Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation

WU Yu-xuan; YU Hui-qun; FAN Gui-sheng

doi:10.12263/DZXB.20230523

您当前的位置：

首页 >

文章列表页 >

Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation

PAPERS | 更新时间：2025-12-08

- Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation
- ACTA ELECTRONICA SINICA Vol. 52, Issue 8, Pages: 2878-2890(2024)
- 作者机构：
  
  华东理工大学计算机科学与工程系，上海 200237
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62276097)
- DOI：10.12263/DZXB.20230523
  CLC： TP183;TP181
- Received：08 June 2023，
  
  Revised：2024-01-17，
  
  Published：25 August 2024
- 稿件说明：
移动端阅览
吴宇轩, 虞慧群, 范贵生. 基于误差补偿的多模态协同交通流预测模型[J]. 电子学报, 2024, 52(08): 2878-2890.

WU Yu-xuan, YU Hui-qun, FAN Gui-sheng. Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation[J]. Acta Electronica Sinica, 2024, 52(08): 2878-2890.
吴宇轩, 虞慧群, 范贵生. 基于误差补偿的多模态协同交通流预测模型[J]. 电子学报, 2024, 52(08): 2878-2890. DOI：10.12263/DZXB.20230523

WU Yu-xuan, YU Hui-qun, FAN Gui-sheng. Multimodal Cooperative Traffic Flow Prediction Model Based on Error Compensation[J]. Acta Electronica Sinica, 2024, 52(08): 2878-2890. DOI：10.12263/DZXB.20230523

摘要

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.

Abstract

Since the traffic flow is affected by multiple factors such as periodic characteristics and unexpected conditions

the prediction accuracy of existing models cannot satisfy the practical requirements. Under this background

this paper 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 (AutoregRessive Integrated Moving Average) model

LSTM (Long-Short-Term Memory network)

a restricted dynamic time regularization technique

and a self-attentive mechanism to achieve the effect of fully learning each part of the data and optimally 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 Error) of MCEC in traffic flow prediction reaches 17.02%

which has a higher prediction accuracy than other prediction models 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 reasonableness of the MCEC model.

关键词

Keywords

references

郭玉坤 , 李永政 . 国外公共交通导向型城市发展研究综述: 基于建筑环境对公共交通客流量影响的视角 [J ] . 城市问题 , 2014 ( 7 ): 26 - 31 .

GUO Y K , LI Y Z . Research review on foreign TOD urban development: Based on the perspective of influences on transit ridership by built environment [J ] . Urban Problems , 2014 ( 7 ): 26 - 31 . (in Chinese)

MILLER I , CAMPBELL M . Sensitivity analysis of a tightly-coupled GPS/INS system for autonomous navigation [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2012 , 48 ( 2 ): 1115 - 1135 .

高海军 , 王健 , 陈龙 , 等 . 空中交通流量管理研究综述 [J ] . 控制工程 , 2003 , 10 ( 6 ): 484 - 487, 517 .

GAO H J , WANG J , CHEN L , et al . Review on the research of air traffic flow management [J ] . Control Engineering of China , 2003 , 10 ( 6 ): 484 - 487, 517 . (in Chinese)

王晓宇 , 赵鹏 , 陈莹锋 . 新基建下的智能交通系统发展综述 [J ] . 上海公路 , 2022 , 2 : 91-95, 167-168 .

WANG X Y , ZHAO P , CHEN Y F . Development of ITS under new infrastructure [J ] . Shanghai Highways , 2022 , 2: 91-95, 167-168 . (in Chinese)

赵娜 , 袁家斌 , 徐晗 . 智能交通系统综述 [J ] . 计算机科学 , 2014 , 41 ( 11 ): 7 - 11, 45 .

ZHAO N , YUAN J B , XU H . Survey on intelligent transportation system [J ] . Computer Science , 2014 , 41 ( 11 ): 7 - 11, 45 . (in Chinese)

邵虎 , 卓越 , 刘鹏杰 , 等 . 城市交通流量估计的运筹学方法 [J ] . 运筹学学报 , 2023 , 27 ( 2 ): 27 - 48 .

SHAO H , ZHUO Y , LIU P J , et al . Operational research methods for urban traffic flow estimation [J ] . Operations Research Transactions , 2023 , 27 ( 2 ): 27 - 48 . (in Chinese)

胡冰华 . 基于时空数据的交通流量预测神经网络算法研究综述 [J ] . 计算机产品与流通 , 2023 ( 3 ): 95 - 97 .

HU B H . A review of neural network algorithms for traffic flow prediction based on spatio-temporal data [J ] . Computer Products and Circulation , 2023 ( 3 ): 95 - 97 . (in Chinese)

陆化普 , 孙智源 , 屈闻聪 . 大数据及其在城市智能交通系统中的应用综述 [J ] . 交通运输系统工程与信息 , 2015 , 15 ( 5 ): 45 - 52 .

LU H P , SUN Z Y , QU W C . Big data and its applications in urban intelligent transportation system [J ] . Journal of Transportation Systems Engineering and Information Technology , 2015 , 15 ( 5 ): 45 - 52 . (in Chinese)

DAI G W , MA C X , XU X C . Short-term traffic flow prediction method for urban road sections based on space-time analysis and GRU [J ] . IEEE Access , 2019 , 7 : 143025 - 143035 .

MACKENZIE J , RODDICK J F , ZITO R . An evaluation of HTM and LSTM for short-term arterial traffic flow prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2019 , 20 ( 5 ): 1847 - 1857 .

WAGNER-MUNS I M , GUARDIOLA I G , SAMARANAYKE V A , et al . A functional data analysis approach to traffic volume forecasting [J ] . IEEE Transactions on Intelligent Transportation Systems , 2018 , 19 ( 3 ): 878 - 888 .

殷礼胜 , 唐圣期 , 李胜 , 等 . 基于整合移动平均自回归和遗传粒子群优化小波神经网络组合模型的交通流预测 [J ] . 电子与信息学报 , 2019 , 41 ( 9 ): 2273 - 2279 .

YIN L S , TANG S Q , LI S , et al . Traffic flow prediction based on hybrid model of auto-regressive integrated moving average and genetic particle swarm optimization wavelet neural network [J ] . Journal of Electronics & Information Technology , 2019 , 41 ( 9 ): 2273 - 2279 . (in Chinese)

王圆 . 基于SARIMA和LSTM模型的智慧城市车流量预测 [D ] . 湘潭 : 湘潭大学 , 2020 .

WANG Y . Based on SARIMA and LSTM Model Smart City Traffic Forecast [D ] . Xiangtan : Xiangtan University , 2020 . (in Chinese)

吴正 . 交通流的动力学模拟与测量方法 [J ] . 复旦学报(自然科学版) , 1991 , 30 ( 1 ): 111 - 117 .

WU Z . Traffic flow dynamic modeling [J ] . Journal of Fudan University , 1991 , 30 ( 1 ): 111 - 117 . (in Chinese)

刘美琪 , 焦朋朋 , 孙拓 . 城市轨道交通进站客流量短时预测模型研究 [J ] . 城市轨道交通研究 , 2015 , 18 ( 11 ): 13 - 17, 29 .

LIU M Q , JIAO P P , SUN T . On short-term forecasting model of passenger flow in urban rail transit [J ] . Urban Mass Transit , 2015 , 18 ( 11 ): 13 - 17, 29 . (in Chinese)

TERESA PAMUŁ A . Road traffic parameters prediction in urban traffic management systems using neural networks [J ] . Transport Problems , 2011 , 6 ( 3 ): 123 - 128 .

乔松林 , 孙仁诚 , 刘吉 . 基于深度学习的短时交通流量预测 [J ] . 青岛大学学报(自然科学版) , 2017 , 30 ( 4 ): 65 - 69 .

QIAO S L , SUN R C , LIU J . Short-term traffic flow forecast based on deep learning [J ] . Journal of Qingdao University (Natural Science Edition) , 2017 , 30 ( 4 ): 65 - 69 . (in Chinese)

王金锋 , 孙连英 , 张天 , 等 . 基于K-LSTM-ecm模型的城市轨道交通短时客流预测 [J ] . 制造业自动化 , 2022 , 44 ( 5 ): 103 - 107, 133 .

WANG J F , SUN L Y , ZHANG T , et al . Short-term passenger flow prediction of urban rail transit based on K-LSTM-ecm model [J ] . Manufacturing Automation , 2022 , 44 ( 5 ): 103 - 107, 133 . (in Chinese)

ZHANG L Z , ALHARBE N R , LUO G C , et al . A hybrid forecasting framework based on support vector regression with a modified genetic algorithm and a random forest for traffic flow prediction [J ] . Tsinghua Science and Technology , 2018 , 23 ( 4 ): 479 - 492 .

周兰庭 , 柳志坤 , 徐长华 . 基于WA-LSTM-ARIMA的混凝土坝变形组合预测模型 [J ] . 人民黄河 , 2022 , 44 ( 1 ): 124 - 128 .

ZHOU L T , LIU Z K , XU C H . Concrete dam deformation combination prediction based on WA-LSTM-ARIMA [J ] . Yellow River , 2022 , 44 ( 1 ): 124 - 128 . (in Chinese)

杨丽 . 小波理论在大坝变形监测数据分析中的应用研究 [D ] . 西安 : 西安理工大学 , 2010 .

YANG L . Applied Research of Wavelet Theory in Dam Deformation Monitoring Data Analysis [D ] . Xi’an : Xi’an University of Technology , 2010 . (in Chinese)

王新洲 , 范千 , 许承权 , 等 . 基于小波变换和支持向量机的大坝变形预测 [J ] . 武汉大学学报(信息科学版) , 2008 , 33 ( 5 ): 469 - 471, 507 .

WANG X Z , FAN Q , XU C Q , et al . Dam deformation prediction based on wavelet transform and support vector machine [J ] . Geomatics and Information Science of Wuhan University , 2008 , 33 ( 5 ): 469 - 471, 507 . (in Chinese)

陈娇娜 , 陶伟俊 , 靳引利 , 等 . 多模态文本信息的高速公路交通事件持续时间预测 [J ] . 中国安全生产科学技术 , 2023 , 19 ( 6 ): 180 - 186 .

CHEN J N , TAO W J , JIN Y L , et al . Prediction of traffic incident duration on expressway based on multimodal text information [J ] . Journal of Safety Science and Technology , 2023 , 19 ( 6 ): 180 - 186 . (in Chinese)

张轶 , 翟盛华 , 陶海红 . 雨衰时间序列的混沌识别与预测 [J ] . 电子学报 , 2023 , 51 ( 2 ): 365 - 371 .

ZHANG Y , ZHAI S H , TAO H H . Chaos identification and prediction for rain attenuation time series [J ] . Acta Electronica Sinica , 2023 , 51 ( 2 ): 365 - 371 . (in Chinese)

张聿远 , 闫文君 , 张立民 . 基于多模态特征融合网络的空时分组码识别算法 [J ] . 电子学报 , 2023 , 51 ( 2 ): 489 - 498 .

ZHANG Y Y , YAN W J , ZHANG L M . Space-time block code recognition algorithm based on multi-modality features fusion network [J ] . Acta Electronica Sinica , 2023 , 51 ( 2 ): 489 - 498 . (in Chinese)

张若楠 , 安高云 . 基于多模态特征转换嵌入的场景图生成 [J ] . 信号处理 , 2023 , 39 ( 1 ): 51 - 60 .

ZHANG R N , AN G Y . Multimodal feature translating embedding based scene graph generation [J ] . Journal of Signal Processing , 2023 , 39 ( 1 ): 51 - 60 . (in Chinese)

杨真真 , 孙雪 , 邵静 , 等 . 基于多尺度偶数卷积注意力U-Net的医学图像分割 [J ] . 信号处理 , 2022 , 38 ( 9 ): 1912 - 1921 .

YANG Z Z , SUN X , SHAO J , et al . Medical image segmentation based on multiscale even convolution attention U-Net [J ] . Journal of Signal Processing , 2022 , 38 ( 9 ): 1912 - 1921 . (in Chinese)

周隽杰 , 付东翔 . 基于Attention-LSTM-Kalman建模的风洞动态流量软测量 [J ] . 数据采集与处理 , 2022 , 37 ( 2 ): 463 - 470 .

ZHOU J J , FU D X . Soft measurement of wind tunnel dynamic flow based on Attention‑LSTM-Kalman modeling [J ] . Journal of Data Acquisition and Processing , 2022 , 37 ( 2 ): 463 - 470 . (in Chinese)

刘宜成 , 李志鹏 , 吕淳朴 , 等 . 基于动态时间调整的时空图卷积路网交通流量预测 [J ] . 交通运输系统工程与信息 , 2022 , 22 ( 3 ): 147 - 157, 178 .

LIU Y C , LI Z P , LV C P , et al . Network-wide traffic flow prediction research based on DTW algorithm spatial-temporal graph convolution [J ] . Journal of Transportation Systems Engineering and Information Technology , 2022 , 22 ( 3 ): 147 - 157, 178 . (in Chinese)

LU H P , YANG F . A network traffic prediction model based on wavelet transformation and LSTM network [C ] // 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS) . Piscataway : IEEE , 2018 : 1 - 4 .

TIAN Y X , PAN L . Predicting short-term traffic flow by long short-term memory recurrent neural network [C ] // 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity) . Piscataway : IEEE , 2015 : 153 - 158 .

张峻屹 , 李双金 , 马爽 . 基于市民生活行为学的交通行为研究综述 [J ] . 交通运输系统工程与信息 , 2022 , 22 ( 2 ): 1 - 16, 63 .

ZHANG J Y , LI S J , MA S . Overview of life-oriented travel behavior research [J ] . Journal of Transportation Systems Engineering and Information Technology , 2022 , 22 ( 2 ): 1 - 16, 63 . (in Chinese)

LI T , ZHANG J B , BAO K N , et al . AutoST: Efficient neural architecture search for spatio-temporal prediction [C ] // Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2020 : 794 - 802 .

李文静 , 王潇潇 . 基于简化型LSTM神经网络的时间序列预测方法 [J ] . 北京工业大学学报 , 2021 , 47 ( 5 ): 480 - 488 .

LI W J , WANG X X . Time series prediction method based on simplified LSTM neural network [J ] . Journal of Beijing University of Technology , 2021 , 47 ( 5 ): 480 - 488 . (in Chinese)

王英伟 , 马树才 . 基于ARIMA和LSTM混合模型的时间序列预测 [J ] . 计算机应用与软件 , 2021 , 38 ( 2 ): 291 - 298 .

WANG Y W , MA S C . Time series forecasting based on ARIMA_DLSTM hybrid model [J ] . Computer Applications and Software , 2021 , 38 ( 2 ): 291 - 298 . (in Chinese)

SONG X , LI W J , MA D F , et al . A match-then-predict method for daily traffic flow forecasting based on group method of data handling [J ] . Computer-Aided Civil and Infrastructure Engineering , 2018 , 33 ( 11 ): 982 - 998 .

SHI X J , CHEN Z R , WANG H , et al . Convolutional LSTM network: A machine learning approach for precipitation nowcasting [C ] // Proceedings of the 28th International Conference on Neural Information Processing Systems . New York : ACM , 2015 : 802 - 810 .

BING Y , YIN H T , ZHU Z X . Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting [EB/OL ] .( 2017-09-14 )[ 2024-01-03 ] . http://arrived.org/abs/1709.04875 http://arrived.org/abs/1709.04875 .

LI Z S , XIONG G , TIAN Y L , et al . A multi-stream feature fusion approach for traffic prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 2 ): 1456 - 1466 .

LI G Y , ZHONG S H , DENG X D , et al . A lightweight and accurate spatial-temporal transformer for traffic forecasting [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 11 ): 10967 - 10980 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Traffic Flow Prediction of Digital Twin Based on Two-Graph Convolution Mechanism

Grey Wolf Optimization Based on Opposition Learning and Its Application in Traffic Flow Forecasting

A Novel Dynamic Path Optimization Method for Urban Traffic Networks

Related Author

HU Chun-hua

ZENG E-lan

RONG Hui-gui

ZHU Sheng-qi

QU Yi

YANG Zhi-wei

LIAO Gui-sheng

LIU Xiang-yang

Related Institution

School of Artificial Intelligence and Advanced Computing

Xiangjiang Laboratory

Changsha Social Laboratory of Artiﬁcial Intelligence, Hunan University of Technology and Business

College of Information Science and Engineering, Hunan University

Department of Communication EngineeringEngineering College of Armed Police ForceXi’anShaanxi 710086China

⁰