DocumentCode :
1393086
Title :
On Guo and Nixon´s Criterion for Feature Subset Selection: Assumptions, Implications, and Alternative Options
Author :
Balagani, Kiran S. ; Phoha, Vir V. ; Iyengar, S.S. ; Balakrishnan, N.
Author_Institution :
Louisiana Tech Univ., Ruston, LA, USA
Volume :
40
Issue :
3
fYear :
2010
fDate :
5/1/2010 12:00:00 AM
Firstpage :
651
Lastpage :
655
Abstract :
Guo and Nixon proposed a feature selection method based on maximizing I( x;Y), the multidimensional mutual information between feature vector x and class variable Y. Because computing I(x;Y) can be difficult in practice, Guo and Nixon proposed an approximation of I(x;Y) as the criterion for feature selection. We show that Guo and Nixon´s criterion originates from approximating the joint probability distributions in I(x;Y) by second-order product distributions. We remark on the limitations of the approximation and discuss computationally attractive alternatives to compute I(x;Y) .
Keywords :
approximation theory; probability; vectors; feature subset selection; feature vector; joint probability distribution; multidimensional mutual information; second-order product distribution; Entropic spanning graphs; Parzen window; feature selection; mutual information;
fLanguage :
English
Journal_Title :
Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on
Publisher :
ieee
ISSN :
1083-4427
Type :
jour
DOI :
10.1109/TSMCA.2009.2036935
Filename :
5395688
Link To Document :
بازگشت