A novel genetic-based instance selection method: Using a divide and conquer approach

Nearest Neighbor (NN) classifier is a simple classifier which can be used in a variety of applications. However, this classifier is known to be vulnerable and very slow when dealing with redundant, irrelevant or noisy instances. To tackle this problem, we propose a novel method based on the combination of Genetic Algorithm and Divide and Conquer Algorithm to select the most relevant instances and hence improve classification accuracy and enhance time complexity and space requirement of NN. Our empirical studies confirm that this combination improves the results in all aspects and overcomes previously proposed methods.