IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 9 - Issue 4, April 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Multivariate Time Serious Traffic Prediction Using Long Short Term Memory Network

[Full Text]

 

AUTHOR(S)

S.Narmadha, Dr.V.Vijayakumar

 

KEYWORDS

Vehicle, Traffic Congestion, Flow, Weather, Precipitation, Multivariate, Deep Learning.

 

ABSTRACT

Short term traffic prediction is essential in the modern intelligent transportation systems. Numerous algorithms were developed for time serious traffic prediction. Long short term memory network (LSTM) is a time serious prediction model which is able to integrate multiple variables such as flow, weather and precipitation. Most of the researches were carried out using the main source of data such as total flow or average speed to predict the vehicle congestion. Weather and rainfall are other factors which are gradually increase the traffic congestion in the crowded city. In this paper, LSTM network is proposed for multivariate analysis based traffic flow prediction. Traffic data contains noise and missing values due to device failures and communication problems. Missing data has been imputed and noise are removed using stacked denoise autoencoder (SDAE). Results are compared with LSTM based univariate analysis and convolutional neural network (CNN) based multivariate analysis. According to the results of LSTM based Multivariate (flow, weather, precipitation) approach without missing value reduces the RMSE error rate to 15.01 to predict the future congestion of a road.

 

REFERENCES

[1] B. Yang, S. Sun, J. Li, X. Lin, Y. Tian, “Traffic Flow Prediction Using LSTM with Feature Enhancement,” Neuro computing, vol. 332, pp.320-327, 2018.
[2] D. Yang, s. Li , z. Peng , p. Wang , j. Wang , and h yang, “MF-CNN: traffic flow prediction using convolutional neural network and multi-features fusion,” IEICE trans. Inf. & syst., vol.e102–d, no.8 august 2019.
[3] H. Shao, B. Soong, “Traffic flow prediction with Long Short-Term Memory Networks (LSTMs),” 2016 IEEE Region 10 Conference (TENCON), Singapore, pp. 2986-2989, 2016.
[4] H. Zhang, X. Wang, J Cao, M Tang, Y Guo, “A multivariate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series,” springer, Vol. 48, Issue 10, pp. 3827–3838, 2018.
[5] J. Li, L. Gao, L. wei and Y. Shi, “Short term traffic flow prediction based on LSTM,” Ninth international conference on Intelligent control and information processing, Wanzhou, pp.251-255, 2018.
[6] M. Chen, G. Yu, P. Chen, and Y. Wang, “Traffic Congestion Prediction Based on Long-Short Term Memory Neural Network Models,” 17th COTA International Conference of Transportation, CICTP 2017, pp.673-681, 2017.
[7] R. Fu, Z. Zhang and L. Li , “ Using LSTM and GRU Network methods for Traffic flow prediction,” 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), Wuhan, pp. 324-328, 2016.
[8] S. Ghosh, M. T. Asif, L. Wynter, “Denoising autoencoders for fast real-time traffic estimation on urban road networks,” 2017 IEEE 56th Annual Conference on Decision and Control (CDC), pp. 6307-6312, 2017.
[9] S. Narmadha, V. Vijayakumar, “A Study on Imputation Methods for Vehicle Traffic Data,” International Journal of Recent Technology and Engineering (IJRTE), Volume-7 Issue-5S, pp.415-420, 2019.
[10] S. Narmadha, V. Vijayakumar, “An Improved Stacked Denoise Autoencoder with Elu Activation Function for Traffic Data Imputation,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), Volume-8 Issue-11, pp.3951-3954, 2019.
[11] S.Narmadha, V. Vijayakumar, “An Effective Imputation Model for Vehicle Traffic Data Using Stacked Denoise Autoencoder,” Advances in Intelligent Systems and Computing, Springer, Cham, vol 1108, pp 71-78, 2020.
[12] S. V. Kumar & L. Vanajakshi, “Short-term traffic flow prediction using seasonal ARIMA model with limited input data,” Eur. Transp. Res. Rev. (2015), 7: 21, Springer, pp. 1-9, 2015.
[13] W. Huang, H. Hong, M. Li, W. Hu, G. Song and K. Xie, “Deep Architecture for Traffic Flow Prediction,” Lecture Notes in Computer Science, vol 8347 pp.165–176, 2013.
[14] W. Xiangxue, X. Lunhui, C. Kaixun, “Data-Driven Short-Term Forecasting for Urban Road Network Traffic Based on Data Processing and LSTM-RNN,” Arabian Journal for Science and Engineering 44, 3043-3060, 2018.
[15] X. Ma, Z. Dai, Z. He, J. Ma, Y. Wang and Y. Wang, “Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction,” Sensors, pp: 1-16, 2017.
[16] X. Luo, D. Li, Y. Yang and S. Zhang, “Spatiotemporal Traffic Flow Prediction with KNN and LSTM,” Journal of advanced transportation, Vol 2019, Article ID 4145353, pp.1-10, Hindawi, 2019.
[17] Y.Tian, L. Pan, “Predicting short term traffic flow by long short term memory recurrent neural network,” 2015 IEEE International Conference on Smart City/SocialCom/SustainCom together with DataCom 2015 and SC2 2015, pp. 153-158.
[18] Y. Tian, K. Zhang, J. Li, X. Lin, B. Yang, “LSTM-based Traffic flow Prediction with Missing Data,” Neuro Computing, Vol 318, pp. 297-305, 2018.
[19] Z. Zou, P. Gao, C. Yao, “ C*ity-level traffic flow prediction via LSTM networks,” ICAIP '18 Proceedings of the 2nd international conference on Advances in Image Processing, pp. 149-153, june 2018
[20] http://pems.dot.ca.gov/
[21] http://mesowest. (The University of Utah.)