Smart Transportation and Evolutionary Algorithms: An Approach to Understand Vehicular Ad-Hoc Network

Maram, Rakesh Kumar; Ponnapalli, V. A. Sankar; Maddiboyina, Harsha Vardan

doi:10.1007/978-3-031-21385-4_39

Cited by 2 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…New VANET anomaly detection algorithms were investigated in response to this issue. To identify jamming attacks, extracted moving station of vehicles as well as spatial characteristics of jammers in [18]. It has been demonstrated that deep learning is a powerful tool for extracting valuable network traffic features, despite the high computational complexity required to meet short-lived link as well as dynamic topology requirements in VANETs [19,20].…”

Section: Literature Reviewmentioning

confidence: 99%

AI-Based Efficient Wireless Technologies and Infrastructure-Based Networks With VANET For Smart Transportation High Performance

Xiong¹,

Li²,

Hou³

et al. 2023

Preprint

View full text Add to dashboard Cite

VANETs (Vehicular Ad-hoc NETworks) were deemed most suitable communication network for supporting the dissemination of alert messages due to their low dissemination delays as well as extensive vehicle coverage in vicinity of an emergency. With the introduction of cooperative ITS services, it is envisaged that emerging vehicular networks will progressively rely on Vehicle to Infrastructure (V2I) communication lines, which are expected to be nominally accessible with certain temporary as well as time-limited connectivity losses. This study proposes a novel method for VANET-based efficient vehicle clustering and routing based on network infrastructure for high-performance smart transportation. the vehicle clustering using infrastructure-based fuzzy K-means convolutional neural networks. then the energy-efficient cluster-based multi-hop distributed routing. the experimental analysis in terms of latency, network lifetime, throughput, QoS, energy efficiency, and packet delivery ratio. In addition, empirical equations that can be used to predict speed recommendations for drivers are derived from the result.

show abstract

Section: Literature Reviewmentioning

confidence: 99%