An Embellished Particle Swarm Optimization Technique in VANET for Finding Optimal Route (E-PSO)

Devi, Sheela; Maheswari, D.

doi:10.1007/s42979-022-01508-z

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PSO is designed to address the improvement of both continuous and discontinuous decision-making purposes [24]. The PSO algorithm is a search algorithm that operates on a population level, drawing inspiration from the natural and sociological behaviour observed in animals, particularly flocks of birds engaged in food-foraging activities.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Adaptive neuro‐fuzzy inference system and particle swarm optimization: A modern paradigm for securing VANETs

Thiruppathy Kesavan,

Murugavalli,

Premkumar

et al. 2023

IET Communications

View full text Add to dashboard Cite

Vehicular Adhoc Networks (VANET) facilitate inter‐vehicle communication using their dedicated connection infrastructure. Numerous advantages and applications exist associated with this technology, with road safety particularly noteworthy. Ensuring the transportation and security of information is crucial in the majority of networks, similar to other contexts. The security of VANETs poses a significant challenge due to the presence of various types of attacks that threaten the communication infrastructure of mobile vehicles. This research paper introduces a new security scheme known as the Soft Computing‐based Secure Protocol for VANET Environment (SC‐SPVE) method, which aims to tackle security challenges. The SC‐SPVE technique integrates an adaptive neuro‐fuzzy inference system and particle swarm optimisation to identify different attacks in VANETs efficiently. The proposed SC‐SPVE method yielded the following average outcomes: a throughput of 148.71 kilobits per second, a delay of 23.60 ms, a packet delivery ratio of 95.62%, a precision of 92.80%, an accuracy of 99.55%, a sensitivity of 98.25%, a specificity of 99.65%, and a detection time of 6.76 ms using the Network Simulator NS2.

show abstract

Section: Particle Swarm Optimizationmentioning

confidence: 99%