跳到主要內容

臺灣博碩士論文加值系統

(100.28.231.85) 您好!臺灣時間:2024/11/06 16:45
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

我願授權國圖
: 
twitterline
研究生:高崇晏
研究生(外文):Shung-Yen Kao
論文名稱:機會發現與基因工程技術在遺傳演算法演化績效改良之研究
論文名稱(外文):Applied Chance Discovery and Genetic Engineering to Find the mprovement Of Genetic Algorithms
指導教授:林文修林文修引用關係
指導教授(外文):Wen-Shiu Lin
學位類別:碩士
校院名稱:輔仁大學
系所名稱:資訊管理學系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:中文
論文頁數:130
中文關鍵詞:遺傳演算法小世界現象機會發現關鍵圖基因工程深度建構區塊約略集合理論
外文關鍵詞:Genetic AlgorithmsThe Small worldChance DiscoveryKeyGraphGenetic EngineeringDeep building BlockRough set Theory
相關次數:
  • 被引用被引用:1
  • 點閱點閱:235
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
遺傳演算法有數個重要的特徵可以幫助我們解決設計上的問題,但是遺傳演算法也有其缺點,它最大的缺點就是對於比較複雜的設計問題上必須花費比較長的時間來傳遞滿意的結果。
本研究創新採用約略集合理論於Chance Discovery之研究,一般而言機會發現的主要應用科技是關鍵圖,關鍵圖的確在機會發現上扮演很重要的角色,但是關鍵圖在遺傳演算法上有其限制,其主要缺點為關鍵圖於分群時,必須由人去調整連結的門檻值,所以在分群上可能因為人為因素的介入,使得分群上過於武斷;再者,關鍵圖在判圖上也必需經由擁有特定領域知識的專家或學者,對關鍵圖進行讀圖以及解釋的動作;一個複雜度高的關鍵圖因為解釋上的困難度高,所以由人類專家來判圖往往會喪失發現機會。因為關鍵圖的這些限制本研究希望利用約略集合理論自動化分群以及決策法則的優點,來取代傳統關鍵圖在本研究上的缺失。
利用約略集合的技術來挖掘隱藏在族群染色體內的深層基因結構,再輔以基因工程的概念企圖擾亂基本遺傳演算法的演化機制,使得演化朝向半決定或決定性的方向來進行。再者,利用約略集合理論和基因工程的互動來改善傳統遺傳演算法的演化效率與效果。
從學術面上來看,本研究藉由小世界拓樸的概念運用於基因工程演算法上,加速改善傳統的遺傳演算法在演化績效上的表現,並且證明了遺傳演算法中小世界現象的存在。
在應用方面以及商業智慧上,因為改善了演算法的限制,相信在不同領域上的運用一定會有相當程度的啟發。例如證券投資領域的擇時擇股上能有更精確的表現、或者對於一些原本遺傳演算法表現不那麼傑出的領域,因為新的改良式遺傳演算法的引入,而更有顯著的成就。
Genetic Algorithms (GAs) have several important features that predestine them to solve design problems. Their main disadvantage however is the excessively long run-time is needed to delivery satisfactory results for large instances of complex design problems and without incorporating with sufficient knowledge, it does have a significant impact on the efficiency of the search for an optimal solution. The main aims of this paper are(1)to demonstrate that the effective and efficient application of the GA concept to design problem solving requires substitution of the basic GAs natural evolutionary by applying chance discovery and genetic engineering,(2) to propose and discuss rough set theory for chance discovery and genetic engineering,(3)to show how to apply the improvement of genetic algorithms to solve De Jong set of test function.
In this paper, we see whether rough set theory can be used to reveal good gene schema and use Genetic Engineering (GE) concept consists of perturbing the natural evolution of the basic GA to some degree by implementing some goal-oriented deterministic or semi-deterministic decisions.
On the intellectual level, showing the connection between rough set theory and genetic engineering to improve GAs as related pieces of the innovation puzzle is scientifically and computationally interesting. The paper goes beyond mere conjecture and show how rough set theory can work together to find effective and efficient GAs.
目 錄
頁次
表 次 vi
圖 次 viii
第壹章 緒論 1
第一節 研究背景與動機 1
第二節 研究問題 3
第三節 研究問題 4
第四節 本研究的重要性 5
第五節 論文架構與流程 6
第貳章 文獻探討 9
第一節 遺傳演算法 9
第二節 基因工程演算法 16
第三節 小世界理論 18
第四節 機會發現與關鍵圖 24
第五節 約略集合理論與折減機制 27
第六節 Schemata、Schema theorem 以及Building Block 36
第七節 本章小結 38
第參章 研究設計 39
第一節 本研究系統運作架構 39
第二節 實驗設計 51
第三節 系統效能測試 55
第肆章 實驗結果與分析 57
第一節 De Jong 五個函數實驗資料分析 57
第二節 系統效能測試 89
第三節 深度BB分析 103
第四節 機會發現路徑分析 109
第五節 分析與討論 115
第伍章 結論與建議 125
第一節 研究結論 125
第二節 研究貢獻 126
第三節 研究限制 127
第四節 後續研究與建議 128
參考文獻 129
1.Beasley, D., Bull, D.R. and Martin, R.R., An overview of genetic algorithms--Part 1: Fundamentals, University Computing 15 (2), 1993 , pp. 58-69.
2.Beasley, D., Bull, D.R. and Martin, R.R., An overview of genetic algorithms--Part 2: Research topics, University Computing 15 (4), 1993, pp. 170-181.
3.Beaubouef, T. and Lang, R., Rough set techniques for uncertainty management in automated story generation, Proceedings of the 36th Annual Conference on Southeast Regional Conference, ACM Press, New York, NY,1998, pp.326-331
4.Bruns, R., Integration of constraint solving techniques in genetic algorithms, Evolutionary Computation, IEEE International Conference on, Perth,WA , Australia, Vol. 1,1995, pp. 33-38.
5.Christiansen, F. B. and Feldman, M.W.Algorithms, genetics, and populations: The schemata theorem revisited. Complexity, 3(3),1998,pp.57–64.
6.Goldberg, D. E., Design of innovation: Lessons from and for competent genetic algorithms. Boston, MA: Kluwer Academic Publishers,2002
7.Goldberg, D. E., The design of innovation: Lessons from and for competent genetic algorithms. Norwell, MA: Kluwer Academic Publishers, 2002.
8.Goldberg, D. E., Genetic Algorithm in Search , Optimization , and Machine Learning, Addison: Wesley, 1989.
9.Goldberg, D. E., Welge, M., & Llorµa, X., DISCUS: Distributed Innovation and Scalable Collaboration In Uncertain Settings (IlliGAL Report No. 2003017). Urbana, IL: University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, 2003.
10.Goldberg, D.E., Sastry, K. and Ohsawa, Y., Discovering Deep Building Blocks for Competent Genetic Algorithms Using Chance Discovery via KeyGraphs(IlliGAL Report No.). Urbana, IL: University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, 2003.
11.Goldberg, D.E., Sastry, K. Ohsawa, Y.,Discovering Deep Building Blocks for Competent Genetic Algorithms Using Chance Discovery via Key Graphs(IlliGAL Report No. 2002026). Urbana, IL: University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, 2002.
12.Goldberg, D.E., The Design of Innovation: Lessons from and for Competent Genetic Algorithms, Volume 7 of the Kluwer Series on Genetic Algorithms and Evolutionary Computation , 2002.
13.Holland, J.H., Adaptation in Natural and Artificial Systems:an Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence, MIT Press, Cambridge, 1975.
14.Jozwiak,L. Postula,Postula,A..,Genetic engineering versus natural evolutionGenetic algorithms with deterministic operators. Journal of systems, 44, 2002, pp, 99-112
15.Llorµa, X., Goldberg, D. E., Ohsawa, Y., Ohnishi, K., Washida, Y., Tamura, H., & Yoshikawa,M.,Chances and Marketing: On-line Conversation Analysis for Creative Scenario Discussion (IlliGAL Report in preparation). Urbana, IL: University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laboratory, 2004.
16.Llora, X., Ohnishi, K. Ying-Ping Chen, Goldberg, D. E. and Welge, M.E.,Enhanced Innovation:A Fusion of Chance Discovery and Evolutionary Computation to Foster Creative Processes and Decision Making(IlliGAL Report No. 2004012). Urbana, IL: University of Illinois at Urbana-Champaign, Illinois Genetic Algorithms Laborator,2004.
17.Marchiori,M., atora,V.,Harmony in the small-world. Physica A,285, 2000, pp.539-546.
18.Mitchell, M., Forrest, S., and Holland, J. H.,The royal road for genetic algorithms: Fitness landscapes and GA performance. In Varela, F. J. and Bourgine, P., editors, Proceedings of the First European Conference on Arti.cial Life, pages 245–254, MIT Press, Cambridge, Massachusetts, 1992.
19.Ohsawa, Y., & Yachida, M.,Discover risky active faults by indexing an earthquake sequence. Proceedings of International Conference on Discovery Science, 1999.
20.Pawlak, Z., Grzymala-Busse, J., Slowinski, R. & Ziarko, W., Rough Sets, Communication of the ACM, 38(11), 1995, pp.88-95.
21.Pawlak, Z., Rough sets approach to knowledge-based decision support, European Journal of Operational Research, 99(1), 1997, pp. 48-57.
24. Pawlak, Z., Rough sets, International Journal of Computer and Information Sciences,
Vol. 11, No. 5,1982, pp. 341-356.
25. Pawlak, Z., Hard and Soft Sets, Rough Sets, Fuzzy Sets and Knowledge Discovery,W.P.
Ziarko (ed.), Springer-Verlag, London, pp. 130-135.
26. Pawlak, Z., Hard and Soft Sets,Rough Sets, Fuzzy Sets and Knowledge Discovery,W.P.
Ziarko (ed.), Springer-Verlag, London, 1994,pp. 130-135.
27. Simoudis, E., Han, J., and Fayyad, U., Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Menlo Park, AAAI Press,CA.,1996
28. Watts, D., & Strogatz, S.,Collective dynamics of `small-world' networks. Nature,
393 ,1998, pp.440-442.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊