Title: Co-location pattern mining for unevenly distributed data: algorithm, experiments and applications
Authors: Yasuhiko Morimoto
Addresses: Graduate School of Engineering, Hiroshima University, 1-7-1 Kagamiyama, Higashi Hiroshima 739-8521, Japan
Abstract: We considered co-location pattern mining algorithm that uses the Voronoi diagram. In general, the density of spatial objects is much higher in urban areas than in rural areas. The proposed algorithm is suitable for such unevenly distributed database. We have applied the co-location pattern mining algorithm for real spatial databases and show the capability of the proposed algorithm for a real spatial database. We also applied our methods for analysing web pages that contains spatial information. There are many web pages that contain spatial information such as addresses, postal codes, and telephone numbers. Most of the spatial information in web pages are location information and is unevenly distributed. We collected such web pages by web-crawling programs. For each page determined to contain location information, we apply geocoding techniques to compute geographic coordinates, such as latitude-longitude pairs. Next, we augment the location information with keyword descriptors extracted from the web page contents. We then apply co-location mining on the augmented location information.
Keywords: spatial data mining; co-location patterns; Voronoi diagrams; unevenly distributed data; location-based services; pattern mining; spatial information; addresses; post codes; telephone numbers; location information; geocoding.
International Journal of Computational Science and Engineering, 2010 Vol.5 No.3/4, pp.185 - 196
Available online: 24 Dec 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article