(3.235.191.87) 您好!臺灣時間:2021/05/14 21:08
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:劉國聲
研究生(外文):Soundy Liu
論文名稱:使用智慧型基因演算法設計最佳的k-NNR分類器
論文名稱(外文):Designing an Optimal Nearest Neighbor Classifier Using an Intelligent Genetic Algorithm
指導教授:何信瑩劉嘉政
指導教授(外文):Shinn-Ying HoChia-Cheng Liu
學位類別:碩士
校院名稱:逢甲大學
系所名稱:資訊工程學系
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:2001
畢業學年度:89
語文別:中文
論文頁數:64
中文關鍵詞:k-NNR分類器智慧型基因演算法系統化推理型樣識別
外文關鍵詞:k-NNR classifierintelligent genetic algorithmssystematic reasoningpattern recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:201
  • 評分評分:
  • 下載下載:29
  • 收藏至我的研究室書目清單書目收藏:1
本論文使用一個高效能的智慧型基因演算法來設計一套最佳的k-NNR分類器,使得此分類器能具有最高的正確率,以及最小的參考集及特徵集。智慧型基因演算法整合基因演算法和直交表來找k-NNR分類器目標函數的最佳解。本演算法主要採用系統化推理的機制來取代傳統基因演算法的隨機搜尋機制,透過直交表可以有效評估親代中個別基因的貢獻程度,進而擷取最佳基因來組合成子代染色體。所以智慧型基因演算法可以有效率找到最高的分類正確率及最少的參考集及特徵集。我們採用一組SATIMAGE資料集和一組人工產生的資料集作為實驗的分類樣本,實驗結果顯示本演算法比目前相關研究中成果最好的演算法可以更有效地設計一個最佳的k-NNR分類器。

In this paper, an efficient intelligent genetic algorithm (IGA) is proposed for designing an optimal k-nearest neighbor rule (k-NNR) classifier which has a high classification accuracy, a small reference set and a small feature set. Intelligent genetic algorithm improves the conventional genetic algorithm using orthogonal experimental designs to search for an optimal solution to the problem of designing an optimal k-NNR classifier. The intelligent genetic algorithm uses a novel intelligent crossover based on orthogonal arrays (OAs). The chromosomes of the children are formed from the best combinations of the better genes representing variables of a function from their parents rather than the random combinations of parents’ genes to achieve crossover. The choice of the better genes is derived by way of a systematic reasoning approach to evaluate the individual genes based on the OA. An experimental study with the SATIMAGE data set and an artificial data set has been carried out. Experimental results show that this proposed algorithm outperforms existing algorithms in terms of the classification accuracy, the sizes of reference set and feature set.

目錄
摘要(中文) …………………………………………………….……………….….…..….I
摘要(英文)……………………………………………….………………….….……..….II
目錄……………………………………………………………….…………..………… III
圖目錄…………………………………………………….……………………..……..…V
表目錄………………………………………………………….………....……...………Ⅵ
第1章簡介1
1.1 研究動機1
1.2 研究範圍1
1.3 本文貢獻7
1.4 論文架構7
第2章相關研究8
2.1 K-NNR分類器8
2.1.1問題描述8
2.1.2 權重型目標函數9
2.1.3 降低參考集的演算法11
2.1.4 特徵選取的演算法12
2.2 直交表13
2.2.1直交表的構成155
2.2.2 因子分析188
2.3 基因演算法19
2.3.1基因演算法之定義19
2.3.2特性20
2.3.3架構20
第3章設計最佳的K-NNR分類器32
3.1智慧型基因演算法32
3.2 K-NNR 分類器設計35
3.3演算法的實作流程36
第4章實驗與效能評估40
4.1分類樣本描述40
4.4.1第一組SATIMAGE資料集40
4.1.2第二組資料人工產生的資料集41
4.2效能比較41
4.2.1 SATIMAGE分類樣本資料43
4.2.2人工產生的資料集分類樣本資料44
4.2.3 智慧型基因演算法與傳統基因演算法的收歛速度比較46
4.2.4 不同 值之比較47
4.2.5 不同分佈的資料集比較50
4.2.6 不同特徵的資料集比較52
第5章結論54
參考文獻………………………………………………………. ……. ……...……..…...55

[1]Rafael C. Gonzalez and Richard E. Woods, “Digital Image Processing,” Addison-Wesley Publishing Company, 1992.
[2]U. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy. Advances in Knowledge Discovery and Data Mining. MIT Press, Cambridge, MA, 1996.
[3]V. Honavar. Machine Learning: Principle and Application. In J. Webster, editor, Encyclopedia of Electrical and Electronics Engineering. Wiley, New York, 1998.
[4]R. Duda and P. Hart. Pattern Classification and Scene Analysis. Wiley, New York, 1973.
[5]Ludmila I. Kuncheva, Lakhmi C. Jain,“Nearest neighbor classifier: Simultaneous editing and feature selection”, Pattern Recognition Letters 20 (1999) 1149-1156.
[6]F. Brill, D. Brown, and W. Martin, “Fast Genetic Selection of Features for Neural Network Classifier,” IEEE Trans. Neural Network, Vol, No.2 Mar. 1992, pp. 324-328.
[7]J. Yang, and V. Honavar, “Feature Subset Selection Using a Genetic Algorithm,” IEEE Intelligent Systems, 1998, pp. 44-49.
[8]楊智傑,以直交表為基底的高效率篩選演算法及其應用,逢甲大學資訊工程研究所碩士論文,1999年.
[9]B. V. Dasarathy, Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques, Los Alamitos, CA: IEEE Computer Society Press, 1991.
[10]B. V. Dasarathy, “Minimal consistent set (MCS) identification for optimal nearest neighbor decision systems design,” IEEE Trans. System Man Cybernet. Vol. 24, pp. 511-517, 1994.
[11]P. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach. Englewood Cliffs, NJ: Printice-Hall, 1982.
[12]L. I. Kuncheva, “Editing for the k-nearest neighbors rule by a genetic algorithm,” Pattern Recognition Lett, Vol. 16, pp. 809-814, 1995.
[13]L. I. Kuncheva, “FITNESS FUNCTIONS IN EDITING k-NN ERFERENCE SET BY GENETIC ALGORITHMS,” Pattern Recognition, Vol. 30, No. 6, pp. 1041-1049, 1997..
[14]Scott C. Newton, Surya Pemmaraju, and Sunanda Mitra, “Adaptive Fuzzy Leader Clustering of Complex Data Sets in Pattern Recognition,” IEEE Tans. Neural Networks, Vol. 3, No. 5, pp. 794-800, 1992.
[15]Miin-Shen Yang and Chien-Hung Chen, “On the Edited Fuzzy k-Nearest Neighbor Rule,” IEEE Trans. System Man Cybernet.-Part B: Cybernetics, Vol. 28, No. 3, pp.461-466, 1998.
[16]Eel-Wan Lee and Soo-Ik Chae, “Fast Design of Reduced-Complexity Nearest-Neighbor Classifiers Using Triangular Inequality,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 20, No. 5, pp. 562-566, 1998.
[17]Faouzi Kossentini and Mark J. T. Smith, “A Fast PNN Design Algorithm for Entropy-Constrained Residual Vector Quantization,” IEEE Trans. Image Processing, Vol. 7, No. 7, pp1045-1050, 1998.
[18]James C. Bezdek, Thomas R. Reichherzer, Gek Sok Lim, and Yianni Attikiouzel, “Multiple-Prototype Classifier Design,” IEEE Trans. System Man Cybernet.-Part C: Applications and Reviews, Vol. 28, No. 1, pp.67-79, 1998.
[19]Ludmila I. Kuncheva and James C. Bezdek, “Nearest Prototype Classification: Clustering, Genetic Algorithms, or Random Search?” IEEE Trans. System Man Cybernet.-Part C: Applications and Reviews, Vol. 28, No. 1, pp.160-164, 1998.
[20]D. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, 1989.
[21]ARUN KUNJUR and SUNDAR KRISHNAMURTY, “A ROBUST MULTI-CRITERIA OPTIMIZATION APPROACH.” Mech. Mach. Theory Vol. 32, No, 7, pp. 797-810, 1997.
[22]D. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. Addision-Wesley, Reading, Massachusetts, 1989.
[23]S. J. Raudys and A. K. Jain, Small sample size effects in statistical pattern recognition: Recommendations for parctitioners and open problems, Proc. 10th Int. Conf. on Pattern Recognition, Atlantic City, New Jersey, pp. 417-423, 1990 [24]Hart, P.E., 1968. The condensed nearest neighbor rule. IEEE Transactions on Information Theory 16, 515-516.
[25] Wilson, D.L., 1972. Asymptotic properties of nearest neighbor rules using edited data. IEEE Transactions on Systems, Man, and Cybernetics SMC-2, 408-421.
[26] Stearns, S., 1976. On selecting features for pattern classifiers. In:3-d International Conference on Pattern Recognition, Coronado, CA, pp. 71-75.
[27] Glen Stuart Peace, Taguchi Methods-A Hands-On Approach, Addison-Wesley, 1993
[28] Holland, J.H, Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975. (Second edition: MIT Press,1992)
[29]蘇木春與張孝德著,機器學習, 全華書局,1999.
[30]劉勇與康立山及陳毓屏著,遺傳算法,科學出版社,2000
[31]Shinn-Ying Ho, Li-Sun Shu and Hung-Ming Chen,“ Intelligent Genetic Algorithm with a New Intelligent Crossover Using Orthogonal Arrays” ,GECCO-99:proceeding of the Genetic and Evolutionary Computation conference ,1999, pp.289-296.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top