Efficient group pattern mining using data summarization

• Main Authors: WANG, Yida, LIM, Ee Peng, HWANG, San-Yih
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2004
• Subjects: Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/1030; https://ink.library.smu.edu.sg/context/sis_research/article/2029/viewcontent/Wang2004_Chapter_EfficientGroupPatternMiningUsi.pdf
• Institution: Singapore Management University

In group pattern mining, we discover group patterns from a given user movement database based on their spatio-temporal distances. When both the number of users and the logging duration are large, group pattern mining algorithms become very inefficient. In this paper, we therefore propose a spherical location summarization method to reduce the overhead of mining valid 2-groups. In our experiments, we show that our group mining algorithm using summarized data may require much less execution time than that using non-summarized data.