基于ETC收费数据的高速公路交通流数据修复及实时预测

doi:10.6040/j.issn.1672-3961.0.2024.082

摘要/Abstract

摘要： 通过填补缺失数据提升交通流数据质量,对高速公路交通流数据进行准确实时预测,本研究首先采用低秩张量分解理论对缺失数据进行修复,利用基于注意力机制的卷积长短期记忆神经网络构建预测模型,并使用山东省高速公路收费系统实际交通流数据对本研究提出的方法进行验证。结果表明:通过对缺失数据进行分类识别,利用混淆矩阵确定识别缺失数据的阈值,引入三维张量模型采用低秩张量补全方法进行缺失数据修复,相较于拉格朗日插值法、KNN以及SVR方法,本方法修复数据效果最优;本研究提出的交通流组合预测模型,相较于SVR、CNN、LSTM和CNN-LSTM四种预测方法,在不同路段、工作日和非工作日均具有更高的预测精度,流量预测的均方误差M_SE和平均绝对百分比误差M_APE分别下降22.47%和8.41%,平均速度预测的M_SE和M_APE分别下降42.83%和6.32%。本研究提出的模型为高速公路交通状态预测方法研究提供了新思路。

关键词: 高速公路, 交通数据修复, 时空相关性, 交通流参数预测, 深度学习

Abstract: By imputing missing data to enhance the quality of traffic flow data, accurate real-time predictions for highway traffic flow can be achieved. This study adopted the low-rank tensor decomposition theory to repair the missing data and used the convolutional long and short term memory neural network based on the attention mechanism to build a prediction model. The actual traffic flow data of the Shandong expressway toll system were used to verify the method proposed in this study. The experimental results showed that: by classifying and identifying missing data, using the confusion matrix to determine the threshold of identifying missing data, introducing the three-dimensional tensor model, and using the low-rank tensor completion method to repair missing data, the data repair effect was the best compared with Lagrange interpolation, KNN, and SVR methods. Compared with SVR, CNN, LSTM, and CNN-LSTM, the combined traffic flow prediction model proposed in this study had higher prediction accuracy in different road sections, working days, and non-working days, and the M_SE and M_APE of traffic prediction decreased by 22.47% and 8.41%, respectively. The average speed forecast for M_SE and M_APE decreased by 42.83% and 6.32%, respectively. The proposed model provided new ideas for research on highway traffic state prediction methods.

Key words: expressways, traffic data repair, spatiotemporal correlation, traffic flow parameter prediction, deep learning

中图分类号:

U491.1+4

薛冰冰,王勇,杨维浩,王川,于迪,王旭. 基于ETC收费数据的高速公路交通流数据修复及实时预测[J]. 山东大学学报 (工学版), 2025, 55(3): 58-71.

XUE Bingbing, WANG Yong, YANG Weihao, WANG Chuan, YU Di, WANG Xu. Real-time expressway traffic data imputation and state prediction based on ETC system data[J]. Journal of Shandong University(Engineering Science), 2025, 55(3): 58-71.

参考文献

[1] 交通运输部. 2022年交通运输行业发展统计公报[N/OL]. 中国交通报,2023-06-16[2025-03-18].https://xxgk.mot.gov.cn/2020/jigou/zhghs/202306/t20230615_3847023.htm
[2] 李世忠. ETC门架车牌识别及交易数据上传不及时问题探讨[J]. 中国交通信息化, 2020(10): 112-116. LI Shizhong. Discussion on the delayed upload of ETC gantry license plate recognition and transaction data [J]. China Transportation Informatization, 2020(10): 112-116.
[3] 张涛, 张健, 祁欣月, 等. 交通缺失数据插补方法研究综述[J]. 现代交通与冶金材料, 2023, 3(4): 69-81. ZHANG Tao, ZHANG Jian, QI Xinyue, et al. A review of imputation methods for missing traffic data[J]. Modern Transportation and Metallurgical Materials, 2023, 3(4): 69-81.
[4] RABBANI M B A, MUSARAT M A, ALALOUL W S, et al. A comparison between seasonal autoregressive integrated moving average(SARIMA)and exponential smoothing(ES)based on time series model for forecasting road accidents[J]. Arabian Journal for Science and Engineering, 2021, 46(11): 11113-11138.
[5] 许书红, 王雯雯, 冯远宏, 等. 交通流数据时空相关修复方法评价分析[J]. 武汉理工大学学报(交通科学与工程版), 2023, 47(3): 408-413. XU Shuhong, WANG Wenwen, FENG Yuanhong, et al. Evaluation and analysis of spatiotemporal correlation repair methods for traffic flow data[J]. Journal of Wuhan University of Technology(Transportation Science and Engineering Edition), 2023, 47(3): 408-413.
[6] 孟闯, 王慧, 林浩, 等. 道路交通流数据预测方法研究综述[J]. 计算机工程与应用, 2023, 59(14): 51-61. MENG Chuang, WANG Hui, LIN Hao, et al. Review of research on prediction methods for road traffic flow data[J]. Computer Engineering and Applications, 2023, 59(14): 51-61.
[7] 张潇潇, 龚龑. 基于LSTM的沪渝高速公路短时交通流预测研究[J]. 中国交通信息化, 2022(9): 133-137. ZHANG Xiaoxiao, GONG Yan. Research on short-term traffic flow prediction of huyu expressway based on LSTM[J]. China Transportation Informatization, 2022(9): 133-137.
[8] 韦佳. 基于时空特性的城市道路交通运行状态预测及评价方法研究[D]. 广州:华南理工大学, 2020. WEI Jia. Research on prediction and evaluation methods of urban road traffic operation status based on spatiotemporal characteristics [D]. Guangzhou:South China University of Technology, 2020.
[9] 黄来荣, 谷庆, 林凤榕, 等. 基于深度学习的高速公路交通速度预测模型研究[J]. 中国交通信息化, 2022(9): 129-132. HUANG Lairong, GU Qing, LIN Fengrong, et al. Research on highway traffic speed prediction model based on deep learning[J]. China Transportation Infor-matization, 2022(9): 129-132.
[10] KARLAFTIS M G, VLAHOGIANNI E I. Statistical methods versus neural networks in transportation research: differences, similaritiesand some insights[J]. Transportation Research Part C-Emerging Technologies, 2011, 19(3): 387-399.
[11] 赵怀鑫, 邓然然, 张英杰, 等. 一种用于高速公路通行情况分析的收费数据挖掘方法[J]. 中国公路学报, 2018, 31(8): 155-164. ZHAO Huaixin, DENG Ranran, ZHANG Yingjie, et al. A toll data mining method for analyzing highway traffic conditions[J]. China Journal of Highway and Transport, 2018, 31(8): 155-164.
[12] DUAN Y, LV Y, LIU Y L, et al. An efficient realization of deep learning for traffic data imputation[J]. Transportation Research Part C-Emerging Technologies, 2016, 72: 168-181.
[13] 唐莺萍, 商强. 基于GPS数据的高速公路行程时间估计与可靠性分析[J]. 山东理工大学学报(自然科学版), 2024, 38(3): 14-19. TANG Yingping, SHANG Qiang. Estimation and reliability analysis of highway travel time based on GPS data[J]. Journal of Shandong University of Technology(Natural Science Edition), 2024, 38(3): 14-19.
[14] HAY A M. The derivation of global estimates from a confusion matrix[J]. International Journal of Remote Sensing, 1988, 9(8): 1395-1398.
[15] 李琳, 王培培, 谷鹏, 等. 基于LU分解和交替最小二乘法的分布式奇异值分解推荐算法[J]. 模式识别与人工智能, 2020, 33(1): 32-40. LI Lin, WANG Peipei, GU Peng, et al. A distributed singular value decomposition recommendation algorithm based on LU decomposition and alternating least squares[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(1): 32-40.
[16] 张晓飞. 解张量分解问题的信赖域交替最小二乘法[D]. 南京:南京师范大学, 2014. ZHANG Xiaofei. A trust-region alternating least squares method for solving tensor decomposition problems[D]. Nanjing:Nanjing Normal University, 2014.
[17] 王昕. 梯度下降及优化算法研究综述[J]. 电脑知识与技术, 2022, 18(8): 71-73. WANG Xin. A review of gradient descent and optimization algorithms[J]. Computer Knowledge and Technology, 2022, 18(8): 71-73.
[18] WU J, WANG Z, WU Y, et al. A tensor cp decomposition method for clustering heterogeneous information networks via stochastic gradient descent algorithms[J]. Scientific Programming, 2017, 28(3): 1058-1071.
[19] SHENG X, WEN Q, FAN L, et al. Low-rank tensor completion by truncated nuclear norm regularization[J]. 2018 24th International Conference on Pattern Recognition(ICPR), 2018: 2600-2605.
[20] 季长清, 高志勇, 秦静, 等. 基于卷积神经网络的图像分类算法综述[J]. 计算机应用, 2022, 42(4): 1044-1049. JI Changqing, GAO Zhiyong, QIN Jing, et al. A review of image classification algorithms based on convolutional neural networks[J]. Journal of Computer Applications, 2022, 42(4): 1044-1049.
[21] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997,9(8):1735-1780.
[22] 常昊. 基于LSTM神经网络的地铁短时客流量预测研究[D]. 西安:西京学院, 2022. CHANG Hao. Research on short-term passenger flow prediction of subway based on LSTM neural network[D]. Xi'an: Xijing University, 2022.
[23] ZHANG G, ZHU S, BAI X. Federated learning-based multi-energy load forecasting method using CNN-Attention-LSTM model[J]. Sustainability, 2022, 14(19): 12843-12857.
[24] LAN T, ZHANG X, QU D, et al. Short-Term traffic flow prediction based on the optimization study of initial weights of the attention mechanism[J]. Sustainability, 2023, 15(2): 1374-1390.
[25] XU C, ZHANG Z, FU F, et al. Analysis of spatiotemporal factors affecting traffic safety based on multisource data fusion[J]. Journal of Transportation Engineering Part A-Systems, 2023, 149(10): 1653- 1662.
[26] XUE B, WANG X, HAN Z. A combined short- and medium-term traffic flow prediction method for proactive traffic control at expressway toll stations[J]. Canadian Journal of Civil Engineering, 2024, 51(11): 1226-1239.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed