Optimal candidate generation in spatial co-location mining

Abstract

Existing spatial co-location algorithms based on levels suffer from generating extra, nonclique candidate instances. Thus, they require cliqueness checking at every level. In this thesis, a novel, spatial co-location mining algorithm that automatically generates co-located spatial features without generating any nonclique candidates at any level is proposed. Subsequently, this algorithm generates fewer candidates than other existing level-wise, co-location algorithms without losing any pertinent information. The benefits of this algorithm have been clearly observed at early stages in the mining process.(77 pages) iv ACKNOWLEDGMENTS

2-D and 3-D Visualization of Many-to-Many Relationships

“…Examples of binary relationship include the gravitation between two masses in physics, symbiotic organisms in biology, term co-occurrence in information retrieval, co-citation [5] in bibliographic coupling studies, spatial co-location [6] in spatial data mining, frequent 2-itemsets in association mining, and friend relationship between two persons in social networks.…”