29 December 2008 Mining fuzzy association rules in spatio-temporal databases
Author Affiliations +
Proceedings Volume 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA); 728541 (2008) https://doi.org/10.1117/12.815993
Event: International Conference on Earth Observation Data Processing and Analysis, 2008, Wuhan, China
Abstract
A huge amount of geospatial and temporal data have been collected through various networks of environment monitoring stations. For instance, daily precipitation and temperature are observed at hundreds of meteorological stations in Northeastern China. However, these massive raw data from the stations are not fully utilized for meeting the requirements of human decision-making. In nature, the discovery of geographical data mining is the computation of multivariate spatio-temporal correlations through the stages of data mining. In this paper, a procedure of mining association rules in regional climate-changing databases is introduced. The methods of Kriging interpolation, fuzzy cmeans clustering, and Apriori-based logical rules extraction are employed subsequently. Formally, we define geographical spatio-temporal transactions and fuzzy association rules. Innovatively, we make fuzzy data conceptualization by means of fuzzy c-means clustering, and transform fuzzy data items with membership grades into Boolean data items with weights by means ofλ-cut sets. When the algorithm Apriori is executed on Boolean transactions with weights, fuzzy association rules are derived. Fuzzy association rules are more nature than crisp association rules for human cognition about the reality.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hong Shu, Hong Shu, Lin Dong, Lin Dong, Xinyan Zhu, Xinyan Zhu, } "Mining fuzzy association rules in spatio-temporal databases", Proc. SPIE 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA), 728541 (29 December 2008); doi: 10.1117/12.815993; https://doi.org/10.1117/12.815993
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Fuzzy feature-based image mining in remote sensing
Proceedings of SPIE (March 27 2001)
Discovering fuzzy spatial association rules
Proceedings of SPIE (March 12 2002)
An improved algorithm of a priori based on geostatistics
Proceedings of SPIE (December 29 2008)
Spatial dependencies mining based on fuzzy neural networks
Proceedings of SPIE (December 29 2008)
Identifying web usage behavior of bank customers
Proceedings of SPIE (March 12 2002)

Back to Top