A Density-Based Spatial Clustering of Application with Noise Algorithm and its Empirical Research

Abstract

With the rapid development and wide popularization of information technology, a large amount of data also follows. It is very important to use data mining tools to screen valuable information from complex data. As one of the widely used density clustering algorithms, density- based spatial clustering of application with noisy (DBSCAN) algorithm is an important data mining method. It can find the multi-dimensional relationship between data elements from the data set, complete the clustering of arbitrary shape and noisy data sets when the number of cluster classes is unknown, and support spatial database. Therefore, based on the example of judging the correctness of the relationship between the user's meter and the substation transformer, and supported by the clustering technology of DBSCAN, this paper finally verifies that the density-based clustering method has a good classification effect on the data with high complexity.