A genetic-based random ensemble forest learning for cloud-based automotive data transformation in internet of vehicle

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F04274644%3A_____%2F25%3A%230001201" target="_blank" >RIV/04274644:_____/25:#0001201 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S1110016825001449" target="_blank" >https://www.sciencedirect.com/science/article/pii/S1110016825001449</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.aej.2025.01.120" target="_blank" >10.1016/j.aej.2025.01.120</a>

Result language

angličtina

Original language name

A genetic-based random ensemble forest learning for cloud-based automotive data transformation in internet of vehicle

Original language description

The Internet of Vehicles (IoV) is a constantly changing field, and the fast convergence of automotive technology and connectivity has brought about a new era marked by enormous cybersecurity risks. A crucial component of the inquiry is a thorough examination of the IoV infrastructure's vulnerabilities, which highlights potential sources of compromise and places where strong cybersecurity measures are required for data transformations in cloud-edge computing. Additionally, the Controller Area Network (CAN) and the Electronic Control Units (ECUs) are critical points in automotive networking to connect user data from smart applications to electric vehicles. Therefore, finding a safe automotive data transformation approach for incorporating Connected and Autonomous Vehicles (CAVs) and investigating particular cybersecurity issues is a critical and key challenge in the IoV ecosystem. To ensure the safe development of the IoV landscape, the research introduces two innovative genetic algorithms, Genetic Algorithm Random Forest (GA-RF) and Genetic Algorithm Ensemble Bagged Trees (GA-EBT), to improve the identification of cyber threats in the IoV context. The simulation results demonstrate that the proposed hybrid algorithm achieves exceptional performance, attaining a high accuracy rate of 99.92 %, the lowest mean absolute error of 0.0028, and the highest precision, recall, and F1 measures near to 100 %. These results are especially noteworthy on real automotive data transformation datasets. These results highlight the significance of the suggested strategy for defending IoV systems from suspicious threats.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10200 - Computer and information sciences

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Alexandria Engineering Journal

ISSN

1110-0168

e-ISSN

2090-2670

Volume of the periodical

120

Issue of the periodical within the volume

1

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

13

Pages from-to

74-86

UT code for WoS article

001426544900001

EID of the result in the Scopus database

2-s2.0-85217218286