Unique signal group selection method based on grey relational analysis and hierarchical clustering

Abstract:
Unique signal often serves as high-consequence system protects password to use. In order to avoid the potential risk of mutual interference caused by using multiple unique signals simultaneously, it is necessary to select the group composed of multiple unique signals with the least similarity among them. In this paper, the data set based on the structure of unique signal is clustered by partition clustering, and the linear complexity and run distribution of the properties of unique signals are analyzed. Then the grey relational analysis method is used to combine the initial clustering results with attributes of unique signals, adjust the weight of each attribute in the whole, and reconstruct the data set based on attributes of unique signals. Finally, the hierarchical clustering method is used to cluster the new data sets, and the better grouping result is obtained, which reduces the potential risk of using multiple unique signals simultaneously.