Application of nonlinear clustering optimization algorithm in web data mining of cloud computing

Abstract

Abstract To improve data mining and data clustering performance to improve the efficiency of the cloud computing platform, the author proposes a bionic optimized clustering data extraction algorithm based on cloud computing platform. According to the Gaussian distribution function graph, the degree of aggregation of the categories and the distribution of data points of the same category can be judged more intuitively. The cloud computing platform has the characteristics of large amount of data and high dimension. In the process of solving the distance between all sample points and the center point, after each center point update, the optimization function needs to be re-executed, the author mainly uses clustering evaluation methods such as PBM-index and DB-index. The simulation data object is the Iris dataset in UCI, and N = 500 samples are selected for simulation. The experiment result shows that when P is not greater than 15, the PBM value changes very little, and when P = 20, the PBM performance of all the four clustering algorithms decreased significantly. When the sample size is increased from 50,000 to 100,000, the DB performance of this algorithm does not change much, and the DB value tends to be stable. In terms of clustering operation time, the K-means algorithm has obvious advantages, the DBSCAN algorithm is the most time-consuming, and the operation time of wolf pack clustering and Mean-shift is in the middle. In the actual application process, the number of samples for each training can be dynamically adjusted according to the actual needs, in order to improve the applicability of the wolf pack clustering algorithm in specific application scenarios. Flattening in cloud computing for data clusters, this algorithm is compared with the common clustering algorithm in PBM. DB also shows better performance.