Abstract | ||
---|---|---|
Despite its simplicity and good classification performance, the Nearest Neighbor (NN) rule is not applied in many practical tasks because of the high amount of computational resources that it requires. Besides, when working with imbalanced training samples, its classification accuracy can be seriously degraded. In the present paper we propose two genetic algorithms to cope with these two issues. The purpose is to obtain complexity reduction while at the same time, to get a better balance in the training sample. Experimental results showing the benefits of our proposals are also reported. |
Year | Venue | Keywords |
---|---|---|
2005 | CCIA | complexity reduction,feature selection,computational resource,genetic algorithm,genetic optimization,nearest neighbor,classification accuracy,imbalanced training set reduction,good classification performance,imbalanced training sample,better balance,training sample,genetic algorithms,genetics |
Field | DocType | Volume |
k-nearest neighbors algorithm,Training set,Data mining,Feature selection,Computer science,Reduction (complexity),Artificial intelligence,Machine learning,Genetic algorithm | Conference | 131 |
ISSN | ISBN | Citations |
0922-6389 | 1-58603-560-6 | 2 |
PageRank | References | Authors |
0.37 | 21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
R Barandela | 1 | 558 | 23.46 |
J. K. Hernández | 2 | 2 | 0.37 |
José Salvador Sánchez | 3 | 565 | 31.62 |
F J. Ferri | 4 | 293 | 22.43 |