关键词: 半监督学习, 土地功能分类, 不确定抽样, 轨迹数据挖掘

Abstract: In order to improve the classification accuracy and solve the problem of the difficulty of labeling social functions of the urban land, a semi-supervised urban land function classification method based on the uncertainty sampling selection strategy is proposed. The algorithm extracts the feature vector of the urban area from the trajectory data, and only a small number of areas need to be labeled. According to the uncertainty sampling active learning selection strategy, unlabeled training samples with more information data are selected and labeled by semi-supervised learning algorithm. The new labeled training samples are added to the training set. The classification results will come out after repeated iteration. Experimental results show that the proposed method can reach the accuracy rate of 90. 2% on classifying urban areas with different social functions. It has a high classification accuracy and reduces a lot of labeling work compared to traditional methods, showing a good performance on a small number of labeled data.

Key words: semi-supervised learning, uncertainty sampling, land use classification, trajectory data mining