A transformative deep learning framework for traffic modelling using sensors-based multi-resolution traffic data
by Shubhashish Goswami; Abhimanyu Kumar
International Journal of Sensor Networks (IJSNET), Vol. 42, No. 3, 2023

Abstract: Intelligent transportation system (ITS) is a cohesive organisation of roads, vehicles, and people which utilised the power of computing for the management of unpredictable traffic conditions. Today, road accidents and congestion are the major problems that arise due to absence of ITS. Due to intricate and dynamic spatio-temporal linkages between various regions in road network, particularly at major intersections of city, these issues are difficult to solve. Deep learning offers enormous potential to enhance traffic operation and management when combined with current sensors-based multi-resolution traffic data and future linked technologies. But we require effective modelling frameworks for deep-learning algorithms to address complicated transportation problems. This work mainly focused on the analysis of traffic conditions using deep learning hybrid framework for a correct prediction of traffic pattern with a real world traffic dataset. Performance of proposed framework betters the benchmarks with RMSE of 52 and MAE of 49.

Online publication date: Thu, 27-Jul-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Sensor Networks (IJSNET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com