezdek, “Switching regression models and fuzzy clustering,” IEEE Trans. Fuzzy Syst., vol. 1, no. 3, pp. 195-204, Aug. 1993.
[5] R.N. Dave and R. Krishnapuram, “Robust clustering methods: a unified view,” IEEE Trans. Fuzzy Syst., vol. 5, no. 2, pp. 270 —293, May 1997.
[6] K.K. Chintalapudi and M. Kam, “A noise-resistant fuzzy c means algorithm for clustering” IEEE Int. Conf. Fuzzy Systems Proceedings. vol. 2, pp. 1458 —1463, May 1998.
[7] R. Krishnapuram, and J.M. Keller “The possibilistic C-means algorithm: insights and recommendations,” IEEE Trans. Fuzzy Syst., vol. 4, no. 3, pp. 385 —393, Aug. 1996.
[8] M. Barni, V. Cappellini, and A. Mecocci, “Comments on A possibilistic approach to clustering,” IEEE Trans. Fuzzy Syst., vol. 4, no. 3, pp. 393 —396, Aug. 1996.
[9] R.N. Dave and S. Sen, “Noise clustering algorithm revisited” Fuzzy Information Processing Society, NAFIPS. Annual Meeting of the North American pp. 199 —204, Sept. 1997
[10] M. Menard, P.A. Dardignac, and V. Courboulay, “Switching regression models using ambiguity and distance rejects: application to ionogram analysis,” 15th int. conf. Pattern Recognition Proceedings. vol. 2, pp. 688 —691, Sept. 2000.
[11] Y. Cheng, “Mean shift, mode seeking, and clustering,” IEEE Trans. Pattern Anal. Machine Intel., vol. 17, no. 8, pp. 790 —799, Aug. 1995.
[12] J.-Q. Chen,Y.-G. Xi, and Z.-J. Zhang, “A clustering algorithm for fuzzy model identification,” Fuzzy Set and Systems vol. 98, no. 3, pp. 319-329, Sept. 1998.
[13] M.J. Mirza and K.L Boyer, “Performance evaluation of a class of M-estimators for surface parameter estimation in noisy range data,” IEEE Trans Robotics and Automation, vol. 9, no. 1, pp. 75 -85, Feb. 1993.
[14] A.F.G. Skarmeta, M.D. elgado, and M.A. Vila, “About the use of fuzzy clustering techniques for fuzy model identification,” Fuzzy Sets and Systems, vol. 106, pp. 179-188, Sept. 1999.
[15] E. Kim, M. Park, S. Ji, and M. Park, “A new approach to fuzzy modeling,” IEEE Trans. Fuzzy Syst., vol. 5, no. 3, pp. 328-337, Aug. 1997.
[16] D.C Hoaglin, F Mosteller, and J. W. Tukey, Understanding Robust and Exploratory Data Analysis, New York, 1982.
[17] L.X. Wang, A Course in Fuzzy Systems and Control. Prentice-Hall, 1997.
[18] M. Park, S. Ji, E. Kim, and M. Park, “A new approach to the identification of a fuzzy model,” Fuzzy Sets and Systems, vol. 104, no. 2, pp. 169-181, June 1999.
[19] J.C. Bezdek, Pattern Recognition With Fuzzy Objective Function Algorithms Plenum, New York, 1981.
[20] C.-C. Kung and C.-C. Lin, “Fuzzy c-regression model with a new cluster validity criterion,” IEEE Int. Conf. Fuzzy Syst., vol. 2, pp. 1499 —1504, May 2002.
[21] T.C Hsia, System Identification. California, Lexington, Mass.: Lexington Books, 1977.
[22] R.N. Dave and S. Sen, “Generalized noise clustering as a robust fuzzy c-M-estimators model,” North American. Conf. Fuzzy Information Processing Society, NAFIPS., pp. 256 —260, Aug. 1998
[23] R.N. Dave and R. Krishnapuram, “M-estimators and robust fuzzy clustering,” North American. Biennial Conf. Fuzzy Information Processing Society, NAFIPS, pp. 400 —404, June 1996.
[24] P. J. Huber, Robust Statistics. New York: Wiley, 1981.
[25] F. R. Hampel, E. M. Ponchotti, P. J. Rousseeuw, and W. A. Stahel, Robust Statistics: The Approach Based on Influence Functions. New York: Wiley, 1986.
[26] C. Goodall, D. C. Hoaglin, F. Mosteller, and J. W. Tukey, “M-estimator of location: An outline of the theory,” in Understanding Robust and Exploratory Data Analysis, Eds. pp. 339—403, New York: 1983.
[27] C.-C. Chuang, S.-F. Su, and S.-S. Chen, “Robust TSK fuzzy modeling for function approximation with outliers,” IEEE Trans. Fuzzy Syst., vol. 9 No. 6 pp. 810 -821, Dec. 2001.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
1. 陳麗如、楊曉芳(民91):資訊科技融入教學-以高雄市鼓山國小柴山分校的推動經驗為例。資訊與教育,第88期,29~46頁。
2. 邱貴發(民83),電腦輔助學習的理念與發展方向。教學科技與媒體,第13期,15~22頁。
3. 邱貴發、鍾邦友(民82),情境學習理論與電腦輔助學習軟體設計。臺灣教育,第 510期,23-29 頁。
4. 鄭晉昌(民82),電腦輔助學習的新教學設計觀--認知學徒制。教育資料與圖書館學,第三十一卷一期,55-66 頁。
5. 張景媛(民84),國中生建構幾何概念之研究暨統整式合作學習的幾何教學策略效果之評估。教育心理學報,第28期,99~144頁。
6. 林建任(民91 ),讓電腦與粉筆齊飛─資訊科技融入數學教學之模式與策略。師說,第167期,20~26頁。
7. 謝新傳(民91a):數學科教材編撰理念。師說,第164期,31~38頁。
8. 林建仲、鄭宗文(民90),合作式學習與問題解決-培養以問題解決為中心的網路合作學習。資訊與教育,第85期,55~62頁。
9. 吳輝遠,吳正己(民91),網際網路的教學應用-以國小數學科為例。資訊與教育,第88期,21~27頁。
10. 吳正己(民90),從英代爾e教師計劃談資訊融入教學。資訊與教育,第85期,15~21頁。
11. 沈中偉(民83),魏考斯基理論在認知策略上的應用。教學科技與媒體,第12期,23~31頁、
12. 何榮桂(民 91),台灣資訊教育的現況與發展-兼論資訊科技融入教學。資訊與教育,第87期,23~41頁。
13. 王春展(民85),情境學習理論及其在國小教育的應用。國教學報,第8期,53~72頁。
14. 蔡秉燁、鍾靜蓉(民91),資訊化教學系統設計之模型建置。資訊與教育,第90期,72~82頁。
15. 謝新傳(民91b),談以電腦為基礎的教學設計-以幾何實驗操作為例。師說,第166期,26~28頁。