Research on the Optimization of Fast Global K-Means Clustering Algorithm in the Context of Big Data

With the rapid development of computer information collection and processing technology, databases and their applications continue to expand. The world today has entered the era of big data with a data explosion. How to effectively obtain the required information and data from massive amounts of data has become a research hotspot for scholars nowadays. Clustering analysis is an important data mining method and has become an important research field in pattern recognition and data mining. It is also widely applied in many fields such as statistical analysis, bio-information processing, image processing, etc. The traditional K-means clustering algorithm has become the most widely applied one among clustering algorithms because of its characteristics of high efficiency, rapidness, and easy understanding and implementation. However, the K-means clustering algorithm also has limitations. The clustering results are easily affected by the random selection of initial centers and noise. This paper describes the basic principles of several K-means clustering algorithms and analyzes the advantages and existing problems of each algorithm. Then, it proposes the strategies, implementation methods and algorithm flows for improving the existing fast global K-means clustering algorithm. Finally, through the analysis of the algorithm complexity and experimental results of the improved fast global K-means clustering algorithm, its effectiveness is proved.