Density Peak Clustering Algorithm Based On Improved Fruit Fly Optimization

In recent years,digital economy has developed rapidly,especially the rapid spread and application of 5G,artificial intelligence and the internet,making data volume increased significantly.At the same time,with the full launch of the "East Data West Calculation" project,there is not only the demand for scientific calculation and big data processing,but also the demand for faster growth of artificial intelligence training and inference calculation for data in the eastern region.Therefore,it highlights the role of data mining technology as an effective way of data analysis.Clustering,as an important analysis method in data mining,can mine the structural information and similar relationships within data,and classify data objects into clusters.DPC is a typical efficient clustering method,which can intuitively and quickly identify class clusters in arbitrarily shaped datasets,and can efficiently assign sample points and effectively eliminate outliers,and has good applicability to large-scale datasets.However,the truncation distance parameter of this algorithm needs to be selected manually,and the parameter selection has a great influence on the clustering results.Aiming at the defects of DPC algorithm,a density peak clustering algorithm based on improved fruit fly optimization is proposed.The specific work is as follows:Firstly,the Tent chaotic mapping is used to initialize the fruit fly population,and the unique properties of Tent chaotic sequence are utilized to improve the initial population diversity and enhance the global exploration ability of the algorithm.And the basic fruit fly optimization algorithm is improved by introducing dynamic step factor and Cauchy mutation strategy to enhance its local exploration ability and help the algorithm jump out of the local optima.The experimental results of six test functions show that the improved FOA algorithm has faster convergence speed and higher solution accuracy.Secondly,the convergence of the improved FOA algorithm is analyzed theoretically from the perspective of the convergence criterion of the stochastic algorithm.Then,in order to solve the shortcomings of the DPC algorithm in terms of the truncation distance parameter,the improved FOA algorithm is fused with the DPC algorithm into a new algorithm.The improved FOA algorithm is used to find the best truncation distance and achieve the final clustering with its stronger optimum-seeking ability.The experimental results show that the new algorithm has improved the clustering performance on the four datasets,and has better performance indexes,and effectively suppresses the influence problem caused by manual selection of the truncation distance parameter.Finally,the improved density peak clustering algorithm is applied to the analysis of economic and financial data sets.The six financial index data that can reflect the development trend of enterprises obtained from the Guotaian database are clustered and analyzed to classify the types of each enterprise so that the enterprise investors can make a reasonable and correct choice.The experimental results show that the improved algorithm has good application value in data analysis in the economic field.