Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/17632
標題: 基因演算法應用在動態資料的分類規則探勘
Classification Rule Mining for Dynamic Data Using Genetic Algorithm
作者: 龐偉智
Parng, Wei-Jyle
關鍵字: Classification Rule Mining
分類規則的探勘
G enetic Algorithms
Dynamic Data Model
基因演算法
動態型資料
出版社: 應用數學系所
引用: 參考文獻 一、中文部分 (一) 圖書 曾憲雄,蔡秀滿,蘇東興,曾秋蓉,王慶堯 (2005)。資料探勘。台北市:旗標出版股份有限公司。 (二) 期刊論文 謝千慧(2004)。一個適用於概念漂移資料串流探勘法之研究。(碩士論文,臺南師範學院,2004)。全國博碩士論文資訊網,92NTNTC395007。 林豐澤, “演化式計算上篇:演化式演算法的三種理論模式”, 智慧科技與應用統計學報,第三卷,第一期,pp. 1-28, 2005 年 6 月。 (三) 網路資源 朱家德(2004) 。 纇神經網路(Neural Network)的簡介。線上檢索日期:2005年12月16日。網址: http://home.pchome.com.tw/home/jia_der_chu_1974/course/ann/ann.htm 二、 西文部分 (一) Books Han, J., Kamber, M. ( 2001). Data Mining Concepts and Techniques. Morgan Kaufmann Publishers. (二) Journal Articles Branke, J. T. Kausler, C. Schmidth, and H. Schmeck. (2000). A multi-population approach to dynamic optimization problems. In Proc. of the Adaptive Computing in Design and Manufacturing, pages 299–308. Branke, J. (1999). Memory enhanced evolutionary algorithms for changing optimization problems. In Proc. of the 1999 Congress on Evolutionary Computation, volume 3, pages 1875–1882. Codreanu, I.; Codreanu, C.; Obreja, V.V.N.; Avram, M.(2004). Use of genetic algorithms in heat transfer problems. Semiconductor Conference, 2004. CAS 2004 Proceedings. 2004 International. Volume 2, 2004 Page(s):499 - 502 vol.2 . Digital Object Identifier 10.1109/SMICND.2004.1403058 Cordelia, L.P., De Stefano, C., Fontanella, F., Marcelli, A. (2005). Evolutionary Computation. The 2005 IEEE Congress on Volume 2, 2-5 Sept. 2005 Page(s):1149 - 1155 Vol. 2 Digital Object Identifier 10.1109/CEC.2005.1554820 . Eick Christoph F., Jong Daw, (1993) . Learning Bayesian Classification Rules through Genetic Algorithms. ACM 0-89791-626-3/83/0011 . Guan, S. U. , & ZhuCollard, F. (2005). An incremental approach to genetic-algorithms-based classification, Systems, Man and Cybernetics, Part B, IEEE Transactions on Volume 35, Issue 2, Apr 2005 Page(s):227 - 239 Digital Object Identifier 10.1109/TSMCB.2004.842247 Hulten, G., Spencer, L., Ddmingos, P. (2001). “Mining Time-Changing Data Streams,” In Proc. 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA., pp. 97-106, Aug. Kimura, S., Sonoda, K., Yamane, S., Matsumura, K., Hatakeyama, M. (2005). Inference of genetic networks using neural network models. Evolutionary Computation. The 2005 IEEE Congress on Volume 2, 2-5 Sept. 2005 Page(s):1738 - 1745 Vol. 2 Digital Object Identifier 10.1109/CEC.2005.1554898 Klinkenberg, R. , Renz, I. (1998). “Adaptive Information Filtering: Learning in The Presence of Concept Drifts,” In M. Sahami, M. Craven, T. Joachims, and A. McCallum, editors, Workshop Notes of the ICML-98 Workshop on Learning for Text Categorization, pp. 33–40, Menlo Park, CA., AAAI Press. Kunchcva, L. I. (2000). Fuzzy Classifier Design, Physica-Verlag, Hcidelbcrg . Liu, B. Abbas, H.A, McKay, B. (2003). Classification Rule Discovery with Ant Colony Optimization. IAT 2003. IEEE/WIC International Conference on 13-16 Oct. 2003 Page(s): 83 - 88 Noda, E., Feritas, A.A., Lopes. H.S. (1999). Dioscvering intresting rules with a genetic algorithm. CEC99 Quinlan, J. R. (1996) Bagging, Boosting, and C4.5. In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 725-730. Rokach, L., Maimon, O. (2005). Top-down induction of decision trees classifiers - a survey. Systems, Man and Cybernetics, Part C, IEEE Transactions on.Volume 35, Issue 4, Nov. 2005 Page(s):476 - 487 Sarker, R., Abbass, H., & Newton, C. (2002). Introducing data mining and knowledge discovery. In R. sarker & H. Abbass & C. Newton (Eds.), Heuristics and Optimisation for Knowledge Discovery (pp. 1-23): Idea Group Publishing. Shao, C.; Bouchard, M. (2003). Efficient classification of noisy speech using neural networks Signal Processing and Its Applications, 2003. Proceedings. Seventh International Symposium on Volume 1, 1-4 July 2003 Page(s):357 - 360 vol.1 Digital Object Identifier 10.1109/ISSPA.2003.1224714 Tan, K.C.; Tay, A.; Lee, T.H.; Heng, C.M. (2002). Mining multiple comprehensible classification rules using genetic programming Evolutionary Computation, 2002. CEC ''02. Proceedings of the 2002 Congress on Volume 2, 12-17 May 2002 Page(s):1302 - 1307 Digital Object Identifier 10.1109/CEC.2002.1004431. Thede, S.M., (2004). An Introduction To genetic Algorithms. ACM SIGIR Conference, Philadelphia, USA, 115-123. Vavak, F. and Fogarty, T. C. (1996). A comparative study of steady state and generational genetic algorithms for use in nonstationary environments. In T. C. Fogarty, editor, AISB Workshop on Evolutionary Computing, Lecture Notes in Computer Science, volume 1143, pages 297–304. Springer. Yang, L., Widyantoro, D.H.,Ioerger, T., Yen, J. (2001). An entropy-based adaptive genetic algorithm for learning classification rules. Evolutionary Computation, 2001. Proceedings of the 2001 Congress on , Volume: 2 , 27-30 May 2001 Pages:790 - 796 vol. 2. Yang, S. (2005). Memory-Based Immigrants for Genetic Algorithms in Dynamic Environments . GECCO’05, June 25–29, 2005, Washington, DC, USA. Copyright 2005 ACM 1-59593-010-8/05/0006
摘要: 在現實的環境中經常會有一些經常性變動或隨時間變動的動態型資料模式,而一般分類規則的演算法大多數是解決簡單,較固定型的靜態資料,當資料不再是簡單固定型的靜態資料,而是連續型,較複雜的動態資料,則傳統分類規則演算法已無法有效面對與解決,因此探索動態型資料模式中分類規則的有用知識,是一項高難度且重要的研究要的議題。 本研究主要是探勘動態型分類規則的問題,假設新的訓練資料(Training Data)以穩定的速率下增加,提出時間序列式基因演算法,以基因演算法為基礎,並配合啟發式搜尋(Heuristic Search method)的方法,以時間軸為序列劃分出不同的階段,每個階段單獨做分類規則基因演算法,並且會依照環境的變化,採用記憶體基礎的遷移式方法,以適應新的環境,實驗的結果顯示本研究的方法適用動態資料之分類。
In real situation, there frequently happens some time-variant dynamic data model. General classification rule algorithms are mostly used to solve simple and steady static data; however, when the data is no longer simple and fixed one, but is consecutive and more complicated dynamic data, the traditional classification classification rule algorithms can not tackle it anymore. Therefore, it's a tough and important issue to study the useful knowledge of the classification rule in the dynamic data model. This study mainly aimed to investigate classification rule with dynamic data model. Suppose that the new Training Data decreases within a stable input system, and we propose time sequence axial genetic algorithms, which was based upon genetic algorithms, and it was cooperated with Heuristic Search method. It is divided into different stages with time sequence axial. Each phase itself is individually done with genetic algorithms with classification rule mining and with the variation of the environment, we use memory-based immigrants schemes to adapt to new stage changes. The result of this research reveals that the method is applicable to dynamic data model
URI: http://hdl.handle.net/11455/17632
其他識別: U0005-2508200614154300
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2508200614154300
Appears in Collections:應用數學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.