An adaptive k-nearest neighbor algorithm

Abstract

An adaptive k-nearest neighbor algorithm (AdaNN) is brought forward in this paper to overcome the limitation of the traditional k-nearest neighbor algorithm (kNN) which usually identifies the same number of nearest neighbors for each test example. It is known that the value of k has crucial influence on the performance of the kNN algorithm, and our improved kNN algorithm focuses on finding out the suitable k for each test example. The proposed algorithm finds out the optimal k, the number of the fewest nearest neighbors that every training example can use to get its correct class label. For classifying each test example using the kNN algorithm, we set k to be the same as the optimal k of its nearest neighbor in the training set. The performance of the proposed algorithm is tested on several data sets. Experimental results indicate that our algorithm performs better than the traditional kNN algorithm.