PROJECT TITLE :

Redundancy Reduction for Prevalent Co-Location Patterns - 2018

ABSTRACT:

Spatial co-location pattern mining is an interesting and vital task in spatial knowledge mining which discovers the subsets of spatial features frequently observed together in nearby geographic space. But, the ancient framework of mining prevalent colocation patterns produces various redundant co-location patterns, which makes it exhausting for users to understand or apply. To handle this issue, during this Project, we study the matter of reducing redundancy in an exceedingly assortment of prevalent co-location patterns by utilizing the spatial distribution info of co-location instances. We 1st introduce the concept of semantic distance between a co-location pattern and its super-patterns, and then outline redundant co-locations by introducing the concept of d-coated, where d (0 = d = one) may be a coverage measure. We tend to develop two algorithms RRclosed and RRnull to perform the redundancy reduction for prevalent co-location patterns. The former adopts the post-mining framework that's commonly used by existing redundancy reduction techniques, while the latter employs the mine-and-scale back framework that pushes redundancy reduction into the co-location mining method. Our performance studies on the synthetic and real-world knowledge sets demonstrate that our technique effectively reduces the dimensions of the initial collection of closed co-location patterns by regarding 50 p.c. Furthermore, the RRnull methodology runs abundant faster than the connected closed co-location pattern mining algorithm.