[1]张扬永.基于TS-NN模型的道路交通车流量预测[J].福建工程学院学报,2021,19(06):560-567.[doi:10.3969/j.issn.1672-4348.2021.06.010]
　ZHANG Yangyong.Prediction of road traffic flow based on the TS-NN model[J].Journal of FuJian University of Technology,2021,19(06):560-567.[doi:10.3969/j.issn.1672-4348.2021.06.010]
点击复制

基于TS-NN模型的道路交通车流量预测()
分享到：

《福建工程学院学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第19卷
期数:
2021年06期
页码:
560-567
栏目:
出版日期:
2021-12-25

文章信息/Info

Title:
Prediction of road traffic flow based on the TS-NN model
作者:
张扬永
中共福建省委党校
Author(s):
ZHANG Yangyong
Fujian Provincial Committee Party School of CPC, Fujian Academy of Governance
关键词:
时间序列; 神经网络; 道路交通; 车流量预测
Keywords:
time series;  neural network;  road traffic;  traffic flow prediction
分类号:
TP312
DOI:
10.3969/j.issn.1672-4348.2021.06.010
文献标志码:
A
摘要:
针对现有的智能交通系统预测方法，基于道路交通的关键参数车流量预测，提出了一种基于深度学习的时间序列交通流预测方法，进一步提升道路交通车流量预测准确率。在对道路交通数据集进行清洗后，使用时间序列和神经网络的结合算法TS-NN 进行车流量预测，实验表明，在城市路段的预测中，TS-NN 相对时间序列模型ARIMA、神经网络模型LSTM 准确率分别提升了1.62%和2.13%?在高速公路数据集上测试上，TS-NN 有更加明显的改进，相对ARIMA、LSTM 分别提升了20.87%和3.53%，在一定程度上，TS-NN 算法确实有助于改进智能交通系统核心算法。
Abstract:
For the existing intelligent traffic system prediction method, a time-series traffic flow prediction method based on deep learning, starting from the key parameters of traffic flow prediction, was proposed to further improve the accuracy of road traffic flow prediction rate. Firstly, the road traffic data set was cleaned, and then TS-NN, the fusion algorithm of time series and neural network, was used for traffic flow prediction. Experimental results show that the prediction accuracy of the TS-NN algorithm in urban sections is improved by 1.62% and 2.13% respectively, compared with that of ARIMA and LSTM. Besides, there are more obvious improvements in the test of the expressway dataset, which are 20.87% and 3.53% higher than ARIMA and LSTM respectively. Therefore, the TS-NN algorithm does contribute to the improvement of its core algorithm to a certain extent.

参考文献/References:

[1] 郝凤霞, 张诗葭. 长三角城市群交通基础设施、经济联系和集聚：基于空间视角的分析[J]. 经济问题探索, 2021（3）: 80-91. [2] 冯思芸,施振佺,曹阳.基于全局时空特性的城市路网交通速度预测模型[J/OL].计算机工程:1-9[2021-07-24].https:∥doi.org/10.19678/j.issn.1000-3428.0061397.[3] 李燕妮. AI技术在智能交通辅助系统中优化控制体现[J]. 机械设计, 2021, 38（6）: 160-161.[4] XU D W, WANG Y D, JIA L M, 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.[5] 张帆, 寻鲁宁, 孙纪新, 等. 基于ARIMA-SVM组合模型的道路交通伤害死亡率预测[J]. 现代预防医学, 2021, 48（10）: 1742-1746. [6] ZHU J, HUANG C Q, YANG M, et al. Context-based prediction for road traffic state using trajectory pattern mining and recurrent convolutional neural networks[J]. Information Sciences, 2019, 473:190-201.[7] QIAO Y H, WANG Y, MA C X, et al. Short-term traffic flow prediction based on 1DCNN-LSTM neural network structure[J]. Modern Physics Letters B, 2021, 35（2）: 2150042. [8] KOESDWIADY A, SOUA R, KARRAY F. Improving traffic flow prediction with weather information in connected cars: a deep learning approach[J]. IEEE Transactions on Vehicular Technology, 2016, 65（12）: 9508-9517. [9] 熊振华,李恒凯.融合多特征神经网络的城市道路速度预测研究[J/OL].测绘科学:1-13[2021-07-19].http:∥kns.cnki.net/kcms/detail/11.4415.P.20201207.1p2.002.html. [10] 曹堉, 王成, 王鑫, 等. 基于时空节点选择和深度学习的城市道路短时交通流预测[J]. 计算机应用, 2020, 40（5）: 88-93.[11] 李瑞敏,王长君.智能交通管理系统发展趋势[J/OL].清华大学学报(自然科学版):1-7[2021-07-24].https:∥doi.org/10.16511/j.cnki.qhdxxb.2021.26.023.[12] JIA T, YAN P G. Predicting citywide road traffic flow using deep spatiotemporal neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22（5）: 3101-3111.

相似文献/References:

[1]许邓艳、卢民荣.基于反向随机投影的神经网络改进算法[J].福建工程学院学报,2020,18(04):358.[doi:10.3969/j.issn.1672-4348.2020.04.010]
　XU Dengyan,LU Minrong.An improved neural network algorithm based on reverse random projection[J].Journal of FuJian University of Technology,2020,18(06):358.[doi:10.3969/j.issn.1672-4348.2020.04.010]

更新日期/Last Update: 2021-12-25