A filter-dominating hybrid sequential forward floating search method for feature subset selection in high-dimensional space
作者： John Q. Gan , Bashar Awwad Shiekh Hasan , Chun Sing Louis Tsui
DOI: 10.1007/S13042-012-0139-Z
关键词: Search algorithm 、 Feature selection 、 Support vector machine 、 Computational intelligence 、 Feature data 、 Artificial intelligence 、 Linear discriminant analysis 、 Data mining 、 Mutual information 、 Pattern recognition 、 Classifier (UML) 、 Computer science
摘要: Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional subset selection. Experiments with this new approach have conducted on five data sets, different combinations classifier separability index alternative criteria evaluating performance potential subsets. The classifiers under consideration include linear discriminate analysis classifier, support vector machine, K-nearest neighbors indexes Davies-Bouldin mutual information based index. Experimental results demonstrated advantages usefulness proposed method in
essex.ac.uk
springer.com
sci-hub.se 参考文章(20)
Petr Somol, Jana Novovičová, Pavel Pudil, Flexible-Hybrid Sequential Floating Search in Statistical Feature Selection Lecture Notes in Computer Science. pp. 632- 639 ,(2006) , 10.1007/11815921_69
F Sepulveda, John Q Gan, Matthew Dyson, T Balli, Ramaswamy Palaniappan, Approximate entropy for EEG-based movement detection Verlag der Technischen Universität Graz. ,(2008)
Janez Demšar, Statistical Comparisons of Classifiers over Multiple Data Sets Journal of Machine Learning Research. ,vol. 7, pp. 1- 30 ,(2006)
Sanmay Das, Filters, Wrappers and a Boosting-Based Hybrid for Feature Selection international conference on machine learning. pp. 74- 81 ,(2001)
Bashar Awwad Shiekh Hasan, John Q. Gan, Qingfu Zhang, Multi-objective evolutionary methods for channel selection in Brain-Computer Interfaces: Some preliminary experimental results IEEE Congress on Evolutionary Computation. pp. 1- 6 ,(2010) , 10.1109/CEC.2010.5586411
Pablo Bermejo, Jose A Gámez, Jose M Puerta, None, A GRASP algorithm for fast hybrid (filter-wrapper) feature subset selection in high-dimensional datasets Pattern Recognition Letters. ,vol. 32, pp. 701- 711 ,(2011) , 10.1016/J.PATREC.2010.12.016
P. Pudil, J. Novovičová, J. Kittler, Floating search methods in feature selection Pattern Recognition Letters. ,vol. 15, pp. 1119- 1125 ,(1994) , 10.1016/0167-8655(94)90127-9
Jinjie Huang, Yunze Cai, Xiaoming Xu, A hybrid genetic algorithm for feature selection wrapper based on mutual information Pattern Recognition Letters. ,vol. 28, pp. 1825- 1844 ,(2007) , 10.1016/J.PATREC.2007.05.011
Dong Ling Tong, Robert Mintram, Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection International Journal of Machine Learning and Cybernetics. ,vol. 1, pp. 75- 87 ,(2010) , 10.1007/S13042-010-0004-X
Özge Uncu, I.B. Türkşen, A novel feature selection approach: Combining feature wrappers and filters Information Sciences. ,vol. 177, pp. 449- 466 ,(2007) , 10.1016/J.INS.2006.03.022