EUVIMEDEUVIMED entdecken
Mixed-Methods-StudieOpen Access · CC BY 4.0

AI-Driven Security Framework for Internet of Mobility Things: A Mixed-Methods Analysis of Machine Learning Applications in Connected Vehicle Networks

Tamara Saad Mohamed

Academic International Journal of Engineering Science · 2025

DOI: 10.59675/e323 ↗

Kurz gefasst

Mixed-Methods-Studie in der Zeitschrift Academic International Journal of Engineering Science, 2025. Verfasst von Tamara Saad Mohamed. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Internet of Mobility Things (IoMT) is the future of transport in a nutshell. It is a car mash-up that combines chat, self-driving technology, and intelligent road technology, utilizing high-tech communications. This article combines two methods to understand how AI can be used to make IoMT safe: a systematic literature review and hands-on experiments. We filtered 45 papers in 202025 and also tested machine-learning models on typical car information. The review featured such AI giants as deep neural networks, federated learning, and adversarial training. At the end of the data, campus area networks CAN bus attack data was proven to yield our convolution neural networks CNNs a 99.2% detection rate and a 0.58% false positive result. Fed-learning models made 97.8% correct with data confidentiality. Altogether, artificial intelligence AI introduces numerous benefits in terms of security; yet we continue to encounter limitations due to the limitations of computer power and the necessity to operate in real-time. We consider that the hybrid AI-plus-traditional model is the most suitable solution to IoMT security. This paper will help establish standard AI security systems for next generation connected mobility.

Zitieren

APA

Mohamed, T. S. (2025). AI-Driven Security Framework for Internet of Mobility Things: A Mixed-Methods Analysis of Machine Learning Applications in Connected Vehicle Networks. Academic International Journal of Engineering Science. https://doi.org/10.59675/e323

Vancouver

Mohamed TS. AI-Driven Security Framework for Internet of Mobility Things: A Mixed-Methods Analysis of Machine Learning Applications in Connected Vehicle Networks. Academic International Journal of Engineering Science. 2025. doi:10.59675/e323

BibTeX
@article{Mohamed2025,
  author = {Mohamed, Tamara Saad},
  title = {AI-Driven Security Framework for Internet of Mobility Things: A Mixed-Methods Analysis of Machine Learning Applications in Connected Vehicle Networks},
  journal = {Academic International Journal of Engineering Science},
  year = {2025},
  doi = {10.59675/e323}
}
Kostenlos starten →