Regional distance-based k-NN classification

k-Nearest Neighbor (k-NN) is very simple and powerful approach to conceptually approximate real-valued or discrete-valued target function. Many researchers have recently approved that k-NN is a high prediction accuracy for variety of real world systems using many different types of datasets. However, as we know, k-NN is a type of lazy learning algorithms as it has to compare to each of stored training examples for each observed instance. Besides, the prediction accuracy of k-NN is under the influence of K values. Mostly, the higher K values make the algorithm yield lower prediction accuracy according to our experiments. For these issues, this paper focuses on two properties that are to upgrade the classification accuracy by introducing Regional Distance-based k-NN (RD-kNN) and to speed up the processing time performance of k-NN by applying multi-threading approach. For the experiments, we used the real data sets, wine, iris, heart stalog, breast cancer, and breast tissue, from UCI machine learning repository. According to our test cases and simulations carried out, it was also experimentally confirmed that the new approach, RD-kNN, has a better performance than classical k-NN.