On Road Vehicle Breakdown Assistance by Using Machine Learning
The On Road Vehicle Breakdown Application (ORVBA) functions as an optimal system to resolve remote automotive breakdowns. Primary end-users of the ORVBA platform will use the system to reach qualified professionals through an application system they can trust. The framework of ORVBA connects solely with certified mechanics who have obtained proper licenses. The ORVBA deals with the Cognitive Radio Networks (CRN), Enhanced Capsule GAN model, and Coupled Hidden Markov Model (CHMM). The continuous system contains specific user records that hold minimal value for other system users. These users remain ignorant about prospective mechanical failures that could manifest far from their regular service locations. Users can obtain access to emergency experts through the On Road Vehicle Breakdown Application (ORVBA) regardless of where they are located or what areas they are situated in. We suggest creating a mobile and web-based support system to fix this. This website lets technicians register their credentials and provide service information. The mobile help app requires two steps: installing the Android app and downloading it. The process automatically collects and stores user location data when connected to a database. The technology leverages user location data to display nearby service providers and stores them on their phone. The list of service providers appears when a user requests service. Even if their mobile devices lose internet connection, people whose automobiles malfunction will have service provider information.
Authors
- B. Pavithra
- Saravanan Matheswaran
- Udayakumar Allimuthu (ORCID: https://orcid.org/0000-0001-5376-0327)
- Farzana Sultana (ORCID: https://orcid.org/0009-0002-8006-5164)
- Vijay P. Singh (ORCID: https://orcid.org/0000-0002-0910-1401)
- P. Alekhya
Institutions
- Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (IN)
Publication Details
- Published
- 2025-06-05
- DOI
- https://doi.org/10.1109/iccsp64183.2025.11089421
- Primary Topic
- Traffic control and management
- Type
- article
- Field-Weighted Citation Impact
- 0.00