(3.238.240.197) 您好!臺灣時間:2021/04/13 01:03
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:何省華
研究生(外文):Hsin-Hua Ho
論文名稱:以無參數的分散量為基礎的k最近鄰分類器
論文名稱(外文):A Novel k-Nearest-Neighbor Classifier Based on Nonparametric Separability
指導教授:郭伯臣郭伯臣引用關係
指導教授(外文):Bor-Chen Kuo
學位類別:碩士
校院名稱:國立臺中教育大學
系所名稱:教育測驗統計研究所
學門:教育學門
學類:教育測驗評量學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:英文
論文頁數:43
中文關鍵詞:樣式辨識分類器k最近鄰分類器
外文關鍵詞:pattern recognitionclassifierk-nearest-neighbor classifiernonparametric weighted feature extraction
相關次數:
  • 被引用被引用:0
  • 點閱點閱:306
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:34
  • 收藏至我的研究室書目清單書目收藏:0
k最近鄰分類器是一個直覺且簡單的分類器。一個好的k最近鄰分類器期望類別的條件機率為局部一致。在本研究裡,我們使用NWFE的分散量建立一個有效的量測,進而找出新的鄰近區域。這個新的測量會將原來用歐式距離建立的鄰近區域延著分散量大的方向收縮且延著分散量小的擴張。而在修正後的鄰近區域的類別條件機率會趨向於更一致性。在實驗裡,k最近鄰分類器使用修正後的鄰近區域會比原來的k最近鄰分類器及其它分類器分類效果好。因此,本文所提之方法可改善原始的k最近鄰分類器,而增進分類的效果。
The k-nearest-neighbor (k-NN) classifier is a simple and appealing classifier. A k-nearest-neighbor classifier expects the class conditional probabilities to be locally constant and suffers form bias in high dimensions. In this paper, we first use separability based on adaptive NWFE to establish an effective metric for computing a new neighborhood. The modified neighborhood shrinks in the direction with high separability and extends further in the other direction, i.e., the modified neighborhood extends further in the direction parallel to the decision boundary. Then the posterior probabilities tend to be more homogeneous in these modified neighborhoods. This new neighborhood can often provide improvement in classification performance. Therefore, any neighborhood-based classifier can be employed by using the modified neighborhoods.
List of Tables IV
List of Figures VI
Chapter 1: Introduction 1
1.1 Statement of Problem 1
1.2 Organization of Thesis 2
Chapter 2: Literature Review 3
2.1 Nonparametric Weighted Feature Extraction 3
2.2 Classifiers 5
2.2.1 k-Nearest-Neighbor Classifier 5
2.2.2 Support Vector Classification Using Cross-Validation 6
2.2.3 Parzen Classifier 8
Chapter 3: k-Nearest-Neighbor Classifier Based on Nonparametric Separability 10
3.1 k-Nearest-Neighbor Classifier Based on Adaptive NWFE Separability 10
3.2 A Simplified Version of the kNN-ANS 15
Chapter 4: Experiment Design 19
Chapter 5: Experiment Results 21
5.1 Experiment Results of Fisher’s Iris data 21
5.2 Experiment results of Washington DC Mall 23
5.2.1 Washington DC Mall with 191 Bands 24
5.2.2 Washington DC Mall with 39 bands 28
5.3 Experiment Results of Educational Quiz Data 32
Chapter 6: Conclusion and Future Research 34
6.1 Conclusion 34
6.2 Future Research 35
References 36
Appendix A: Completely Experimental Results 38
Chinese Part
郭伯臣、吳慧珉、楊晉民、柯立偉、白家豪(民92)。樣式辨識技術於學生補救教學分組之應用-以國小數學領域「扇形」單元為例,九十二學年度師範學院教育學術論文發表會,台南師院,10月24-25日。
郭伯臣(民95)統計樣式辨認於測驗資料之應用。測驗統計年刊,第十三輯下期,pp.146-170。


English Part
Baudat, G. & Anouar F., (2000), Generalized Discriminant Analysis Using a Kernel Approach, Neural computation, December, 2385-2404.

Duin, R, P. W, (2002), PRTools, a Matlab Toolbox for Pattern Recognition.
(Available for download from http://www.ph.tn.tudelft.nl/prtools/).

Fisher R.A., (1936), The Use of Multiple Measurements in Taxonomic Problems, Annual Eugenics, 7, Part II, 179-188.

Fukunaga, K., (1972), Introduction to Statistical Pattern Recognition, San Diego: Academic Press Inc.

Friedman, J. (1994). Flexible Metric Nearest Neighbour Classification, Tech. Rep., Stanford University, November.

Friedman, M. & Kandel, A., (1999), Introduction to Pattern Recognition: Statistical, Structural, Neural, and Fuzzy Logic Approaches, World Scientific, Singapore.

Hastie, T. & Tibshirani, R., (1996), Discriminant Adaptive Nearest Neighbor Classification, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 18, no. 6, 607-615.

Kuncheva, L. I., (2000), Fuzzy Classifier Design. Studies in Fuzziness and Soft Computing. Springer-Verlag, Heidelberg.

Kuo, B-C. & Landgrebe, D. A.,(2001), Improved Statistics Estimation and Feature Extraction for Hyperspectral Data Classification, Technical Report, Purdue University, West Lafayette, IN., TR-ECE 01-6, December.

Kuo, B-C. & Landgrebe, D. A., (2002, 2004), Nonparametric Weighted Feature Extraction for Classification, IEEE Trans. on Geoscience and Remote Sensing, vol. 42, no. 5, 1096-1105, May.

Landgrebe, D. A., (2003). Signal Theory Methods in Multispectral Remote Sensing, John Wiley and Sons, Inc.

Short, R. & Fukanaga, K. (1980), A New Nearest Neighbor Distance Measure, in Proc. 5th IEEE Int. Conf. on Pattern Recognition, 81-86.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔