臺灣博碩士論文加值系統

　　在現代「知識社會」中，基本的經濟資源將不再是資本、自然資源或勞力，而是「知識」，知識員工也將成為其中的要角。若想成功地將個人知識轉成組織知識，知識管理將扮演一個關鍵性的角色。吾人可將知識概分為內隱知識及外顯知識，尤以個人化之內隱知識更為組織中的重要資產，因此若能將組織中高度個人化的知識保存，對組織之知識管理將有莫大助益。個人化內隱知識之取得為知識管理之門檻，近年來隨著人工智慧、軟式運算與資訊科技的快速進步，要實現高階智慧型決策支援系統已非難事。因此本研究以探勘個人化內隱知識為出發點，並以財報分析專家之內隱知識為實證對象進行研究。對財報分析專家而言，財務報表分析是一項複雜且耗時的非結構性工作，專家的決策模式是影響財務報表分析成效的重要關鍵，然而專家之決策評定具有易受主、客觀環境影響而顯現不明確與不確定之特性，因此若能探勘出專家之決策模式，則能使專家之決策評定更客觀與明確。
　　本研究擬提出一整合型分析模式，結合知識擷取及知識探勘兩種分析方法，其中知識擷取採用大聲思考法與口語草稿分析法，擷取專家之決策模式並將各公司之財務資訊建置成案例庫；知識探勘則結合模糊分群法、模糊推論系統及基因演算法與退火神經網路之結合，並進一步分析此案例庫，探勘出專家之模糊決策知識法則，並將此結果提供予專家進行檢視與驗證。本研究所建構之模糊知識庫系統，亦可提供專家檢視與修正其本身決策模式之機會。

In the “knowledge society” era, the knowledge plays a more important role than the capital, natural resources, and labor in an organization. How one turns one’s personal knowledge into organizational knowledge is one of the most crucial issues of knowledge management. Knowledge can be generally categorized into tacit knowledge and explicit knowledge, each of which has its significance in an organization. Although the personal tacit knowledge is difficult to formalize, recent progresses in artificial intelligence, soft computing, and database technologies have made the research of utilizing data-driven model analysis in extracting tacit knowledge more and more encouraging. In this study, we are devoted to the study of discovering the decision knowledge of an expert in financial statement analysis. The analysis task of financial statement has been shown complicated and unstructured in nature and the decision model of an expert is prone to imprecise and uncertain. For this, we apply the over-whelming fuzzy modeling, which has been well-studied in engineering and scientific areas.
We propose an integrated scheme toward modeling the tacit decision knowledge of the expert. The scheme is composed of two major steps: knowledge acquisition and knowledge discovery. In the knowledge acquisition step, a verbal protocol analysis is performed to acquire the mental decision model of the expert and to construct the decision cases. Then the knowledge discovery is conducted to build up a fuzzy knowledge base system by mining the decision cases using fuzzy clustering, fuzzy inference system, genetic algorithm and simulated annealing. The discovered tacit knowledge is further validated and reviewed by the expert so that the decision model can be enhanced.

目錄 .................................................. i
圖目錄 ................................................ iii
壹、緒論 .............................................. 1
一、研究動機與目的 ................................... 1
二、研究方法 ......................................... 5
三、研究貢獻 ......................................... 7
貳、文獻回顧 .......................................... 9
參、研究架構 .......................................... 17
一、知識擷取(knowledge acquisition) .................. 18
二、知識探勘(knowledge discovery) .................... 19
(一)模糊知識庫系統(fuzzy knowledge-base system) ..... 19
1. 模糊分群法(fuzzy clustering) ................... 20
(1) GK演算法(GK algorithm) ...................... 20
(2) 模糊分群驗證(fuzzy clustering validation) ... 22
a. S函數(S-function) ........................ 22
b.分割密度(partition density) ............... 22
c. silhouette coefficient ................... 23
2. 分群投影(cluster projection) ................... 24
3. 模糊規則之推導 ................................. 25
4. 規則化簡(rule simplification) .................. 26
(1) 相似度衡量 .................................. 26
(2) 合併模糊集合 ................................ 29
(3) 模糊規則之化簡及移除 ........................ 30
5. 模糊知識庫系統(fuzzy knowledge-base system) .... 31
(1) 模糊集合 .................................... 32
(2) 模糊推論系統 ................................ 33
a. 模糊化 (fuzzification) ................... 34
b. 模糊知識庫 (knowledge base) .............. 34
c. 模糊推論(fuzzy inference) ................ 35
d. 反模糊化(defuzzification) ................ 36
(二)基因演算法(genetic algorithm) ................... 36
1. 參數編碼 ....................................... 39
2. 產生初始族群 ................................... 39
3. 定義適應函數 ................................... 39
4. 基本運算子 ..................................... 40
(1) 複製(reproduction) .......................... 40
a. 輪盤式選擇(roulette wheel selection) ..... 40
b. 競爭式選擇(tournament selection) ......... 41
(2) 交配(crossover) ............................. 41
(3) 突變(mutation) .............................. 42
5. 基因演算法之演算流程 ........................... 42
6. 基因演算法之特性 ............................... 43
(三)退火神經網路(simulated annealing) ............... 44
(四)基因演算法結合退火神經網路(GASA) ................ 46
(五)知識驗證與檢視 .................................. 47
肆、實證研究 .......................................... 49
一、問題描述 ......................................... 49
二、資料來源 ......................................... 51
三、知識擷取－VPA之實證 .............................. 51
四、知識探勘 ......................................... 53
(一)Sugeno模式之模糊知識庫系統 ...................... 54
(二)Mamdani模式之模糊知識庫系統 ..................... 56
五、實證結果分析 ..................................... 59
伍、結論與建議 ........................................ 68
一、研究結論 ......................................... 68
二、未來研究方向 ..................................... 69
參考文獻70

1.李昇暾、薛兆亨，「以基因演算法擷取個別財報分析專家之模糊決策知識」，第十屆全國資訊管理學術研討會, 1999/11
2.張本法，「結合類神經網路與基因演算法於水下聲源訊號辨識系統之研究」，中原大學資訊工程學系碩士論文，2000.。
3.陳安斌、黃銘信、王信文，「運用指數型模糊群聚法於認購權證避險策略之研究」，Mar 1999, 中華管理評論, Nov. 2, No. 2, pp. 67-90.
4.盧芸玲、劉瑞瓏，「智慧型代理人在企業知識管理中之應用與展望」，國科會計畫編號NSC88-2213-E-216-003與NSC89-2213-E-216-003,中華大學資訊管理學系。
5.薛兆亨，李昇暾，「以機率型類神經網路建立財報分析專家之決策模式－以短期償債能力分析為例」，東吳經濟商學學報第26期，民國八十八年九月，pp. 87-107.
6.謝育勳，「員工知識管理資訊系統之設計與發展─資料採擷技術之應用」，國立中央大學 人力資源管理研究所碩士論文，民國八十八學年度。
7.Ackley, D. H. and Hinton, G. E. and Sejnowski, T. J. “A Learning Algorithm for Boltzman Machines”, 1985 Cognitive Science, 9, 147-169.
8.Alam, P., Booth, D., Lee, K. and Thordarson, T. “The Use of Fuzzy Clustering Algorithm and Self-Organizing Neural Networks for Identifying Potentially Failing Banks: an Experimental Study”, Expert Systems with Applications 18 (2000) 185-199.
9.Bezdek, J.C. “Fuzzy Mathematics in Pattern Classification”, Ph. D. Thesis, Applied Math. Center, Cornell University, Ithaca (1973).
10.Carlos A. P.-R., Moshe S. “A Fuzzy-Genetic Approach to Breast Cancer Diagnosis”, Preprint submitted to Elsevier Science, 17 Dec., 1998.
11.Chen, M.-S. and Wang, S.-W. “Fuzzy Clustering for Optimizing Fuzzy Membership Functions”, Fuzzy Sets and Systems 103 (1999) 239-254.
12.Dhar, V. and Sten, R., Intelligent Decision Support Methods, The Science of Knowledge Work, Prentice Hall, Inc., 1997
13.Duda, R. and Hart, P. “Pattern Classification and Scene Analysis”, Wiley, New York (1973).
14.Dunn, J.C. “A Fuzzy Relative of the ISODATA Process and its Use in Detecting Compact”, Well separated Clusters. Journ. Cybern. 3 (1974), 95-104.
15.Editorial, “The Role of Artificial Intelligence in Knowledge Management”, Knowledge-Based Systems 13 (2000) 135-139.
16.Eom, K. B. “Fuzzy Clustering Approach in Unsupervised Sea-Ice Classification”, Neurocomputing 25 (1999) 149-166.
17.Genther, H. and Glesner, M. “Advanced Data Pre-processing using Fuzzy Clustering Techniques”, Fuzzy Sets and Systems 85 (1997) 155-164.
18.Jang, J.-S. R. and Sun, C.-T. and Mizutani, E. “Neuro-Fuzzy and Soft Computing－A Computational Approach to Learning and Machine Intelligence”, Prentice-Hall, 1997.
19.Jin, Y., Seelen, W. V. and Sendhoff, B. “Extracting Interpretable Fuzzy Rules from RBF Neural Networks”, 2000 Institute for Neuroinformatic, IR-INI 2000-02.
20.Kaufman, L. and Rousseeuw, P. J. “Finding Groups in Data－An Introduction to Cluster Analysis”, John Wiley & Sons, Inc. 1990.
21.Kennedy, R. L. et. al. (1998), “Solving Data Mining Problems through Pattern Recognition”, Unica Technologies, Inc.
22.Kim, C. N., Chung, H. M., and Paradice, D. B. (1997), “Inductive Modeling of Expert Decision Making in Loan Evaluation: A Decision Strategy Perspective,” Decision Support Systems, 21, pp. 83-98.
23.Kirkpatrick, S., Gelatt, C. D. and Vecchi, M. P. “Optimization by Simulated Annealing”, Science, 220 (4598):671-680, May 1983.
24.Klawonn, F. and Kruse, R. “Clustering Methods in Fuzzy Control. In: W. Gaul, D. Pfeifer (eds.), From Data to Knowledge: Theoretical and Practical Aspects of Classification”, Data Analysis and Knowledge Organization. Springer-Verlag, Berlin (1995), 195-202.
25.Klawonn, F. and Kruse, R. “Derivation of Fuzzy Classification Rules from Multidimensional Data. In: G.E. Lasker, X. Liu (eds.). Advances in Intelligent Data Analysis.”,The International Institute for Advanced Studies in Systems Research and Cybernetics, Windsor, Ontario (1995), 90-94
26.Klawonn, F. and Keller, A. “Fuzzy Clustering and Fuzzy Rules” Proc. 7th International Fuzzy Systems Association World Congress (IFSA’97) Vol. I, Academia, Prague (1997), 193-198.
27.Krishnapuram, R. and Kim, J. “A Note on the Gustafson-Kessel and Adaptive Fuzzy Clustering Algorithms”, IEEE Transactions on Fuzzy Systems, Vol. 7, No. 4, August 1999.
28.Li, S.-T., Shue, L.-Y., and Shiue, W., "The Development of a Decision Model for Liquidity Analysis," Expert Systems with Applications, Vol. 19, No. 4, 2000, pp. 271-278.
29.Liebowitz, J. “Knowledge Management and its Link to Artificial Intelligence”, Expert Systems with Applications 20 (2001) 1-6.
30.Lim, M. H., Rahardja, S. and Gwee, B. H. “A GA Prardigm for Learning Fuzzy Rules”, Fuzzy Sets and Systems 82 (1996) 177-186.
31.Medasani, S., Kim, J. and Krishnapuram, R. “An Overview of Membership Function Generation Techniques for Pattern Recognition”, International Journal of Approximate Reasoning 19 (1998) 391-417.
32.Motohide, T., etc. “Extraction of Quantified Fuzzy Rules from Numerical Data”, IEEE, 2000.
33.Noh, J.B. and Lee, K.C. and Kim, J.K. etc., “A Case-Based Reasoning Approach to Cognitive Map-Driven Tacit Knowledge Management”, Expert Systems with Applications 19 (2000) 249-259.
34.Payne, J., Braunstein, M. and Carroll, J., “Exploring Predecisional Behavior: An Alternative Approach to Decision Research”, Organizational Behavior and Human Performance, (1978) pp. 17-44.
35.Setnes, M. “Supervised Fuzzy Clustering for Rule Extraction”, 1999 IEEE International Fuzzy Systems Conference Proceedings, August 22-25, 1999, Seoul, Korea.
36.Setnes, M. and Babuska, R., etc. “Similarity Measures in Fuzzy Rule Base Simplification”, IEEE Transactions on Systems, Man, and Cybernetics－Part B: Cybernetics, Vol. 28, NO. 3, June 1998.
37.Shaw, M. J., Subramaniam, C., Tan, G. W. and Welge, M. E. “Knowledge Management and Data Mining for Marketing”, Decision Support Systems 31 (2001) 127-137.
38.Sugeno, M. and Yasukawa, T. “A Fuzzy-Logic-Based Approach to Qualitative Modeling.”, IEEE Transaction on Fuzzy Systems 1 (1993), 7-31.
39.Sun, R-L., Weigand, and Dayhoff, J.E. “Evolving Population-Based Search Algorithms through Thermodynamic Operation: Dynamic System Design and Intergration”, Ph. D. Thesis Report, Institute for Systems Research, 1995.
40.Wang, C.-H. and Hong, T.-P., Tseng, S.-S. “Genetic-Fuzzy Knowledge-Integration Strategies”, IEEE, 1998.
41.Yu, P.-T. and Own, C.-M. “Mining Time Series Data with Fuzzy Association Rules”, Fuzzy Sets and Systems, 109. (1998) 217-240.
42.Zadeh, L.A. "Fuzzy sets," Inf. Control, Vol. 8, pp. 338-353, 1965.