Sensor Data Analysis in a Real-Time IoT and Blockchain-Based System for Monitoring Driver Alcohol Levels

Monitoring alcohol levels of drivers is essential for maintaining public safety, especially for preventing traffic accidents. This paper presents the development and evaluation of a sensor-based module designed to predict breath alcohol levels using a modular sensor battery, integrated with blockchain technology and a data collection platform. The proposed system monitors the driver's location and alcohol level in real-time, preserving data integrity through the use of blockchain. The experimental setup involved varying alcohol concentrations and measuring sensor responses at different distances from the source. The core of this research is the analysis of the collected data, using machine learning techniques, specifically Random Forest and Extreme Gradient Boosting, to assess the reliability and accuracy of the sensor readings. The analysis confirmed a strong correlation between the sensor's readings and actual alcohol levels, demonstrating that the system achieves high accuracy when the sensors are placed within 1000 mm of the source.