We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Optimal Deep Learning Enabled Statistical Analysis Model for Traffic Prediction.
- Authors
Dutta, Ashit Kumar; Srinivasan, S.; Kumar, S. N.; Balaji, T. S.; Won Il Lee; Joshi, Gyanendra Prasad; Sung Won Kim
- 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 preprocesses 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.
- Subjects
STATISTICAL models; STATISTICS; PREDICTION models; DEEP learning; LONG-term memory; STATISTICAL learning
- Publication
Computers, Materials & Continua, 2022, Vol 72, Issue 3, p5563
- ISSN
1546-2218
- Publication type
Article
- DOI
10.32604/cmc.2022.027707