A Modified K-Nearest Neighbor Algorithm Using Feature Optimization

A classification technique is an organized approach for building classification model from given input dataset. The learning algorithm of each technique is employed to build a model used to find the relationship between attribute set and class label of the given input data. Presence of irrelevant information in the data set reduces the speed and quality of learning. The technique of feature selection reduces the amount of data needed and execution time and it also improves the accuracy for prediction in the classification problem. In this paper we have modified KNearest Neighbor algorithm with relevant feature selection which selects the relevant features and removes irrelevant features of the dataset automatically. KeywordsClassification, K Nearest Neighbor, Feature Space, Filter Approach, Wrapper Approach, Relevant Feature Selection, Covariance, Covariance Matrix