K-means algorithm for optimizing clustering center

Abstract

The invention discloses a k-means algorithm for optimizing a clustering center. The k-means algorithm comprises the steps of solving a sample mean value C and an average distance ad of a sample data set; calculating the distances between all data objects and C according to a formula of the distance between two points in the space; finding out a data point with a distance smaller than or equal to an average distance ad to a direction position point X1 through a two-point distance formula; calculating the distances between all sample set data objects and a direction position point O1; and repeating the above process until K initial clustering centers are found. According to the initial clustering center optimization K-Means improved algorithm provided by the invention, the dependency of the clustering result on the initial clustering center is reduced, the clustering precision, convergence speed and stability are improved, and the influence of isolated points is also eliminated.

Description

technical field [0001] The invention belongs to the technical field of image processing and data mining, and in particular relates to a k-means algorithm for optimizing cluster centers. Background technique [0002] In recent years, the advent of the era of big data has prompted the rapid development of machine learning technology. As one of the commonly used methods in traditional machine learning algorithms, cluster analysis is widely favored due to its practicality, simplicity and efficiency. It has been successfully applied in many fields. Clustering is also an important concept in data mining. Its core is Find valuable information hidden in data objects. [0003] K-Means algorithm is the most popular algorithm among clustering algorithms. Compared with other clustering algorithms, K-Means algorithm has been widely used in clustering algorithms because of its better effect and simple thinking. However, the K-Means algorithm also has its own limitations, such as the num...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the traditional K-Means algorithm being sensitive to the initial clustering center and causing low clustering accuracy and poor stability, the present invention proposes a k-means algorithm that optimizes the clustering center, which reduces the impact of the clustering result on the initial clustering. The dependence of the center improves the accuracy, convergence speed and stability of clustering, and also gets rid of the influence of isolated points

Images