Air traffic flow prediction based on k nearest neighbor regression

In order to improve the prediction accuracy of air traffic flow, a method of applying k nearest neighbor regression to air traffic flow prediction is proposed, and the relevant problems, such as the flow data preprocess and the estimate value generation, are discussed. Based on the real flow data of Beijing terminal corridors, the proposed method is compared with support vector regression by experiments. The experiment results show that, the proposed method outperforms the support vector regression on all the prediction evaluating indicators.