Published Paper Details:

The evolution of smart vehicles demands advanced monitoring systems capable of real-time data acquisition, processing, and predictive analysis to enhance safety, efficiency, and performance [1], [2]. This paper presents a compact, low-cost predictive analysis system using Raspberry Pi Zero to monitor critical vehicle parameters [3]. The proposed system integrates various sensors, including a resistive loop-based fuel level sensor, a pressure sensor, and a LIDAR-based tyre level sensor [6], [7]. These sensors provide real-time feedback on fuel availability, pressure variations, and tyre conditions, enabling predictive maintenance and reducing potential breakdowns [4], [5]. The Raspberry Pi controller processes the sensor data and displays it on an LCD module while transmitting it to an IoT-based mobile application for remote access and control [1], [9]. The vehicle's motion is managed using an L298 motor driver, allowing the system to simulate autonomous navigation [2]. Additionally, a light positioning system is implemented, where the front light dynamically turns in the direction of vehicle movement to improve visibility during operation [8]. This light control is also managed through a motor driver interfaced with the Raspberry Pi. The entire system is powered by a portable battery source, ensuring mobility and real-world applicability [10]. By leveraging Python programming and IoT communication, the system provides a scalable platform for smart vehicle monitoring and control [3], [9]. Experimental results demonstrate the effectiveness of predictive analytics in detecting abnormal conditions, ensuring timely alerts, and enhancing the overall intelligence of the vehicle [4]. This approach holds potential for future integration into autonomous and semi-autonomous transport systems [5].