Title: A dynamic thresholding technique in spatially co-located objects mining from vehicle moving data

Authors: E. Baby Anitha; K. Duraiswamy

Addresses: Department of CSE, K.S.R College of Engineering, Tiruchengode, Namakkal District, Tamil Nadu, India ' Department of CSE, K.S. Rangasamy College of Technology, Tiruchengode, Namakkal District, Tamil Nadu, India

Abstract: Co-location pattern discovery is intended towards the processing data with spatial contexts to discover classes of spatial objects that are frequently located together. The existing moving vehicle location prediction technique not analyses the moving vehicles co-location instance. So, we improve the previous technique process by mining spatially co-located moving objects using spatial data mining techniques. Initially, the neighbour relationship is computed by the prim's algorithm. After that, the candidate co-locations are pruned according to the presence of candidate co-location in the input data and the final stage of co-location instances selection is performed by compute neighbourhood and node membership functions. The values obtained using neighbourhood membership function is compared with the dynamic threshold values. The co-location instances are selected which satisfy the dynamic threshold value. Moreover, the proposed co-location pattern mining with dynamic thresholding technique is compared with the existing co-location pattern mining technique.

Keywords: co-location patterns; neighbourhood membership; node membership; dynamic threshold; pruning; co-located objects; spatial data mining; moving vehicle location; pattern mining; moving vehicles.

DOI: 10.1504/IJBIDM.2017.082703

International Journal of Business Intelligence and Data Mining, 2017 Vol.12 No.1, pp.62 - 77

Received: 17 Aug 2016
Accepted: 10 Oct 2016
Published online: 07 Mar 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article