利用时变经验模态分解的主干道短时交通量预测

doi:10.3969/j.issn.1674-0696.2022.03.06

摘要/Abstract

摘要： 为描述短时交通量数据中隐藏的非线性与非平稳特性，提高短时交通量的预测精度，进而更好地构建智能交通平台，提出了一种基于时变滤波经验模态分解(TVF-EMD)与最小二乘支持向量机(LSSVM)的混合预测模型，即TVF-EMD-LSSVM模型。其中：TVF-EMD方法主要用来降低数据中暗含的非平稳性对预测结果影响；LSSVM模型是为了描摹数据中包含的非线性信息演化趋势。研究结果表明：相比经验模态分解(EMD)方法而言，TVF-EMD方法的分解结果更加适合交通流预测；该分解技术与LSSVM模型的结合可提供更好的预测结果，相比LSSVM模型而言，其平均绝对误差、平均相对百分比误差、均方根误差和均方根相对误差分别降低了9.186、18.947%、13.591、0.316%，且均等系数提高了0.082 1。

关键词: 交通工程；短时交通量预测；时变滤波经验模态分解；最小二乘支持向量机；时间序列

Abstract: In order to describe the hidden non-linear and non-stationary characteristics in the short-time traffic data, improve the prediction accuracy of short-time traffic, and then better build an intelligent transportation platform, a hybrid prediction model based on time-varying filtered empirical modal decomposition (TVF-EMD) and least-squares support vector machine (LSSVM), i.e., the TVF-EMD-LSSVM model, was proposed. Among the TVF-EMD-LSSVM model, the TVF-EMD method was mainly used to reduce the influence of the non-stationarity implied in the data on the prediction results, while the LSSVM model was designed to trace the evolutionary trend of the non-linear information contained in the data. The research results show that compared with empirical mode decomposition (EMD), the decomposition results of TVF-EMD method are more suitable for traffic flow prediction. Meanwhile, the combination of this decomposition technique and LSSVM model can provide better prediction results. Compared with LSSVM model, the mean absolute error, mean relative percentage error, root mean square error and root mean square relative error of the proposed model are reduced by 9.186, 18.947%, 13.591 and 0.316% respectively, and its equalization coefficient is increased by 0.082 1.

Key words: traffic engineering; short-term traffic volume prediction; TVF-EMD; LSSVM; time series

中图分类号:

U491

赵磊娜1,2，王延鹏2，邵毅明2，李淑庆2，温欣雨1. 利用时变经验模态分解的主干道短时交通量预测[J]. 重庆交通大学学报（自然科学版）, 2022, 41(03): 37-44.

ZHAO Leina1,2, WANG Yanpeng2, SHAO Yiming2, LI Shuqing2, WEN Xinyu1. Short-Term Traffic Volume Prediction of Arterial Road Using TVF-EMD Method[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(03): 37-44.

参考文献

［1］ ZHONG Renxin, LUO J C, CAI H X, et al. Forecasting journey time distribution with consideration to abnormal traffic conditions［J］. Transportation Research Part C:
Emerging Technologies, 2017, 85: 292-311.
［2］唐坤.数据驱动的城市路网行程时间估计与预测方法研究［D］.南京：东南大学，2019.
TANG Kun. Research on Data-Driven Travel Time Estimation and Prediction in Urban Road Network［D］. Nanjing: Southeast University, 2019.
［3］ DAVIS G A, NIHAN N L. Using time-series designs to estimate changes in freeway level of service, despite missing data［J］.Transportation Research Part A: General,
1984, 18(5/6): 431-438.
［4］ KUMAR S V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data［J］.European Transport Research Review, 2015,
7: 1-9.
［5］ ZHAO Zheng, CHEN Weihai, YUE Haosong, et al. A novel short-term traffic forecast model based on travel distance estimation and ARIMA［C］∥ 2016 Chinese
Control and Decision Conference(CCDC). IEEE, 2016: 6270-6275.
［6］ YANG Zhaosheng, BING Qichun, LIN Ciyun, et al. Research on short-term traffic flow prediction method based on similarity search of time series［J］. Mathematical
Problems in Engineering, 2014: 1-8.
［7］ WANG Yibing, PAPAGEORGIOU M. Real-time freeway traffic state estimation based on extended Kalman filter: A general approach［J］. Transportation Research
Part B: Methodological, 2005, 39(2): 141-167.
［8］ OKUTANI I, STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory［J］.Transportation Research Part B: Methodological, 1984, 18
(1): 1-11.
［9］ WILLIAMS B M, DURVASULA A P, BROWN D. Urban freeway traffic flow prediction: Application of seasonal autoregressive integrated moving average and
exponential smoothing models［J］.Journal of the Transportation Research Record, 1998, 1644(1): 132-141.
［10］ KANDIL N, WAMKEUE R, SAAD M, et al. An efficient approach for short term load forecasting using artificial neural networks［J］.International Journal of Electrical
Power & Energy Systems, 2006, 28(8): 525-530.
［11］ ZHANG Kunpeng, ZHENG Liang, LIU Zijian, et al. A deep learning based multitask model for network-wide traffic speed prediction［J］. Neurocomputing, 2019,
396: 438-450.
［12］ VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach
［J］.Transportation Research Part C: Emerging Technologies, 2005, 13(3): 211-234.
［13］ ZHU Jiazheng, CAO Jinxin, ZHU Yuan. Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the
adjacent intersections［J］. Transportation Research Part C: Emerging Technologies, 2014, 47(2): 139-154.
［14］ XU Dongwei, WANG Yongdong, PENG Peng, et al. Real-time road traffic state prediction based on kernel-KNN［J］. Transportmetrica A: Transport Science, 2020,
16(1): 104-118.
［15］ WU C H, HO J M, LEE D T. Travel-time prediction with support vector regression［J］. IEEE Transactions on Intelligent Transportation Systems, 2004, 5(4): 276-281.
［16］ WANG Jin, SHI Qixin. Short-term traffic speed forecasting hybrid model based on chaos-wavelet analysis-support vector machine theory［J］. Transportation
Research Part C: Emerging Technologies, 2013, 27: 219-232.
［17］ SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers［J］.Neural Processing Letters, 1999, 9: 293-300.
［18］ SABRY M, ABDEL-LATIF H, HAGGAG S A, et al. Use of box and Jenkins time series technique in traffic volume forecasting［J］. Research Journal of Social Sciences,
2007, 2: 83-90.
［19］ KUMAR S V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data［J］.European Transport Research Review,
2015, 7(3): 1-9.
［20］ OKUTANI I, STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory［J］.Transportation Research Part B: Methodological,1984, 18
(1): 1-11.
［21］ POLSON N G, SOKOLOV V O. Deep learning for short-term traffic flow prediction［J］.Transportation Research Part C: Emerging Technologies, 2017, 79: 1-17.
［22］ PAMULA T. Road traffic parameters prediction in urban traffic manage-ment systems using neural networks［J］.Transport Problems an International Scientific
Journal, 2011, 6(3): 123-128.
［23］ TANG Jinjun, GAO Fan, LIU Fang, et al. A denoising scheme-based traffic flow prediction model: Combination of ensemble empirical mode decomposition and
fuzzy C-means neural network［J］. IEEE Access, 2020, 8: 546-559.
［24］赵阳阳，夏亮，江欣国.基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型［J］.交通运输工程学报，2020，20(4)：194-204.
ZHAO Yangyang, XIA Liang, JIANG Xinguo. Short-term metro passenger flow prediction based on EMD-LSTM［J］. Journal of Traffic and Transportation Engineering,
2020, 20(4): 194-204.
［25］ TIAN Xiujuan, YU Dexin, XING Xue, et al. Hybrid short-term traffic flow prediction model of intersections based on improved complete ensemble empirical mode
decomposition with adaptive noise［J］. Advances in Mechanical Engineering, 2019, 11(4): 1-15.
［26］ FENG Shuo, WANG Xingmin, SUN Haowei, et al. A better unde-rstanding of long-range temporal dependence of traffic flow time series［J］. Physica A: Statistical
Mechanics and Its Applications, 2018, 492: 639-650.
［27］ LI Li, SU Xiaonan, ZHANG Yi, et al. Trend modeling for traffic time series analysis: An integrated study［J］. IEEE Transactions on Intelligent Transportation Systems,
2015, 16(6): 3430-3439.
［28］ LI Zhiheng, LI Yuebiao, LI Li. A comparison of detrending models and multi-regime models for traffic flow prediction［J］. IEEE Intelligent Transportation Systems
Magazine, 2014, 6(4): 34-44.
［29］ DAI Xingyuan, FU Rui, ZHAO Enmin, et al. DeepTrend 2.0: A light-weighted multi-scale traffic prediction model using detrending［J］. Transportation Research Part
C: Emerging Technologies, 2019, 103: 142-157.
［30］ YANG Bailin, SUN Shulin, LI Jianyuan, et al. Traffic flow predic-tion using LSTM with feature enhancement［J］. Neurocomputing, 2019, 332: 320-327.
［31］ ZHANG Weibin, YU Yinghao, QI Yong, et al. Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning［J］. Transportmetrica A:
Transport Science, 2019, 15(2): 1688-1711.
［32］ DO L N N, VU H L, VO B Q, et al. An effective spatial-temporal attention based neural network for traffic flow prediction［J］. Transportation Research Part C:
Emerging Technologies, 2019, 108: 12-28.
［33］ LI Li, SU Xiaonan, WANG Yanwei, et al. Robust causal dependence mining in big data network and its application to traffic flow predictions［J］. Transportation
Research Part C: Emerging Technologies, 2015, 58(B): 292-307.
［34］ GUO Fangce, POLAK J W, KRISHNAN R. Predictor fusion for short-term traffic forecasting［J］. Transportation Research Part C: Emerging Technologies, 2018, 92:
90-100.
［35］ LYU Yisheng, DUAN Yanjie, KANG Wenwen, et al. Traffic flow prediction with big data: A deep learning approach［J］. IEEE Transactions on Intelligent
Transportation Systems, 2015, 16(2): 865-873.
［36］戴豪民，许爱强，孙伟超.基于改进奇异谱分析的信号去噪方法［J］.北京理工大学学报，2016，36(7)：727-732.
DAI Haomin, XU Aiqiang, SUN Weichao. Signal denoising method based on improved singular spectrum analysis［J］. Transactions of Beijing Institute of Technology,
2016, 36(7): 727-732.
［37］ LI Heng, LI Zhi, MO Wei. A time varying filter approach for empirical mode decomposition［J］. Signal Processing, 2017, 138: 146-158.
［38］ WANG Yanpeng, ZHAO Leina, LI Shuqing, et al. Short term traffic flow prediction of urban road using time varying filtering based empirical mode decomposition［
J］. Applied Sciences, 2020, 10(6): 1-15.
［39］ JIANG Yan, HUANG Guoqing. Short-term wind speed prediction: Hybrid of ensemble empirical mode decomposition, feature selection and error correction［J］.
Energy Conversion and Management, 2017, 144: 340-350.
［40］余林，舒勤，柏吉琼.基于 EMD 聚类与 ARMA 的交通流量预测方法［J］.公路，2015(5)：124-129.
YU Lin, SHU Qin, BAI Jiqiong. Traffic predication method based on EMD cluster and ARMA［J］. Highway, 2015(5): 124-129.
［41］蒋肖.基于混沌理论和数据融合的短时交通流预测［D］.重庆：重庆邮电大学，2016.
JIANG Xiao.Chaos Theory and Data Fusion Based Short-term Prediction for Traffic Flow［D］. Chongqing: Chongqing University of Posts and Telecommunications, 2016.
［42］王涛，谢思红，黎文皓.基于FFOS-ELM和PF的短时交通流自适应预测模型［J］.重庆交通大学学报(自然科学版)，2021，40(6)：21-27.
WANG Tao, XIE Sihong, LI Wenhao. Adaptive prediction model of short-term traffic flow based on FFOS-ELM and PF［J］. Journal of Chongqing Jiaotong University
(Natural Science), 2021, 40(6): 21-27.
［43］翁小雄，郝翊.基于LSTM引入客车占比特征的短时交通流预测［J］.重庆交通大学学报(自然科学版)，2020，39(11)：20-25.
WENG Xiaoxiong, HAO Yi. Short-term traffic flow prediction based on LSTM introduction of passenger car proportion characteristics［J］. Journal of Chongqing Jiaotong
University(Natural Science), 2020, 39(11): 20-25.

[1]	韩宝睿, 濮海建, 朱震军. 基于改进Lotka-Volterra模型的城市轨道交通与常规公交竞合关系演变研究[J]. 重庆交通大学学报（自然科学版）, 2023, 42(2): 106-112.
[2]	何烈云, 周妍, 黄少泽, 刘强. 叠加放行信号控制方式适用条件及效益评价[J]. 重庆交通大学学报（自然科学版）, 2023, 42(1): 113-119.
[3]	李振龙, 董爱华, 杨磊. 基于群决策和熵权法的换道轨迹评价研究[J]. 重庆交通大学学报（自然科学版）, 2023, 42(1): 120-127.
[4]	翁小雄, 覃镇林, 张鹏飞. 基于图卷积门控循环网络的个体地铁出行预测[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 1-6.
[5]	蓝章礼, 王超, 杨晴晴, 金豪. 基于多粒度特征分割的车辆重识别算法[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 7-15.
[6]	赵欣, 酆磊, 林皓博, 陈曦, 肖宇舟. 相邻T型路口非直线路径绿波控制方法研究[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 16-23.
[7]	张智勇, 黄鑫灿, 邵越. 礼让行人条件下右转保护型相位设置阈值研究[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 24-33.
[8]	冯天军, 杨夏玉, 夏春亭, 梁春岩, 李赫楠. 基于分隔设施的寒区城市道路行车安全间距研究[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 34-38.
[9]	潘义勇, 吴静婷, 施颖. 交叉口处老年人碰撞事故伤害严重程度分析[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 39-44.
[10]	吕贞, 戚春华, 朱守林. 草原公路不同分心状态下驾驶人动态视觉特性[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 45-52.
[11]	张玲玉, 王力, 张立立, 张骁, 孙德辉. 智能汽车的切换型人机共驾研究进展与展望[J]. 重庆交通大学学报（自然科学版）, 2022, 41(09): 130-139.
[12]	赵树恩, 刘伟. 基于改进VGG模型的低照度道路交通标志识别[J]. 重庆交通大学学报（自然科学版）, 2021, 40(10): 178-184.
[13]	李英帅1，闫琦若1，赵聪2. 基于公交车右转内轮差效应的范围研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(09): 43-48.
[14]	阎莹1，刘革1，田敏1，刘佳乐1，穆岩2. 基于Trucksim的弯坡组合路段临界车速确定方法[J]. 重庆交通大学学报（自然科学版）, 2021, 40(09): 49-54.
[15]	胡明伟1,2,3，施小龙1，翟素云4,刘鹏1. 自动驾驶混合交通流的交通和环境效益评估[J]. 重庆交通大学学报（自然科学版）, 2021, 40(08): 7-14.