Recently, intelligent transportations system (ITS) has gained significant internet due to the higher needs for road safety and competence in interconnected road network. As a vital portion of the ITS, traffic flow prediction (TFP) is offer support in several dimensions like routing, traffic congestion, and so on. To accomplish effective TFP outcomes, several predictive approaches have been devised namely statistics, machine learning (ML), and deep learning (DL). This study designs an optimal stacked sparse autoencoder based traffic flow prediction (OSSAE-TFP) model for ITS. The goal of the OSSAE-TFP technique is to determine the level of traffic flow in ITS. In addition, the presented OSSAE-TFP technique involves the traffic and weather data for TFP. Moreover, the SSAE based prediction model is designed for forecasting the traffic flow and the optimal hyperparameters of the SSAE model can be adjusted by the use of water wave optimization (WWO) technique. To showcase the enhanced predictive outcome of the OSSAE-TFP technique, a wide range of simulations was carried out on benchmark datasets and the results portrayed the supremacy of the OSSAE-TFP technique over the recent state of art methods.
Optimal Stacked Sparse Autoencoder Based Traffic Flow Prediction in Intelligent Transportation Systems
Studies in Systems, Decision and Control
Virtual and Augmented Reality for Automobile Industry: Innovation Vision and Applications ; Chapter : 6 ; 111-127
2022-02-24
17 pages
Article/Chapter (Book)
Electronic Resource
English
Spatio-Temporal AutoEncoder for Traffic Flow Prediction
IEEE | 2023
|Traffic Flow Prediction For Intelligent Transportation System Using Machine Learning
DOAJ | 2023
|Road traffic flow prediction method based on stacked regression
European Patent Office | 2023
|