IMPROVING TRAFFIC DENSITY PREDICTION USING LSTM WITH PARAMETRIC ReLU (PReLU) ACTIVATION
DOI:
https://doi.org/10.33480/jitk.v9i2.5046Keywords:
activation function, LSTM, prediction, PReLU, traffic flowAbstract
In the presence of complex traffic flow patterns, this research responds to the challenge by proposing the application of the Long Short-Term Memory (LSTM) model and comparing four different activation functions, namely tanh, ReLU, sigmoid, and PReLU. This research aims to improve the accuracy of traffic flow prediction through LSTM model by finding the best activation function among tanh, relu, sigmoid, and PReLU. The method used starts from the collection of traffic flow datasets covering the period 2015-2017 used to train and evaluate the LSTM model with the four activation functions. Tests were conducted by observing the Train Mean Squared Error (MSE) and Validation MSE. The experimental results show that PReLU provides the best results with a Train MSE of 0.000505 and Validation MSE of 0.000755. Although tanh, ReLU, and sigmoid provided competitive results, PReLU stood out as the optimal choice to improve the adaptability of the model to complex traffic flow patterns.
Downloads
References
T. Afrin and N. Yodo, “A Survey Of Road Traffic Congestion Measures Towards A Sustainable and Resilient Transportation System,” Sustainability, vol. 12, no. 11, p. 4660, 2020, doi: https://doi.org/10.3390/su12114660.
F. Outay, H. A. Mengash, and M. Adnan, “Applications Of Unmanned Aerial Vehicle (UAV) In Road Safety, Traffic and Highway Infrastructure Management: Recent Advances and Challenges,” Transp. Res. Part Policy Pract., vol. 141, pp. 116–129, 2020, doi: https://doi.org/10.1016/j.tra.2020.09.018.
Y. Berhanu, E. Alemayehu, D. Schröder, and others, “Examining Car Accident Prediction Techniques and Road Traffic Congestion: A Comparative Analysis of Road Safety and Prevention of World Challenges In Low-Income and High-Income Countries,” J. Adv. Transp., vol. 2023, 2023 doi: https://doi.org/10.1155/2023/6643412.
S. M. Abdullah et al., “Optimizing Traffic Flow in Smart Cities: Soft GRU-Based Recurrent Neural Networks for Enhanced Congestion Prediction Using Deep Learning,” Sustainability, vol. 15, no. 7, p. 5949, 2023, doi: https://doi.org/10.3390/su15075949.
S. F. Pane, J. Ramdan, A. G. Putrada, M. N. Fauzan, R. M. Awangga, and N. Alamsyah, “A Hybrid CNN-LSTM Model With Word-Emoji Embedding For Improving The Twitter Sentiment Analysis on Indonesia’s PPKM Policy,” in 2022 6th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 2022, pp. 51–56. doi: 10.1109/ICITISEE57756.2022.10057720.
A. G. Putrada, N. Alamsyah, S. F. Pane, and M. Nurkamal Fauzan, “Feature Importance on Text Analysis for a Novel Indonesian Movie Recommender System,” in 2023 11th International Conference on Information and Communication Technology (ICoICT), 2023, pp. 34–39. doi: 10.1109/ICoICT58202.2023.10262504.
Y. Yu, K. Adu, N. Tashi, P. Anokye, X. Wang, and M. A. Ayidzoe, “RMAF: Relu-Memristor-Like Activation Function For Deep Learning,” IEEE Access, vol. 8, pp. 72727–72741, 2020, doi: 10.1109/ACCESS.2020.2987829.
D. Macêdo, C. Zanchettin, A. L. Oliveira, and T. Ludermir, “Enhancing Batch Normalized Convolutional Networks Using Displaced Rectifier Linear Units: A Systematic Comparative Study,” Expert Syst. Appl., vol. 124, pp. 271–281, 2019, doi: https://doi.org/10.1016/j.eswa.2019.01.066.
S. Poornima and M. Pushpalatha, “Prediction Of Rainfall Using Intensified LSTM Based Recurrent Neural Network With Weighted Linear Units,” Atmosphere, vol. 10, no. 11, p. 668, 2019, doi: https://doi.org/10.3390/atmos10110668.
F. Wirthmüller, M. Klimke, J. Schlechtriemen, J. Hipp, and M. Reichert, “Predicting The Time Until A Vehicle Changes The Lane Using LSTM-Based Recurrent Neural Networks,” IEEE Robot. Autom. Lett., vol. 6, no. 2, pp. 2357–2364, 2021, doi: 10.1109/LRA.2021.3058930.
W. Wei, H. Wu, and H. Ma, “An Autoencoder and LSTM-Based Traffic Flow Prediction Method,” Sensors, vol. 19, no. 13, p. 2946, 2019, doi: https://doi.org/10.3390/s19132946.
Z. Wang, X. Su, and Z. Ding, “Long-Term Traffic Prediction Based on LSTM Encoder-Decoder Architecture,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 10, pp. 6561–6571, 2020 doi: 10.1109/TITS.2020.2995546.
FEDESORIANO, “Traffic Prediction Dataset.” Accessed: Dec. 15, 2023. [Online]. Available: https://www.kaggle.com/datasets/fedesoriano/traffic-prediction-dataset
D. Hungness and R. Bridgelall, “Exploratory Spatial Data Analysis of Traffic Forecasting: A Case Study,” Sustainability, vol. 14, no. 2, p. 964, 2022 doi: https://doi.org/10.3390/su14020964.
D.-H. Lee, Y.-T. Kim, and S.-R. Lee, “Shallow Landslide Susceptibility Models Based on Artificial Neural Networks Considering The Factor Selection Method and Various Non-Linear Activation Functions,” Remote Sens., vol. 12, no. 7, p. 1194, 2020, https://doi.org/10.3390/rs12071194.
A. Ciuparu, A. Nagy-Dăbâcan, and R. C. Mureşan, “Soft++, A Multi-Parametric Non-Saturating Non-Linearity That Improves Convergence In Deep Neural Architectures,” Neurocomputing, vol. 384, pp. 376–388, 2020, https://doi.org/10.1016/j.neucom.2019.12.014.
Y. Koçak and G. Ü. Şiray, “New Activation Functions for Single Layer Feedforward Neural Network,” Expert Syst. Appl., vol. 164, p. 113977, 2021, doi: https://doi.org/10.1016/j.eswa.2020.113977.
A. G. Putrada, N. Alamsyah, S. F. Pane, M. N. Fauzan, and D. Perdana, “Knowledge Distillation for a Lightweight Deep Learning-Based Indoor Positioning System on Edge Environments,” in 2023 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2023, pp. 370–375. doi: 10.1109/ISITIA59021.2023.10220996.
W. Yuan, F. Hu, and L. Lu, “A New Non-Adaptive Optimization Method: Stochastic Gradient Descent With Momentum And Difference,” Appl. Intell., pp. 1–15, 2022, doi: https://doi.org/10.1007/s10489-021-02224-6.
N. Alamsyah, Saparudin, and A. P. Kurniati, “A Novel Airfare Dataset To Predict Travel Agent Profits Based On Dynamic Pricing,” in 2023 11th International Conference on Information and Communication Technology (ICoICT), 2023, pp. 575–581. doi: 10.1109/ICoICT58202.2023.10262694.
Y. Li et al., “Dense Skip Attention Based Deep Learning For Day-Ahead Electricity Price Forecasting,” IEEE Trans. Power Syst., 2022, doi: 10.1109/TPWRS.2022.3217579.