An Enhancement of k-Nearest Neighbor Classification Using Genetic Algorithm
چکیده
K-Nearest Neighbor Classification (kNNC) makes the classification by getting votes of the k-Nearest Neighbors. Performance of kNNC is depended largely upon the efficient selection of k-Nearest Neighbors. All the attributes describing an instance does not have same importance in selecting the nearest neighbors. In real world, influence of the different attributes on the classification keeps on changing with time. To solve this problem, we have proposed an enhancement of kNNC where Genetic Algorithm (GA) has been applied for effective selection and upgrade of attribute set to find out k-Nearest Neighbors. Our experimental results demonstrate a significant improvement in classification accuracy in comparison with the conventional kNNC.