Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery

Pattern Recognition Letters

Volumn 23, Issue 1-3, 2002, Pages 183-190

  Yu, Shixin ^a   De Backer, Steve ^a   Scheunders, Paul ^a  

^a UNIVERSITY OF ANTWERP   (Belgium)

Author keywords

Classification; Feature selection; Hybrid systems

Indexed keywords

FUZZY SETS; GENETIC ALGORITHMS; IMAGE COMMUNICATION SYSTEMS; IMAGING SYSTEMS; SATELLITE COMMUNICATION SYSTEMS; SPECTROMETERS;

AIRBORNE VISIBLE/INFRARED IMAGING SPECTROMETERS (AVIRIS);

FEATURE EXTRACTION;

ALGORITHM; FUZZY MATHEMATICS; SATELLITE IMAGERY; SPECTROMETER;

EID: 0036132565     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8655(01)00118-0     Document Type: Article

References (26)

1. Estimating probabilities: A crucial task in machine learning
2. Multi-objective pattern and feature selection by a genetic algorithm
3. Feature selection: Evaluation, application, and small sample performance
4. A fuzzy k-nearest neighbor algorithm
5. On combining classifiers
6. Wrappers for feature subset selection
7. Nearest neighbor classifier: Simultaneous editing and feature selection
8. Optimal combination of pattern classifiers
9. Information extraction principles and methods for multispectral and hyperspectral data
10. Feature extraction based on decision boundaries
11. A branch and bound algorithm for feature subset selection
12. Floating search methods in feature selection
13. Induction of decision trees
14. Combining the results of several neural network classifiers
15. The strength of weak learnability
16. A note on genetic algorithms for large-scale feature selection
17. Prototype and feature selection by sampling and random mutation hill climbing algorithms
18. Combination of multiple classifiers using local accuracy estimates
19. Methods of combining multiple classifiers and their application to handwriting recognition
20. Feature subset selection using a genetic algorithm