UB-H: an unbalanced-hierarchical layer binary-wise construction method for high-dimensional data

Abstract Cloud computing, which is distributed, stored and managed, drawing attention as data generation storage volumes increase. In addition, research on green increases energy efficiency, also widely studied. An index constructed to retrieve huge dataset efficiently, the layer-based indexing methods are used for efficient query processing. These construct a list of layers, so that only one layer required information retrieval instead entire dataset. The existing layers using convex hull algorithm. However, execution time this method very high, especially in large, high-dimensional datasets. Furthermore, if total number increases, processing resulting efficient, but slow, paper, we propose an unbalanced-hierarchical method, hierarchically divides dimensions input increase reduce building time. We demonstrate proposed procedure significantly reduces time, compared through various experiments.