基于误差补偿的多模态协同交通流预测模型

Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation

交通流量因受周期性特征、突发状况等多重因素影响,现有模型的预测精度无法满足实际要求.对此,本文提出了基于误差补偿的多模态协同交通流预测模型(Multimodal Collaborative traffic flow prediction model based on Error Compensation,MCEC).针对传统预测模型不能兼顾时间序列和协变量的问题,提出基于小波分析的特征拓展方法,该方法引入聚类算法得到节假日标签特征,将拥堵指数、交通事故图、天气信息作为拓展特征,对特征进行多尺度分解.在训练阶段,为达到充分学习各部分数据、最优匹配模型的效果,采用差分整合移动平均自回归模型(Autoreg Ressive Integrated Moving Average Model,ARIMA)、长短期记忆神经网络(Long Short-Term Memory network,LSTM)、限制动态时间规整技术(Dynamic Time Warping,DTW)以及自注意力机制(Self-Attention),设计了多模态协同模型训练.在误差补偿阶段,将得到的相应过程值输入基于支持向量机回归(Support Vector Regression,SVR)的误差补偿模块,对各分量的误差进行学习、补偿,并重构得到预测结果.使用公开的高速公路数据集对MCEC进行验证,在多个时间间隔下对比实验结果表明,MCEC在交通流量预测中的平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)达到17.02%,比LSTM-SVR、ConvLSTM(Convolutional Long Short-Term Memory network)、ST-GCN(Spatial Temporal Graph Convolutional Networks)、MFFB(Multi-stream Feature Fusion Block)、Transformer等预测模型具有更高的预测精度,MCEC模型具有较好的有效性与合理性.

Since the traffic flow is affected by multiple factors such as periodic characteristics and unexpected condi⁃tions,the prediction accuracy of existing models cannot satisfy the practical requirements.Under this background,this pa⁃per proposes a multimodal collaborative traffic flow prediction model based on error compensation(MCEC).To address the problem that traditional prediction models cannot take account of time series and covariates,this paper proposes a feature expansion method based on wavelet analysis,which introduces a clustering algorithm to obtain holiday labeling features,and uses congestion index,traffic accident map,and weather information as expanded features,and decomposes them on multiple scales.In the training phase,a multimodal collaborative model training was designed by adopting ARIMA(Autore⁃gRessive Integrated Moving Average)model,LSTM(Long-Short-Term Memory network),a restricted dynamic time regu⁃larization technique,and a self-attentive mechanism to achieve the effect of fully learning each part of the data and optimal⁃ly matching the model.In the error compensation stage,the obtained corresponding process values are input into the error compensation module based on SVR(Support Vector Regression)to learn and compensate the errors of each component,and reconstruct the prediction results.The MCEC is validated using a publicly available real highway data set.The results of a large number of comparison experiments at multiple time intervals show that the MAPE(Mean Absolute Percentage Er⁃ror)of MCEC in traffic flow prediction reaches 17.02%,which has a higher prediction accuracy than other prediction mod⁃els such as LSTM-SVR,ConvLSTM(Convolutional Long Short-Term Memory network),ST-GCN(Spatial Temporal Graph Convolutional Networks),MFFB(Multi-stream Feature Fusion Block),Transformer,indicating the validity and rea⁃sonableness of the MCEC model.