Title: Ensuring safety of vehicular cyber physical systems using machine learning and MQTT

Authors: Neha Bagga; Sheetal Kalra; Parminder Kaur

Addresses: Department of Computer Science, Guru Nanak Dev University, Amritsar, Punjab, India; School of Computer Science Engineering, Lovely Professional University, Phagwara, Punjab, India ' Department of Computer Science and Engineering, G.N.D.U. Regional Campus, Jalandhar, Punjab, India ' Department of Computer Science, Guru Nanak Dev University, Amritsar, Punjab, India

Abstract: One of the pressing concerns for emerging nations is maintenance of roads, including identification and repair of pavement distress. Previous research has focused on pothole detection and lane identification, with the distress details being shared with drivers via database or an Android application. However, this approach is battery-intensive for sensors in smart vehicles and requires a regular internet connection. To address these issues, we have proposed a model trained using Python and TensorFlow to identify road distress and steep curves with an accuracy of 85.2% and 83.1%, respectively. The simulation uses Geocoder to capture the geographical coordinates of the distress, and the collected data is transferred to other CPS devices in cars using MQTT which outperforms databases and Android applications in terms of efficiency, sensor load, and internet connectivity. Drivers receive alerts within 10 seconds, allowing them to make informed decisions which helps prevent accidents and fatalities on the road.

Keywords: VCPS; MQTT; safety; autonomous vehicle; sensors.

DOI: 10.1504/IJVICS.2025.145794

International Journal of Vehicle Information and Communication Systems, 2025 Vol.10 No.2, pp.165 - 183

Received: 23 Jun 2023
Accepted: 23 Feb 2024
Published online: 24 Apr 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article