@inproceedings{055bd55520ef46f6819fb6370f4938de,
title = "Hierarchically organized skew-tolerant histograms for geographic data objects",
abstract = "Histograms have been widely used for fast estimation of query result sizes in query optimization. In this paper, we propose a new histogram method, called the Skew-Tolerant Histogram (STHistogram) for two or three dimensional geographic data objects that are used in many real-world applications in practice. The proposed method provides a significantly enhanced accuracy in a robust manner even for the data set that has a highly skewed distribution. Our method detects hotspots present in various parts of a data set and exploits them in organizing histogram buckets. For this purpose, we first define the concept of a hotspot, and provide an algorithm that efficiently extracts hotspots from the given data set. Then, we present our histogram construction method that utilizes hotspot information. We also describe how to estimate query result sizes by using the proposed histogram. We show through extensive performance experiments that the proposed method provides better performance than other existing methods.",
keywords = "histograms, query optimization, spatial databases",
author = "Roh, {Yohan J.} and Kim, {Jae Ho} and Chung, {Yon Dohn} and Son, {Jin Hyun} and Kim, {Myoung Ho}",
year = "2010",
doi = "10.1145/1807167.1807236",
language = "English",
isbn = "9781450300322",
series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",
pages = "627--638",
booktitle = "Proceedings of the 2010 International Conference on Management of Data, SIGMOD '10",
note = "2010 International Conference on Management of Data, SIGMOD '10 ; Conference date: 06-06-2010 Through 11-06-2010",
}