Floating search methods in feature selection

Pattern Recognition Letters

Volumn 15, Issue 11, 1994, Pages 1119-1125

  Pudil, P ^a   Novovicova J ^a   Kittler, J ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

Feature ordering; Feature selection; Pattern recognition; Search methods

Indexed keywords

ALGORITHMS; COMPUTER SELECTION AND EVALUATION; ONLINE SEARCHING; PATTERN RECOGNITION SYSTEMS; PERFORMANCE;

CRITERION FUNCTION; FEATURE ORDERING; FEATURE SELECTION; FLOATING SEARCH METHODS; OPTIMALITY; SEQUENTIAL BACKWARD SELECTION; SEQUENTIAL FORWARD SELECTION;

PATTERN RECOGNITION;

EID: 0028547556     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-8655(94)90127-9     Document Type: Article

References (16)

1. On the max-min approach for feature ordering and selection
2. Feature selection in pattern recognition
3. A detailed study of the max-min in pattern recognition
4. Optimum feature selection by zero-one integer programming
5. Feature set search algorithms
6. On the effectiveness of receptors in recognition system
7. Experimental study of information and inter-intra class distance ratios and feature selection and orderings
8. A branch and bound algorithm for feature subset selection
9. Statistical approach to pattern recognition: Theory and practical solution by means of PREDITAS system
10. A comparative evaluation of floating search methods for feature selection
11. An analysis of the max-min approach to feature selection
12. Computationally efficient quasioptimal algorithms for feature selection
13. On automatic feature selection
14. A note on genetic algorithm for large-scale feature selection
15. On selecting features for pattern classifiers
16. A direct method of nonparametric measurement selection