Open Access

ARTICLE

Optimal Deep Learning Enabled Statistical Analysis Model for Traffic Prediction

by Ashit Kumar Dutta¹, S. Srinivasan², S. N. Kumar³, T. S. Balaji^4,5, Won Il Lee⁶, Gyanendra Prasad Joshi⁷, Sung Won Kim^8,*

1 Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Ad Diriyah, Riyadh, 13713, Kingdom of Saudi Arabia
2 Institute of Biomedical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Saveetha Nagar, Thandalam, Chennai, 602105, India
3 Department of Electrical & Electronics Engineering, Amal Jyothi College of Engineering, Kanjirappally, Kerala, 686518, India
4 Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Saveetha Nagar, Thandalam, Chennai, 602105, India
5 Department of Electronics and Communication Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Vadapalani Campus, Chennai, 600026, India
6 Department of Business Administration, Hanbat National National University, Daejeon, 34158, Korea
7 Department of Computer Science and Engineering, Sejong University, Seoul, 05006, Korea
8 Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongbuk-do, 38541, Korea

* Corresponding Author: Sung Won Kim. Email:

Computers, Materials & Continua 2022, 72(3), 5563-5576. https://doi.org/10.32604/cmc.2022.027707

Received 24 January 2022; Accepted 08 March 2022; Issue published 21 April 2022

Abstract

Due to the advances of intelligent transportation system (ITSs), traffic forecasting has gained significant interest as robust traffic prediction acts as an important part in different ITSs namely traffic signal control, navigation, route mapping, etc. The traffic prediction model aims to predict the traffic conditions based on the past traffic data. For more accurate traffic prediction, this study proposes an optimal deep learning-enabled statistical analysis model. This study offers the design of optimal convolutional neural network with attention long short term memory (OCNN-ALSTM) model for traffic prediction. The proposed OCNN-ALSTM technique primarily pre-processes the traffic data by the use of min-max normalization technique. Besides, OCNN-ALSTM technique was executed for classifying and predicting the traffic data in real time cases. For enhancing the predictive outcomes of the OCNN-ALSTM technique, the bird swarm algorithm (BSA) is employed to it and thereby overall efficacy of the network gets improved. The design of BSA for optimal hyperparameter tuning of the CNN-ALSTM model shows the novelty of the work. The experimental validation of the OCNN-ALSTM technique is performed using benchmark datasets and the results are examined under several aspects. The simulation results reported the enhanced outcomes of the OCNN-ALSTM model over the recent methods under several dimensions.

---

Keywords

---