1.中山大学智能工程学院,广东 深圳 518106
2.广东省智能交通系统重点实验室,广东 广州 510006
3.佛山交通运行监测中心,广东 佛山 528000
姚博凡(1994年生),男;研究方向:交通大数据;E-mail: yaobf@mail2.sysu.edu.cn
蔡铭(1977年生),男;研究方向:交通大数据、交通环境工程和智能交通系统;E-mail:caiming@mail.sysu.edu.cn
纸质出版日期:2021-05-25,
网络出版日期:2020-11-10,
收稿日期:2019-11-04,
录用日期:2019-12-03
扫 描 看 全 文
姚博凡,邓如丰,熊宸等.基于时空特征向量的城市快速路交通状态长时段预测[J].中山大学学报(自然科学版),2021,60(03):115-123.
YAO Bofan,DENG Rufeng,XIONG Chen,et al.Long-term traffic status prediction of urban expressway based on spatio-temporal eigenvector[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2021,60(03):115-123.
姚博凡,邓如丰,熊宸等.基于时空特征向量的城市快速路交通状态长时段预测[J].中山大学学报(自然科学版),2021,60(03):115-123. DOI: 10.13471/j.cnki.acta.snus.2019.11.04.2019B111.
YAO Bofan,DENG Rufeng,XIONG Chen,et al.Long-term traffic status prediction of urban expressway based on spatio-temporal eigenvector[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2021,60(03):115-123. DOI: 10.13471/j.cnki.acta.snus.2019.11.04.2019B111.
针对交通状态长时段预测问题,提出了基于时空特征向量的长时段交通状态预测模型。该模型在分析交通状态变化时空关联性的基础上,构建了表征交通状态变化规律的时空特征向量,包括时间轴特征、路段历史平均交通状态特征、时间常发拥堵特征和上下游路段的历史交通状态特征。单路段预测实验结果表明,模型预测准确度较高,全天预测准确度在90%左右,高峰预测准确度在80%左右。此外,与单一时间特征相比,提出的时空特征向量能显著提高预测准确度。多路段的实验结果表明,基于时空特征向量的SVM预测方法具有较好的普适性,全天平均预测准确度达到了95%左右,高峰平均预测准确度达到了88%左右。
This paper proposes a long-term traffic status prediction model based on a spatio-temporal eigenvector in order to solve the problem of long-term traffic status prediction. Based on the analysis of the spatio-temporal correlation of traffic status changes, the model constructs the spatio-temporal eigenvector that represents the law of traffic status variation, including time axis feature, historical average traffic status feature, recurrent congestion feature and historical average traffic status feature of upstream and downstream roads. The prediction results of the single roads show that the model has a good prediction performance. The accuracy of all-day prediction is about 90% and the accuracy of peak hour prediction is about 80%. Furthermore, compared with single time features, the proposed spatio-temporal eigenvector can significantly improve the prediction accuracy. The prediction results of multiple roads show that the SVM prediction method based on spatio-temporal has a good universality. The average accuracy of allday prediction is about 95% and the average accuracy of peak hour prediction is about 88%.
长时段预测支持向量机交通状态时空特征向量
long-term predictionsupport vector machinetraffic statusspatio-temporal eigenvector
葛梦雪, 宋国华, 王芃森, 等. 基于手机应用软件测算OD数据的区域交通需求预测[J]. 公路交通科技, 2019, 36(5): 152-158.
GE M X, SONG G H, WANG P S, et al. Regional traffic demand forecasting based on OD data calculated by mobile phone application software[J]. Journal of Highway and Transportation Research and Development, 2019, 36(5): 152-158.
ZHAO Y, ZHANG H, AN L, et al. Improving the approached of traffic demand forecasting in the big data era[J]. Cities, 2018, 82: 19-26.
李林超, 张健, 杨帆, 等. 基于核函数切换和支持向量回归的交通量短时预测模型[J]. 东南大学学报(自然科学版), 2017, 47(5): 1032-1036.
LI L C, ZHANG J, YANG F, et al. Traffic volume prediction based on support vector regression with switch kernel functions[J]. Journal of Southeast University (Natural Science Edition), 2017, 47(5): 1032-1036.
HABTEMICHAEL F, CETIN M. Short-term traffic flow rate forecasting based on identifying similar traffic patterns[J]. Transportation Research Part C: Emerging Technologies, 2016, 66: 61-78.
GUO F, KRISHNAN R, POLAK J. The influence of alternative data smoothing prediction techniques on the performance of a two-stage short-term urban travel time prediction framework[J]. Journal of Intelligent Transportation Systems, 2017, 21(3): 214–226.
罗文慧, 董宝田, 王泽胜. 基于CNN-SVR混合深度学习模型的短时交通流预测[J]. 交通运输系统工程与信息, 2017, 17(5): 68-74.
LUO W H, DONG B T, WANG Z S. Short-term traffic flow prediction based on CNN-SVR hybrid deep learning model[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(5): 68-74.
康军, 段宗涛, 唐蕾, 等. 一种LS-SVM在线式短时交通流预测方法[J]. 计算机应用研究, 2018, 35(10):2965-2968.
KANG J, DUAN Z T, TANG L, et al. LS-SVM online short term traffic flow prediction method[J]. Application Research of Computers, 2018, 35(10):2965-2968.
熊亭, 戚湧, 张伟斌, 等. 基于时空相关性的短时交通流预测模型[J]. 计算机工程与设计, 2019, 40(2): 501-507.
XIONG T, QI Y, ZHANG W B, et al. Short term traffic flow forecasting model based on temporal-spatial correlation[J]. Computer Engineering and Design, 2019, 40(2): 501-507.
GUO F, POLAK J, KRISHNAN R. Predictor fusion for short-term traffic forecasting[J]. Transportation Research Part C: Emerging Technologies, 2018, 92: 90-100.
谢海红, 戴许昊, 齐远. 短时交通流预测的改进K近邻算法[J]. 交通运输工程学报, 2014, 14(3): 87-94.
XIE H H, DAI X H, QI Y. Improved K-nearest neighbor algorithm for short-term traffic flow forecasting[J]. Journal of Traffic Transportation Engineering, 2014, 14(3): 87-94.
史殿习, 丁涛杰, 丁博, 等. 一种基于非参数回归的交通速度预测方法[J]. 计算机科学, 2016, 43(2): 224-229.
SHI D X, DING T J, DING B, et al. Traffic speed forecasting method based on nonparametric regression[J]. Computer Science, 2016, 43(2): 224-229.
田瑞杰, 张维石, 翟华伟. 基于时间序列与BP-ANN的短时交通流速度预测模型研究[J]. 计算机应用研究, 2019(11):1-8.
TIAN R J, ZHANG W S, ZHAI H W. Short-term traffic flow velocity prediction model based on time series and BP-ANN[J]. Application Research of Computers, 2019(11):1-8.
孙静怡, 牟若瑾, 刘拥华. 考虑大型车因素的支持向量机短时交通状态预测模型研究[J]. 公路交通科技, 2018, 35(10): 126-132.
SUN J Y, MOU R J, LIU Y H. Study on short-term traffic state forecasting model of SVM considering proportion of large vehicles[J]. Journal of Highway and Transportation Research and Development, 2018, 35(10): 126-132.
WANG J, SHI Q. 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.
陈忠辉, 凌献尧, 冯心欣, 等. 基于模糊C均值聚类和随机森林的短时交通状态预测方法[J]. 电子与信息学报, 2018, 40(8): 106-113.
CHEN Z H, LING X Y, FENG X X, et al. Short-term traffic state prediction approach based on FCM and random forest[J]. Journal of Electronics & Information Technology, 2018, 40(8): 106-113.
XU D W, WANG Y D, PENG P, et al. Real-time road traffic state prediction based on Kernel-KNN[J]. Transportmetrica A: Transport Science, 2020,16(1): 104-108.
LIU Y, WU H. Prediction of road traffic congestion based on random forest[C]//2017 10th International Symposium on Computational Intelligence and Design (ISCID). IEEE, 2017.
刘欢, 邵社刚, 王赵明. 基于向量自回归模型的城市快速路交通状态短时预测研究[J]. 公路交通科技(应用技术版), 2019, 15(2): 314-319.
LIU H, SHAO S G, WANG Z M. Study on short-term traffic status prediction of urban expressway based on vector autoregression model[J]. Journal of Highway and Transportation Research and Development (Applied Technology Edition), 2019, 15(2): 314-319.
XU D, WANG Y, JIA L, et al. Real-time road traffic state prediction based on ARIMA and Kalman filter[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(2): 287-302.
POLSON N, SOKOLOV V. Deep learning for short-term traffic flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2017, 79: 1-17.
WANG J, CHEN R, HE Z. Traffic speed prediction for urban transportation network: A path based deep learning approach[J]. Transportation Research Part C: Emerging Technologies, 2019, 100: 372-385.
国家质量监督检验检疫总局. 城市交通运行状况评价规范:GB/T 33171-2016[S]. 北京: 国家标准化管理委员会, 2016.
General Administration of Quality Supervision, Inspection and Quarantine. Specification for urban traffic performance evaluation:GB/T 33171-2016[S]. Beijing: Standardization Administration, 2016.
0
浏览量
2
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构