城市快速路区间旅行时间短期预测新算法

城市道路交通状况的预测，是实现未来路况查询、车辆动态导航等智能交通系统技术的关键。该文在分析浮动车数据的时间相关性的基础上，研究城市快速路的区间旅行时间短期预测算法。首先，采用统计方法和K-NN分类法相结合的新方法对缺失数据进行填充，并利用小波变换对每天的数据进行消噪处理；其次，在分别利用时间序列模型和人工神经网络模型对城市快速路区间旅行时间进行短期预测的基础上，通过模型组合获得预测值；最后，结合北京市区二环的一段快速路区间旅行时间的历史数据和实时数据，对该文所提出的快速路区间旅行时间短期预测算法进行了评价。结果显示，该算法的预测结果的平均绝对误差百分比控制在10.43%以内，具有良好的精度。

A New Algorithm of Short-term Travel Time Prediction for Urban Expressway

The prediction of urban road traffic status is a key to achieve ITS technologies such as future road traffic information query platform and dynamic route guidance system. It studied the algorithm of short-term travel time prediction, based on the analysis of temporal correlation of floating car data collected from urban expressway. First, the missing data was complemented with a new method which combined statistical method and K-NN classification approach, and data de-noising based on wavelet transformation approach was executed. Second, the final result was estimated, based on the short-term travel time prediction results forecasted with time series model and artificial neural network model respectively. Finally, using the data collected from the 2nd Ring Expressway in Beijing, the proposed algorithm was evaluated. The results show that the mean absolute percentage error （MAPE） is limited in 10.43% successfully, and the algorithm is expected to have a good performance in short-term travel time prediction.