Efficient Mining Maximal Variant Usage and Low Usage Biclusters in Discrete Function-Resource Matrix

The functional layer is the pillar of the whole prognostics and health management system. Its effectiveness is the core of system task effectives. In this paper, we proposed a new bicluster mining algorithm: DoCluster, to effectively mine all biclusters with maximal variant usage rate and low usage rate in the discrete function-resource matrix. In order to improve the mining efficiency, DoCluster algorithm constructs a sample weighted graph firstly; secondly, all biclusters with maximal variant usage rate and low usage rate satisfying the variant usage rate and low usage rate definition are mined using sample-growth and depth-first method in the constructed weighted graph. DoCluster algorithm also uses several pruning strategies to ensure the mining of maximal bicluster without candidate maintenance. The experimental results show DoCluster algorithm is more efficient than other two algorithms.