• Nurshahrily Idura Ramli, Mohd Izani Mohamed Rawi


For decades and even more so at this state of time, traffic congestion had been affecting not just the environment and health, but also damaging the state of the social and economic well-being of a nation.  Proportionate with recent development and advancement in technology, various efforts and methods are proposed in mitigating traffic congestion, including through vehicular communications in Vehicular Ad-hoc Network (VANET) environments. Various methods were proposed in this domain that consists of machine learning algorithms and routing mechanisms, among others to classify and disseminate traffic information to mitigate congestion. This paper presents the Hemorheology-based Traffic Congestion Classification Model (HTCCM), a biologically inspired model that is based upon a hypertension classification in hemorheology. HTCCM is simulated in a hybrid VANET architecture consisting of vehicles and Road-Side Units (RSU) communication, in a decentralized architecture. It is specifically developed to detect congestion, subsequently classifying the level of congestion and disseminating alert messages to vehicles for congestion avoidance purposes. This paper attempts to demonstrate the capacity of a novel bio-inspired model in detecting and classifying traffic congestion in the VANET environment. HTCCM reveals a functional model to be used for both classifying and disseminating traffic alerts without the adoption of any machine learning algorithms that might be overfitting.

How to Cite
Nurshahrily Idura Ramli, Mohd Izani Mohamed Rawi. (2020). HEMORHEOLOGY-BASED TRAFFIC CONGESTION CLASSIFICATION MODEL FOR VANET. International Journal of Advanced Science and Technology, 29(6s), 794 - 806. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/8908