|Table of Contents|

Traffic congestion prediction method based onlong short-term memory model(PDF)


Research Field:
Publishing date:


Traffic congestion prediction method based onlong short-term memory model
Lv Xian1Qi Yong1Zhang Weibin2
1.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China; 2.School of Electronic Engineering and Photoelectric Technology,Nanjing University of Science and Technology,Nanjing 210094,China
traffic congestion prediction traffic flow long short-term memory model denoising autoencoder deep learning
In order to fully consider the influence of various factors and mine the deep features hidden in the traffic flow data in the traffic congestion prediction algorithm,a traffic congestion prediction method based on a long short-term memory(LSTM)model is proposed. The method fully considers the characteristics of traffic flow,weather,holidays and other factors. Firstly,the denoising autoencoder model is used to extract the core features of the input data,and the LSTM model’s long-term memory of historical data is used. The combination predicts the urban traffic congestion degree effectively. Compared with the existing traffic congestion prediction model,the results show that the proposed method has high prediction accuracy and robustness,and the accuracy can reach more than 92%.


[1] Zhong Ming,Sharma S,Lingras P. Genetically designed models for accurate imputation of missing traffic counts[J]. Transportation Research Record:Journal of the Transportation Research Board,2004(1879):71-79.
[2]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.
[3]Zhang Hesheng,Zhang Yi,Li Zhiheng,et al. Spatial-temporal traffic data analysis based on global data management using mas[J]. IEEE Transactions on Intelligent Transportation Systems,2004,5(4):267-275.
[4]Ni Daiheng,Leonard J D,Guin A,et al. Multiple imputation scheme for overcoming the missing values and variability issues in its data[J]. Journal of transportation engineering,2005,131(12):931-938.
[5]崔玮. 高速路网交通状态判别与预测的研究[D]. 淄博:山东理工大学交通运输工程学院,2016.
[6]陈洪,陈森发. 基于模糊GMDH网络的交通流量预测模型[J]. 南京理工大学学报,2010,34(1):46-50.
Chen Hong,Chen Senfa. Traffic flow prediction model based on fuzzy GMDH network[J]. Journal of Nanjing University of Science and Technology,2010,34(1):46-50.
[7]Lu Jian,Chen Shuyan,Wei Wang,et al. A hybrid model of partial least squares and neural network for traffic incident detection[J]. Expert Systems with Applications,2012,39(5):4775-4784.
[8]Lv 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.
[9]中国气象局. 气象灾害预警信号发布与传播办法[EB/OL]. http://www.cma.gov.cn/2011zwxx/2011zflfg/2011zgfxwj/201208/t20120803_180761.html. 2007-06-11/2019-07-16.
[10] 谭娟,王胜春. 基于深度学习的交通拥堵预测模型研究[J]. 计算机应用研究,2015,32(10):2951-2954.
Tan Juan,Wang Shengchun. Research on traffic congestion prediction model based on deep learning[J]. Journal of Computer Applications,2015,32(10):2951-2954.
[11]Bae B,Kim H,Lim H,et al. Missing data imputation for traffic flow speed using spatio-temporal cokriging[J]. Transportation Research Part C:Emerging Technologies,2018,88:124-139.
[12]Zeng Weiliang,He Zhaocheng,She Xiwei. Data repair method for real time urban link speed estimation[C]//11th International Conference of Chinese Transpor-tation Professionals(ICCTP). Nanjing,China:Ame-rican Society of Civil Engineers National Natural Science Foundation of China,2011:1733-1744.
[13]Vincent P,Larochelle H,Bengio Y,et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning. [S.l.]:ACM,2008:1096-1103.
[14]王晓杰. 基于深度学习的短时交通流预测[D]. 青岛:青岛大学计算机科学与技术学院,2017.
[15]高晓波. 基于深度学习的短时交通拥堵预测模型[D]. 大连:大连理工大学软件工程学院,2017


Last Update: 2020-02-29