Land Evaluation Based on Semi-supervised Learning Algorithm

In order to classify tremendous amount of unlabeled samples accurately and efficiently, a land evaluation method based on semi-supervised learning algorithm is proposed in this paper. Extracting land evaluation association rules by training a small amount of labeled samples as the supervised information, combining with the Chameleon algorithm as the unsupervised method, the method clusters a great amount of unlabeled samples, which takes full advantage of high accuracy of supervised learning classification, reduces the complexity of clustering process, and improves the facility, interpretability and accuracy for the land evaluation model. Experimental results of Guangdong Province land resource demonstrate that, by only using 300 training samples chosen randomly, 94.4184% correct area rate of land evaluation could be obtained by the semi-supervised learning algorithm. It provides a higher precision with the accuracy improved by 4.9041%, comparing with the results of the method clustering in the same condition.