基于ε-支持向量机回归的快速公交到站时间预测

(1.厦门大学信息科学与技术学院,福建 厦门 361005; 2.福建信息职业技术学院,福建 福州 350003)

支持向量机回归; 快速公交; 到站时间; 停靠时间; 车头时距

The Bus Rapid Transit Arrival Time Prediction Based on ε-SVR
ZHANG Yang1,2*,CHENG En1

(1.School of Information Science and Engineering,Xiamen University,Xiamen 361005,China; 2.Fujian Polytechnic of Information Technology,Fuzhou 350003,China)

support vector regression; bus rapid transit; arrival time; stop time; headway

DOI: 10.6043/j.issn.0438-0479.201606039

备注

选择ε-支持向量机回归(ε-SVR)算法预测快速公交(BRT)车辆的到站时间,以提高公共交通的准点性.分别对BRT的停靠时间和路段行驶时间建立模型.根据分析,在停靠站时间预测建模过程中选取车头时距、时段、天气等7维特征向量作为模型输入,采用人工调查法,对厦门BRT-1路的数据进行采集,归一化处理后建模.仿真结果显示该模型能够比较准确地预测厦门BRT-1路的运行路线到站时间,并验证天气因素对该线路的到站时间预测影响最大.

In this article,we select ε-support vector machine regression(ε-SVR)algorithm to predict the bus rapid transit(BRT)arrival time,in order to improve the public transport on time.The bus stop time and road travel time models are established.During the modeling process,seven dimensional features such as the headway,time,weather etc.,are chosen as model inputs.Artificial investigation method is used to collect the data of Xiamen BRT-1.These data are normalized during the modeling process.Simulation results show that the model can accurately predict bus running time of Xiamen BRT-1.Results verify that weather factors exert the highest influence on the arrival time of Xiamen BRT-1.