作者：Lu Chen; Yunjun Gao; Xinhan Li;等
来源：One of the Best Papers in ICDE 2015（ICDE 2015优秀论文）
This paper proposes an efficient disk-based metric access method, the Space-filling curve and Pivot-based B+-tree (SPB-tree), to support a wide range of data types and similarity metrics. Moreover, we present efficient similarity search algorithms and corresponding cost models based on the SPB-tree. Extensive experiments with both real and synthetic data show that the SPB-tree has much lower construction cost, smaller storage size, and can support more efficient similarity queries with high accuracy cost models than is the case for competing techniques.
