權重型基因之基因法則於特徵選取之應用

Application of Gene Weighted Genetic Algorithm to Feature Selection

陳肇宗(Zhao-Zong Chen)

指導教授 ： 姚立德

國立臺北科技大學/機電學院/電機工程系所/碩士(2006年)

https://doi.org/10.6841/NTUT.2006.00344

摘要

特徵選取（feature selection）的目的是要從原有的特徵點中挑選出最佳的部分特徵點，使其辨識率(recognition rate)能夠達到最高值。這些鑑別能力較好的特徵點，不但能夠簡化分類的計算，而且也可以幫助瞭解此分類問題的因果關係。
將基因法則(Genetic Algorithm)應用於特徵選取上則是近年來被發展出來的方法。而本文所提出的權重型基因之基因法則(Gene Weighted Genetic Algorithm， GWGA)，將染色體中的每一個基因給予一個交配的權重値，並以機率的方式來做交配的運算，改變了傳統基因法則交配的方式以解決容易陷入局部最佳解(local minimize)的問題，並且能夠適當的減少特徵數目。
最後，利用UCI標準資料來驗證本文提出之方法，並且將其應用於實際電力負載分類的問題上。

關鍵字

特徵選取 ； 基因法則

並列摘要

The feature selection which choose the best feature from original feature, and maximum the recognition rate. These best feature can simplification classified computation, and comprehend the causal relation of classified question.
Among the different categories of feature selection algorithms, the genetic algorithm (GA) is a rather recent development. In this thesis, the Gene Weighted Genetic Algorithm, that is give a gene weighted value in each gene of chromosome, and make the crossover operation by the probability, this change can reduce local minimize when used traditional method of Genetic Algorithm.
Moreover, several examples is also proposed as UCI standard databases are used to verify the effectiveness of the proposed approach. inally, we also employ the GWGA in a real practice of load profile.

並列關鍵字

feature selection ； genetic algorithm

參考文獻

[1] N. Kwark and C. H. Choi, “Input feature selection for classification problems,” IEEE Transactions Neural Networks, Vol. 13, No. 1, pp.143-159, Jan 2002.

[2] J. Feng, Y. Yang, H. Wang and X. M. Wang,“Feature selection based on genetic algorithms and support vector machines for handwritten similar Chinese characters recognition,”Proceedings of 2004 International Conference on Machine Learning and Cybernetics, Vol. 6, pp. 26-29, Aug 2004.

[3] H. Frohlich, O. Chapelle and B. Scholkopf, “Feature selection for support vector machines by means of genetic algorithm,”IEEE International Conference on Tools with Artificial Intelligence, pp. 142-148, Nov 2003.

[4] A. Gonzalez and R. Perez, “Selection of relevant features in a fuzzy genetic learning algorithm,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 31, No. 3, pp.417-425, Jun 2001.

[7] Y. Tang, Y. Q. Zhang and Z. Huang, “FCM-SVM-RFE gene feature selection algorithm for leukemia classification from microarray gene expression data,”IEEE International Conference on Fuzzy Systems, pp. 97-101, May 2005.