Density-based partitioning and clustering method for K center points in data mining

Abstract

The invention relates to a density-based partitioning and clustering method for K center points in data mining. The method comprises the following steps that 1, a needed data set is given, and the clustering number K is determined; 2, the densities and average density of data objects are calculated; 3, the minimum density distance value of each data object in the data set is calculated; 4, the minimum density distance values of the data objects in the data set are descendingly sorted, and K data objects corresponding to the minimum density distance values are selected as a clustering center from large to small according to the determined clustering number K, wherein the densities of the K data objects are larger than the average density; 5, the data objects in the data set are distributed to an initial clustering center closest to the data objects, and a clustering result is obtained. The high-quality center points can be selected, subsequent iteration updating steps in a K-means algorithm are not needed, computation complexity is lowered, classification accuracy is improved, high stability is achieved, and operation efficiency is improved.

Description

technical field [0001] The invention relates to a clustering method, in particular to a density-based K center point division clustering method in data mining, which belongs to the technical field of clustering analysis. Background technique [0002] Data mining is one of the hot topics in computer research today. As an unsupervised machine learning method, cluster analysis refers to how to automatically divide data objects into different clusters for a set of data objects, so that the same cluster Objects in a certain measure have high similarity, while data objects in different clusters have low similarity. Cluster analysis is widely used in cutting-edge fields such as machine learning, data mining, speech recognition, image segmentation, business analysis, and bioinformatics processing. At present, traditional clustering algorithms mainly include five categories, they are: partition-based clustering algorithms, hierarchical-based clustering algorithms, density-based clus...

AI Technical Summary

Problems solved by technology

However, there are some defects in the original K-means algorithm: 1), the original algorithm requires the user to give the K value, that is, the number of clusters, this value is mainly obtained from experience, so it is difficult to determine the K value; 2), The algorithm is sensitive to the initial clustering center, and the selection of the initial center will affect the clustering results and the efficiency of the algorithm operation; 3), the algorithm is sensitive to abnormal data, which will cause the result to fall into a local optimal solution

Another problem is that the initial center point may be selected as a point in the same cluster, that is, although the density of a certain point is relatively high, a point in the cluster corresponding to the point has already been selected as the center point. You should choose representative points in other classes, otherwise, the result will easily fall into the local optimal solution

Images