基于SVM和Kalman滤波的公交车到站时间预测模型

Bus Arrival Time Prediction Model Based on Support Vector Machine and Kalman Filter

提出一种基于支持向量机(SVM)和Kalman滤波的公交车辆到站时间预测模型。在该模型中,SVM基于历史数据,按照时间段、天气和路段3个输入特性,预测各路段车辆运行时间的基线;然后通过Kalman滤波利用最新的车辆运行信息,结合SVM输出的基线时间来动态预测车辆到达各时间点的实际时间;最后,应用大连市经济技术开发区7路公交线的数据对该模型进行了校验。实例验证结果表明:该模型具有较高的预测精度。

Authors presented the bus arrival time prediction model based on support vector machine （SVM） and Kalman filter technique. The SVM which had three input features including, time-of-day, weather and segment was used to predict the baseline of bus running time from historical trip data. Applying the newest bus running information, combined with baseline time of SVM input, Kalman filter was used to predict bus arrival time dynamically. Bus arrival time forecasted by the proposed model was assessed with the data of transit route number 7 in Dalian Economic and Technological Development Zone in China. Results show that the model is a powerful tool for bus arrival time prediction.