Deep Learning- Based Vehicular Traffic Prediction For Its Applications


Al-Selwi, Hatem Fahd and Abd. Aziz, Azlan and Abas, Fazly Salleh (2023) Deep Learning- Based Vehicular Traffic Prediction For Its Applications. In: 1st FET PG Engineering Colloquium Proceedings 2023, 16 June - 15 July 2023, Multimedia University, Malaysia. (Submitted)

[img] Text
23_PPM Poster_CSCI_Hatem_June2023.pdf
Restricted to Registered users only

Download (437kB)


Intelligent Transportation Systems (ITS) are crucial for managing traffic, but accurate prediction is challenging. Deep learning, specifically Graph Convolutional Neural Networks (GCNs)[1], shows promise in handling complex traffic data. This project focus studies recent developments in traffic prediction using GCNs and proposes a novel GCN-based method with attention mechanisms and Kalman Filter. Experimental results demonstrate a 5% accuracy improvement compared to the original model.

Item Type: Conference or Workshop Item (Poster)
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 10 Aug 2023 08:25
Last Modified: 15 Aug 2023 01:44


Downloads per month over past year

View ItemEdit (login required)