No abstract

No abstract

No abstract

No abstract

Due to the rapid and exponential development of spatial databases, traditional spatial relationships and its co-locating measures have become inaccurate and inefficient. Many different spatial co-locating algorithms have been tried to detect nearest neighbor patterns within limited datasets in order to evaluate their spatial patterns. Finding co-locating patterns using skyline computational models is one of the active research areas on large spatial databases. However, most of the conventional spatial skyline co-locating models require high computational memory and time on large spatial databases.  Another limitation with traditional skyline models is finding the filtered candidate sets in the local and skyline computational models. In order to improve the accuracy of the traditional skyline models, a hybrid parallel filter based skyline model is developed on the large spatial databases to optimize data filtering along with ranking process. Experimental results describes the efficiency of proposed model on conventional skyline computational models on large databases.