臺灣博碩士論文加值系統

本研究提出一套以階層式方法與粒子群演算法為基礎之ID3模糊決策樹，稱之為「階層式粒子群模糊決策樹(Hierarchical Particle Swarm Fuzzy Decision Tree; HPS-FDT) 」演算法。而設計一個高效能的模糊分類決策樹，必須考量歸屬函數(Membership Function)調整與規則庫(Rule Base)的設計，因為複雜的歸屬函數形狀需花費大量計算時間，而過多或過少的規則將會造成使用上的不易或使精確度降低。本研究利用粒子群最佳化調整歸屬函數形狀，並且為了有效控制規則數量，使用階層式方法控制屬性、語意個數，使其規則減少至適合的數量。本研究以三個主要目標為研究主軸，分別為「提高分類正確率」、「減少分類規則數量」、「降低使用到的資料屬性個數與語意個數」。另外以IRIS與WINE兩組資料進行實驗分析後，研究發現HPS-FDT不論在模糊規則數量或資料分類準確度皆有不錯的表現。

為了說明本研究提出的HPS-FDT可以運用在實際資料中，以網路銀行之基金交易資料作為實際案例；首先，利用顧客行為變數的RFM指標模式將顧客區隔分類。獲得每個顧客分類之後，將顧客基本資料以及顧客交易資料作為HPS-FDT欲分析之顧客特徵屬性，最後分析最佳化模糊決策樹所產生的顧客規則，瞭解顧客特徵屬性與顧客分類之間的關係，讓銀行業者能藉此針對不同價值之顧客做出適當的行銷策略。

Decision tree is one of most common techniques for classification problems in data mining. Recently, fuzzy set theory has been applied to decision tree construction to improve its performance. However, how to design flexile fuzzy membership functions for each attribute and how to reduce the total number of rules and improve the classification interpretability are two major concerns. To solve the problems, this research proposes a hieratical particle swarm optimization to develop a fuzzy decision tree algorithm (HPS-FDT). In this proposed HPS-FDT algorithm, all particles are encoded using a hieratical approach to improve the efficiency of solution search. The developed HPS-FDT builds a decision tree to achieve: (1) Maximize the classification accuracy, (2) Minimize the number of rules and (3) Minimize the number of attributes and membership functions. Through a serious of benchmark data validation, the proposed HPS-FDT algorithm shows the high performance for several classification problems. In addition, the proposed HPS-FDT algorithm is tested using a mutual fund dataset provided by an internet bank to show the real world implementation possiblility. With the results, managers can make a better marketing strategy for specific target customers.

中文摘要 i
英文摘要 iii
誌謝 v
目 錄 vi
表 目 錄 viii
圖 目 錄 ix

第一章 緒論 1
1.1研究背景與動機 1
1.2問題描述 2
1.3研究目的 3
1.4研究範圍及內容 3
1.5論文架構與流程 4

第二章 文獻探討 6
2.1 資料探勘 6
2.1.1 資料探勘的定義 6
2.1.2 資料探勘之種類 7
2.1.3 決策樹 9
2.2 模糊理論 13
2.2.1模糊理論之定義 15
2.2.2 模糊系統 18
2.2.3 模糊分割之種類 23
2.2.4 模糊決策樹 25
2.3粒子群最佳化 27
2.3.1 粒子群最佳化之發展背景 28
2.3.2 粒子群最佳化之演算方法 30
2.3.3 粒子群最佳化之相關發展與應用 33
2.4 階層式基因方法 34

第三章 研究方法 38
3.1 階層式粒子群模糊決策樹(HPS-FDT) 38
3.2 歸屬函數 40
3.3 粒子最佳化演算法 41
3.3.1 階層式粒子編碼 44
3.3.2族群初始化 47
3.3.3 適應函數 47
3.3.4 維度更新與學習 49
3.3.5歸屬函數位置轉換 50
3.3.7 粒子群終止條件 54
3.4 模糊決策樹 54
3.5 模糊分類推論 57
3.6 階層式粒子群模糊決策樹(HPS-FDT)案例 60

第四章 系統實作 68
4.1系統架構 68
4.2 演算法參數設定 72
4.3 演算法效能驗證─IRIS分類問題 80
4.3.1 IRIS實驗分析 80
4.3.2 不同模糊分類方法效能比較 86
4.4演算法效能驗證─WINE分類問題 87
4.4.1 WINE實驗分析 89
4.4.2不同分類方法效能比較 94
4.4.3 探討適應函數權重參數設定對於WINE資料集之影響 95
4.5 小結 101

第五章 基金交易之顧客實例分析 102
5.1 系統流程架構 102
5.2 基金交易資料 103
5.3 RFM分析 107
5.4 顧客特徵屬性之分類 109
5.4.1語意個數之影響 110
5.4.2 訓練率之影響 111
5.4.3 實驗分析 113
5.4.4 討論 118

第六章 結論與未來研究方向 122
6.1 結論 122
6.2 未來研究方向 123

文獻 124
附錄一：RFM 模式 131
附錄二：決策樹之葉節點資訊 133

1.Abd, S. and M.-S. Lan, “A method for fuzzy rules extraction directly from numerical data and its application to pattern classification”, IEEE Trans. on Fuzzy System Vol. 3 pp. 18-28, 1995.
2.Bergh, F. van den and A. P.E. ngelbrecht., “A new Locally Convergent Particle Swarm Optimiser”, The Proceedings of IEEE International Conference on Systems, Man and Cybernetics, In Hammamet, Tunisia, Vol. 3, 2003.
3.Berry, M. J. A. and G. Linoff, Data Mining for techniques: For Marketing, Sales and Customer Support, John Wiley & Sons, Inc., Canada, 1997.
4.Cabena, P., P. O. Hadjinaian., D. R. J. Stadler., J. Verhees and A. Zanasi., Discovering Data Mining from Concept to Implementation, Prentice Hall, 1997.
5.Changchien, S.W. and T. C. Lu, “Mining association rules procedure to support on-line recommendation by customers and products fragmentation”, Expert Systems with Application, Vol.20, pp. 325-335, 2001.
6.Chen, H.-M. and S.-Y. Ho, “Designing an Optimal Eveolutionary Fuzzy Tree for Data Mining”, Proceeding of the 2001 Genetic and Evolutionary Computation Conference, In San Francisco, California, pp, 943-950, 2001.
7.Detyniechi, M. and C. Marsala., “Discovering Knowledge for Better Video Indexing based on Colors”, The 12th IEEE International Conference, Vol. 2, pp. 1177-1181, 2003.
8.Dorigo, M. and G. D. Caro., “Ant Colony Optimization: A New Meta-Heuristic”, The Proceedings of the 1999 Congress, Vol. 2, pp. 1470-1477, 1999.
9.Eberhart, R.C. and Y. Shi., “Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization”, The Proceedings of IEEE on Evolutionary Computation, Vol. 1, pp. 84-88, 2000.
10.El-Sonbaty, Y. and M.A. Ismail, “On-line Hierarchical clustering”, Pattern Recognition Letters, Vol. 19, No. 14, pp.1285-1291, 1998.
11.Esmin, A.A.A., A.R. Aoki. and G. Lambert-Torres., “Particle Swarm Optimization For Fuzzy Membership Functions Optimization”, IEEE International Conference, Vol. 3, 2002.
12.Fayyad, U., G. Piatetsky and P. Smyth, “From data mining to knowledge discovery in databases”, AI Magazine, 37-54, 1996.
13.Gaing, Z.L., “Discrete Particle Swarm Optimization Algorithm for Unit Commitment”, IEEE on Power Engineering Society General Meeting, Vol. 1, pp. 418-424. 2003.
14.Goodman, J., “Leveraging the customer database to your competitive advantage”, Direct Marketing, Vol. 12, pp. 26-27, 1992.
15.Grupe, G. H., Owrang, M. M., “Database Mining Discovering New Knowledge and Cooperative Advatage”, pp26-31, 1995.
16.Ha, Jiawei and M. Kamber , Data Mining Concepts and Techniques, Morgan Kaufmann Publishers, pp.286-289 ,2001.
17.Hu, X., R.C. Eberhart and Y. Shi “Swarm intelligence for permutation optimization: a case study of n-queens problem”, Swarm Intelligence Symposium, The Proceedings of the 2003 on IEEE (SIS '03), pp.243-246, April 2003.
18.Hughes, A. M., Strategic Database Marketing, Chicago: Probus Publishing, pp. 487-499, 1994.
19.Ishibuchi, H., K. Nozaki, and H. Tanaka, “Efficient fuzzy particion of patten space for classification problems”, Fuzzy Sets and Systems, Vol. 59, pp. 295-304, 1993.
20.Jang, D. S. and H. I. Choi, “Automatic generation of fuzzy rules with fuzzy associative memory”, Proceedings of the ISCA 5th International Conference, pp.182-186, 1996.
21.Janikow, C. Z., “A genetic algorithm for optimizing fuzzy decision trees”, Information Sciences, 89, pp.275-296, 1996.
22.Janikow, C.Z., “Fuzzy decision tree: Issues and methods”, IEEE Trans. on System, Man, and Cybernetics – Part B: Cybernetics, Vol. 28, No. 1, pp. 1-14, 1998.
23.Kahan, R., “Using database marketing techniques to enhance your one-to-one marketing initiatives”, Journal of Consumer Marketing, Vol.15, pp. 491-493 1998.
24.Karr, C. L. and E. J. Gentry, “Fuzzy control of pH using genetic algorithms”, IEEE Trans. on Fuzzy System, Vol. 1, pp. 46-53, 1993.
25.Kbir, M.A., H. Bernkirane, K. Maalmi and R. Benslimane, “Hierarchical fuzzy partition for pattern classification with fuzzy if-then rules”, Pattern Recognition Letters”, Vol. 21, No.6-7, pp.503-509, 2000.
26.Kennedy, J. and R. Eberhart., “Particle Swarm Optimization”, The Proceedings of IEEE International Conference on Neural Networks, Vol.4, pp. 1942-1948. 1995.
27.Kennedy, J. and R.C. Eberhart., “A Discrete Binary Version of the Particle Swarm Algorithm”, The Proceedings of IEEE on International Conference, Piscataway, NJ, Vol. 5, pp. 12-15. 1997
28.Kosko, B., Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ, 1992.
29.Krivda, C. D., “Unearthing underground data”, LAN, Vol.5, 42-48, 1996.
30.Kuncheva, L.I., “How good are fuzzy if-then classifiers", IEEE Trans. on System, Man, and Cybernetics-Part B, vol. 30, No.4, pp.501-509, 2000.
31.Liu B., L. Wang, Y.-H. Jin, F. Tang and D.-X. Huang, “Imporoved particle swarm Optimization combined with chaos”, Elsevier Science on Chaos, Solitons and Fractals. Vol. 25, No. 5, pp.1261-1271, 2005.
32.Lozano, J. A. and P. Larrañagem, “Applying genetic algorithms to search for the best hierachical clustering of a dataset”, Pattern Recognition Letters, Vol. 20, No. 9, pp.911-918, 1999.
33.Macus, C., “A practical yet meaningful approach to customer segmentation”, Journal of consumer marketing, Vol.5, pp. 494-504, 1998.
34.Medasani, S., J. Kim and R. Krishnapuram, “An overview of membership function generation techniques for pattern recognition”, International Journal of Approximate Reasoning, Vol.19, 391-417, 1998.
35.Mugambi, E.M., A. Hunter., G. Oatley and L. Kennedy., “Polynomial-fuzzy decision tree structures for classifying medical data”, Knowledge-Based System, Vol. 17, Issue. 2-4, pp. 81-87, 2004.
36.Mulhern, F. J., “Customer profitability analysis： measure, concentration, and research directions”, Journal of Interactive Marketing, Vol. 13, No. 1, pp. 25-40, 1999.
37.Peer, E.S., F. van den Bergh and A.P. Engelbrecht., “Using Neighbourhoods with the Guaranteed Convergence PSO”, IEEE on Swarm Intelligence Symposium, pp. 235-242, 2003.
38.Salerno, J., “Using the particle swarm optimization technique to train a recurrent neural model”, In Proceedings of the Ninth IEEE International Conference on Tools with Artificial Intelligence, pp. 45-49, 1997.
39.Salman, A. I. Ahmad and S. Al-Madani, “Particle swarm optimization for task assignment problem”, Elsevier Science on Microprocessors and Microsystems. Vol. 26, No. 8, pp. 363-371, 2002.
40.Shaw, M. J., C. Subramaniam and G. W. Tan, “Knowledge management and data mining for marketing”, Decision Support Systems, Vol.31, 127-137, 2001.
41.Shi, Y. and R. Eberhart, “A Modified Particle Swarm Optimizater”, IEEE World Congress on Computational Intelligence. pp. 69-73, 1998.
42.Shimojima, K., T. Fukuda, and Y. Hasegawa, “Virus-evolutionary genetic algorithm for fuzzy controller optimization”, In the Proc. Genetic Algorithm and Soft Computing (Studies in Fuzziness, Vol. 8), pp. 369-388, 1996.
43.Sousa,T., A. Silva and A. Neves “ Particle Swarm based Data Mining Algorithms for Classification tasks”, ELSEVIER on Parallel Computing, No.30, pp. 767-783, 2004.
44.Suh, E. H., K. C. Noh and C. K. Suh, “Customer list segmentation using the combined response model.” Expert Systems with Application, Vol.17, pp. 89-97, 1999.
45.Surmann, H., A. Kanstein, and K. Goser, “Self-organizing and genetic algorithms for an automatic design of fuzzy control and decision systems”, in Proc. EUFIT’93, pp. 1097-1104, 1993.
46.Tang, K.-S., K.-F. Man, Z.-F. Liu and S. Kwong“, Minimal fuzzy memberships and rules using hierarchical genetic algorithms”, IEEE Trans. on Industrial Electronics, Vol. 45, no. 1, pp. 162-169, 1998.
47.Tasgetiren, M.F., M. Sevkli, Y.-C. Liang and G.Gencyilmaz “Particle swarm Optimization algorithm ofr single machine total weighted tardiness problem”, IEEE of Evolutionary Computation. 2004.
48.Wang, K.P., L. Huang, C.G. Zhou and W. Pang, “Particle Swarm Optimization for Traveling Salesman Problem”, in Proceedings of the Second International Conference on Machine Learning and Cybernetics, November 2003. vol. 3, pp. 1583-1585.
49.Weber, R., “Fuzzy-ID3：A class of methods for automatic knowledge acquisition”, Proceedings 2nd International Conference on Fuzzy Logic and Neural networks, 1985, 265-268.
50.Yen, J., “Fuzzy Logic-A Modern Perspective”, IEEE Trans. on Knowledge and Data Engineering, vol. 11, no. 1, pp. 153-165, 1999.
51.Yuan, Y. and M. J. Shaw, “Induction of Fuzzy Decision Trees”, Fuzzy Sets and Systems, 69, 1995, pp. 125-139.
52.Zhang, H., X. Li, H. Li, F. Huang, “Particle swarm optimization-based schemes for resource-constrained project scheduling”, Elsevier Science on Automation in Construction. Vol. 14, No. 3, pp.393-404, 2005.
53.http://www.ics.uci.edu/~mlearn/MLRepository.html
54.王文俊，認識Fuzzy，全華科技，1997年。
55.段麗莉，「以多目標基因演算法設計高效能模糊分類器」，碩士論文，逢甲大學資訊工程學系研究所，民國92年六月。
56.張孝德與蘇木春編，機器學習類神經網模糊系統以基因演算法則，全華科技，1997年。
57.陳宏銘，「設計最佳化之演化式模糊決策樹」，碩士論文，逢甲大學資訊工程研究所，民國90年6月。
58.陳泰康，「使用智慧型基因演算設計高效能的模糊系統」，碩士論文，逢甲大學資訊工程研究所，民國89年6月。
59.陳麗君，「應用資料探勘技術於信用卡黃金級客戶之顧客關係管理」，碩士論文，元智大學工業工程與管理研究所，民國92年6月。
60.曾俊傑，「一個智慧型指紋辨識系統的設計方法論」，碩士論文，義守大學，電機工程學系研究所，民國90年6月。
61.葉思緯，「應用粒子群最佳化演算法於多目標存貨分類之研究」，碩士論文，元智大學工業工程與管理研究所，民國93年6年。
62.葉家妤，「應用最佳化模糊決策樹於顧客關係管理之研究」，碩士論文，元智大學工業工程與管理研究所，民國93年6月。
63.葉麗雯，「供應商產能有限及價格折扣下多產品多供應商最佳化採購決策」，碩士論文，元智大學工業工程與管理研究所，民國92年7月。
64.蕭豐達，「應用模糊理論與決策樹方法於空載影像建築物分類之探討」，碩士論文，朝陽科技大學，環境工程與管理系研究所，民國93年7月。
65.龔書賢，「應用基因演算法及權重項目法於關聯法則挖掘之研究」，碩士論文，元智大學工業程與管理研究所，民國92年7月。