A modified k-nearest neighbor classifier to deal with unbalanced classes

Publication Type:
Conference Proceeding
IJCCI 2009 - International Joint Conference on Computational Intelligence, Proceedings, 2009, pp. 408 - 413
Issue Date:
Full metadata record
We present in this paper a simple, yet valuable improvement to the traditional k-Nearest Neighbor (kNN) classifier. It aims at addressing the issue of unbalanced classes by maximizing the class-wise classification accuracy. The proposed classifier also gives the option of favoring a particular class through evaluating a small set of fuzzy rules. When tested on a number of UCI datasets, the proposed algorithm managed to achieve a uniformly good performance.
Please use this identifier to cite or link to this item: