Panda: A predictive spatio-temporal query processor

Abdeltawab M. Hendawi, Mohamed F. Mokbel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Scopus citations

Abstract

This paper presents the Panda system for efficient support of a wide variety of predictive spatio-temporal queries that are widely used in several applications including traffic management, location-based advertising, and ride sharing. Unlike previous attempts in supporting predictive queries, Panda targets long-term query prediction as it relies on adapting a well-designed long-term prediction function to: (a) scale up to large number of moving objects, and (b) support large number of predictive queries. As a means of scalability, Panda smartly precomputes parts of the most frequent incoming predictive queries, which significantly reduces the query response time. Panda employs a tunable threshold that achieves a trade-off between query response time and the maintenance cost of precomptued answers. Experimental results, based on large data sets, show that Panda is scalable, efficient, and as accurate as its underlying prediction function.

Original languageEnglish (US)
Title of host publication20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
Pages13-22
Number of pages10
DOIs
StatePublished - Dec 1 2012
Event20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012 - Redondo Beach, CA, United States
Duration: Nov 6 2012Nov 9 2012

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Other

Other20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2012
CountryUnited States
CityRedondo Beach, CA
Period11/6/1211/9/12

Keywords

  • location-based services
  • predictive spatio-temporal queries

Fingerprint Dive into the research topics of 'Panda: A predictive spatio-temporal query processor'. Together they form a unique fingerprint.

Cite this