An Attempt to Discover Analytical Information for Multi-Dimensional Data Sets
Yong Shi, Daniel Brown · 2018 International Conference on Inventive Research in Computing Applications (ICIRCA) · 2018
We propose an algorithm to improve the cluster analysis process. Clusters are subgroups in a data set that contain data points with similar characteristics within the same subgroup. Cluster analysis is the process of defining and calculating the similarity between data points and grouping them into the same cluster. We present the issues involved in cluster analysis, and present an algorithm to divide the original data set into multiple smaller data sets in the same data space, then perform cluster analysis on each new data set, and finally integrate the clustering results from all the smaller data sets into the final clusters. We discuss various situations where clusters will be discovered in the data space, and conduct experiments and discuss the results of our algorithm.