Leveraging the Deep Learning Tools and Techniques in the Efficacious Prediction of Vehicular Traffic Flow
Saniya Malik
DAV Police Public School, Gurugram
Download PDFAbstract
Effective flow of traffic expectation is essential for compelling traffic decrease in metropolitan areas. Nonetheless, conventional measurable models frequently need assistance to catch the complicated elements of the vehicular traffic stream precisely, especially under unique circumstances. To improve the accuracy of traffic flow predictions, we propose a novel strategy in this research project that uses gradient descent, AdaBoost, Long Short-Term Memory (LSTM) neural networks, and other deep learning methods. Our model makes precise predictions for the next step using previous traffic data. This enables traffic managers to optimize signal timings and proactively reroute traffic. We consolidate AdaBoost, which coordinates LSTM forecasts as extra information to help the model's presentation. We assess the accuracy of our model utilizing MAE and R2 score strategies, determining the expected traffic stream against the genuine traffic stream. Experimental outcomes show that our proposed model outflanks customary factual models, displaying lower MAE and higher R2 scores. This suggests that it is effective at accurately predicting traffic flow and suggests a promising method for managing traffic and reducing congestion. Our study contributes to developing traffic flow prediction models by providing a more accurate and reliable method. Future work could investigate the mix of constant information streams and outside factors, like atmospheric conditions and occasions, to improve prediction accuracy and successfully address dynamic traffic circumstances. By enhancing traffic with the executive's methodologies, decreasing blockage, and working on general traffic stream productivity, our proposed model holds huge potential for further developing metropolitan traffic conditions.
Keywords: deep learning tools; Vehicular Traffic Flow; Long Short-Term Memory (LSTM)
- Dong, X., Lei, T., Jin, S., & Hou, Z. (2018). Short-term traffic flow prediction based on XG- Boost. 7th Data Driven Control and Learning Systems Conference, 25-27 May 2018. https://doi.org/10.1109/DDCLS.2018.8516114 [Google Scholar]
- Duan, Y., Lv, Y., & Wang, F. Y., “Performance evaluation of the deep learning approach for traffic flow prediction at different times,” Proc. - 2016 IEEE Int. Conf. Serv.
- Erhan, D., Bengio, Y., Courville, A., Manzagol, P., Vincent, P., & Bengio, S. (2010). Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research.
- Essien, A., Petrounias, I., Sampaio, P., & Sampaio, S. (2021). A deep-learning model for urban traffic flow prediction with traffic events mined from twitter. World Wide Web, 24, 1345–1368 .
- Fu, R., Zhang, Z., & Li, L. (2016). Using LSTM and GRU neural network methods for traffic flow prediction. 31st Youth Academic Annual Conference of Chinese Association of Automation, 11-13 Nov. 2016. IEEE: Wuhan.