论文部分内容阅读
采用一种新颖的神经网络-支持向量机(SVM),来预测公交车的到站时间,其目的是要验证SVM在运行时间预测领域的可行性.该模型采用了时间段、天气、路段以及当前路段的运行时间和下一路段的最新运行时间5个输入变量.最后,应用大连市开发区4路公交线对该模型进行了校验,并得到若干结论.
A novel neural network-support vector machine (SVM) is proposed to predict the arrival time of buses in order to verify the feasibility of SVM in the run-time prediction. The model uses the time segment, weather, road segments and The current section of the running time and the next section of the latest running time of the five input variables.Finally, the application of the Dalian Development Zone 4 bus lines to verify the model and get a number of conclusions.