Prediction of the Unused Land for Construction Based on Multi-classifier Fusion

For current situation in urban areas in China, there are a large number of unused lands or inefficient lands for construction, which leads to a waste of massive land resources. For the idle land and inefficient land, the traditional way to solve the problems is spatial overlay analysis of the information about the usage of land of existing problem. In this paper, a method of prediction of the unused land for construction based on multi-classifier fusion is introduced. The multi-classifier fuses three types of classifier: naïve Bayes classifier, Random Forest classifier, and SVM classifier. By the algorithm of multi-classifier, unused land for construction can be discovered in advance and achieve prediction goal.