摘要
针对现实中公交运行受突发路况影响,运行速度呈现非平稳性的问题,平稳化处理运行速度具有重要意义.结合时序特征处理技术和深度学习,建立一种使用自动车辆定位数据预测公交到站时间的互补集合经验模态分解(CEEMD)-长短期记忆(LSTM)神经网络模型.该模型收集公交自动车辆定位数据(AVL),经预处理后引入互补集合经验模态分解平稳化公交运行速度,再借助Adam参数寻优后的长短期记忆神经网络,对福州市303路公交某日早高峰公交到站时间进行预测.结果表明:优化的公交到站时间预测模型平均绝对误差比单一模型低了1.69 min,预测精度高于长短期记忆神经网络模型和经验模态分解的到站时间预测模型,可有效地为安装车载自动车辆定位系统的公交线路预测公交到站时间提供参考.
For the problem of actual bus operation is affected by sudden road conditions and non⁃stationary running speed of bus,stabilize the bus running speed is important.This paper proposed an optimized complementary ensemble empirical mode decomposition(CEEMD)⁃long short⁃term memory(LSTM)model for bus arrival time prediction combined with time series feature processing technology and deep learning by auto vehicle location(AVL)data.The model collects bus AVL data,then bus running speed was stabilized by CEEMD after preprocessing.Next,with the help of Adam⁃LSTM predicted the bus arrival time of Fuzhou 303 bus in morning peak of one day.Experimental results show that the MAE of optimized LSTM neural network model was lower than single LSTM model,1.69 minutes.It can be concluded that CEEMD optimized improves the prediction accuracy and can provide a reference for bus arrival time prediction.
作者
赖元文
王鈜民
LAI Yuanwen;WANG Hongmin(College of Civil Engineering,Fuzhou University,Fuzhou,Fujian 350108,China)
出处
《福州大学学报（自然科学版）》
CAS
北大核心
2023年第6期819-826,共8页
Journal of Fuzhou University(Natural Science Edition)
基金
国家自然科学基金资助项目(72201065)。
关键词
智能交通
公交到站时间预测
互补集合经验模态分解
长短期记忆
公交自动车辆定位数据
intelligent transportation
bus arrival time prediction
complementary ensemble empirical mode decomposition
long short term memory
bus auto vehicle location data
