The K Nearest Neighbor(knn) classifier has been widely used in the applications of data mining and machine learning, because of its simple implementation and distinguished performance. However, because the distance be...
详细信息
The K Nearest Neighbor(knn) classifier has been widely used in the applications of data mining and machine learning, because of its simple implementation and distinguished performance. However, because the distance between all training samples and test samples have to be calculated, when there are too many samples or samples have huge features dimensionality, the time complexity and space complexity are high. The paper proposes a knn algorithm with the minimum intra-class distance and the maximum extra-class distance(MIME-knn). By finding a transformation matrix, the algorithm minimizes the intra-class distance and maximizes the distance between classes, which can improve the classificationperformance of traditional knn algorithm. At the same time, the algorithm will also reduce the dimensionality of the samples to achieve the purpose of reducing time and space complexity. Experimental results show that the MIME-knn work well in practical.
暂无评论