Open AccessA Modified Fault Detection Bayesian Learning Model For Inter Connected Vehicle Networks
Author(s) -
Syed Umar,
Tadele Debisa Deressa,
Bodena Terfa
Publication year - 2021
Publication title -
international journal of scientific research in science and technology
Language(s) - English
Resource type - Journals
eISSN - 2395-602X
pISSN - 2395-6011
DOI - 10.32628/ijsrset218242
Subject(s) - computer science , fault management , fault (geology) , fault detection and isolation , bayesian network , point (geometry) , real time computing , wireless , distributed computing , data mining , artificial intelligence , machine learning , telecommunications , engineering , node (physics) , geometry , mathematics , structural engineering , seismology , actuator , geology
Currently an important worldwide web, The IoT represents the biggest connected vehicle network of all, but will evolve into a much larger network of connected vehicles. Though a concept promising, the combination of different enabling frequencies does pose various intrinsic and defining challenges in the form of communication systems like privacy and protection. It is also important to establish an effective and dependable strategy to access information for solutions which emerge from increasingly complex vehicle and data systems because of the proliferation of wireless medium. In this article, we provide and improve a new algorithm known as Advanced Fault Detection and Management with Bayesian Network techniques, in which we intend to locate and adjust spatial vehicle faults in real time. Often, we apply measurement method to discover the most effective fault detection methodology, which is the turning point. A sequence of recent studies illustrated findings shows that the suggested approaches include fault detection and correction utilizing tools accessible previously.