Optimized KD Tree Application in Instance-Based Learning
Peng Chen, Yong Wang · 2008
Nearest neighbor is the basic method in instance-based learning, which is used to approach the real and discrete objective function. In order to enhance the learning speed in nearest neighbor, the optimization of KD tree algorithm was applied in the nearest neighbor method by building the index of the training set. Proper adjustments of the inserting order of the training set can bring the tree more balance and can improve the structure of KD tree, so as to improve its learning efficiency. This paper firstly introduced the most common query in KD tree and summarized two methods of query nearest neighbor. Practice has finally proved that the improved KD tree has good performance in dealing with both region search and nearest neighbor search.