Title :
A new approach to feature subset selection
Author :
Liu, Da-zhong ; Feng, Zhi-Jing ; Wang, Xi-Zhao
Author_Institution :
Fac. of Math. & Comput. Sci., Hebei Univ., Baoding, China
Abstract :
The paper presents a brief overview to the approaches of feature subset selection (FSS), commonly used in machine learning or pattern recognition. A combined algorithm based on the two algorithms, i.e., the mutual information selector (MIFS) and relevance information selector (RELFSS), is put forward. Experiments show some advantages of the combined algorithm.
Keywords :
feature extraction; learning (artificial intelligence); set theory; feature subset selection; machine learning; mutual information selector; pattern recognition; relevance information selector; Entropy; Feature extraction; Frequency selective surfaces; Fuzzy sets; Machine learning; Machine learning algorithms; Mathematics; Measurement uncertainty; Mutual information; Scattering;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382072
