Hierarchical clustering algorithm of the minimum risk

Clustering analysis is grouping a set of physical or abstract objects into the similar class. In traditional clustering algorithm, objects are usually divided into a certain cluster. This paper applies the risk evaluation of decision-theoretic rough set model in clustering analysis which solves the problem of uncertain boundary region, and proposes a hierarchical clustering algorithm of the minimum risk which can adjust threshold value to construct a clustering evaluation function in order to find the solution to optimize the result. At last, the case analysis shows the algorithm is feasible. It could provide a strong support for marine environment monitoring system and so on.