Computational intensity prediction model of vector data overlay with random forest method

Abstract

Spatial analysis is the core of geographic information system (GIS), of which, spatial overlay of vector data is a major job. Computational intensity of the spatial overlay has a direct effect on the overall performance of the GIS. High precision modeling for the computational intensity and analysis of the vector data overlay has been a challenging task. Thus, the paper proposes a novel approach, which utilizes self-learning and self-training features of optimized random forest algorithm to the vector data overlay analysis. Simulation experiments show that the proposed model is superior to non-optimized random forest algorithm and support vector machine model with higher prediction precision and is also capable of eliminate redundant computational intensity features.