Recurrent Neural Networks for Time Series Forecasting. Choosing the best Architecture for Passenger Traffic Data
DOI:
https://doi.org/10.18372/1990-5548.72.16941Keywords:
neural networks, recurrent neural networks, LST Marchitecture, GRU architecture, time series, passenger flowAbstract
Accurately predicting the urban traffic passenger flow is of great importance for transportation resource scheduling, planning, public safety, and risk assessment. Traditional statistical approaches for forecasting time series are not effective in practice. They often require either strict or weak data stationarity, which is almost impossible to obtain with real data. An alternative method is time series forecasting using neural networks. By their nature, neural networks are non-linear and learn based on input and output data. With this approach, increasing the efficiency of the network is reduced to increasing the amount of data of the initial sample. Today, the class of recurrent neural networks is mainly used for forecasting time series. Another important stage is the choice of neural network architecture. In this article the use of long short term memory and gated recurrent units architecture is considered and also is compared their performance for passenger flow forecasting.
References
Chirag Kothari, US Airline passengers from 1949 to 1960. Kaggle. 2018, April. [Online]. Available: https://www.kaggle.com/datasets/chirag19/air-passengers.
Jayesh Bapu Ahire, The Artificial Neural Networks. Part 1, 2018, August. [Online]. Available: https://www.datasciencecentral.com/the-artificial-neural-networks-handbook-part-1.
Savvas Varsamopoulos, and Koen Almudever, “Designing neural network based decoders for surface codes,” pp. 1–12, Nov. 2018.
Christopher Olah, Understanding LSTM Networks. 2015, August. [Online]. Available: http://colah.github.io/posts/2015-08-Understanding-LSTMs.
Michael Phi, “Illustrated Guide to LSTM and GRU,” Medium Blog. 2018, September. [Online]. Available: https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21.
Fulvia Ceccarelli, and Marco Sciandrone, “Prediction of chronic damage in systemic lupus erythematosus by using machine-learning models,” Plos One. 12(3), 2017, March. Available: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174200. https://doi.org/10.1371/journal.pone.0174200
Kyungdoo Nam and Thomas Schaefer, Forecasting international airline passenger traffic using neural networks, pp. 239–252. 1995, September. [Online]. Available: https://www.researchgate.net/publication/233684273_Neural_network_forecasting_for_airlines_A_comparative_analysis.
Diederik P. Kingma, and Jimmy Lei Ba, “Adam: A method for Stochastic Optimization,” 3rd International Conference for Learning Representations, San Diego. 2015, June. [Online]. Available: https://arxiv.org/abs/1412.6980
Bowen Du, and Hao Peng, “Deep Irregular Convolutional Residual LSTM for Urban Traffic Passenger Flows Prediction,” IEEE Transactions on Intelligent Transportation Systems, 2020, March, pp. 972–985. https://doi.org/10.1109/TITS.2019.2900481
W. Min, and L. Wynter, “Real-time road traffic prediction with spatiotemporal correlations,” Transportation Research Part C: Emerging Technologies, vol. 19, no. 4, pp. 606–616, August 2011. https://doi.org/10.1016/j.trc.2010.10.002
A. Abadi, T. Rajabioun, and P. A. Ioannou, “Traffic flow prediction for road transportation networks with limited traffic data,” IEEE Trans. Intell. Transp. Syst., vol. 16, no. 2, Apr. 2015, pp. 653–662.
Quang Hung Do, “Forecasting Air Passenger Demand: A Comparisonof LSTM and SARIMA,” Journal of Computer Science, 16(7): 1063, Jul, 2020. https://doi.org/10.3844/jcssp.2020.1063.1084
S. Haykin, Neural networks. A comprehensive Foundation. Second edition, in Prentice Hall, 2020, pp. 919–925.
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
