Next-Gen Transportation Safety: A Mobile Machine Learning Approach to Driver Drowsiness Detection

Industrial processes and efficiency in the era of Industry 4.0 are driven by advancements in technology, including intelligent systems aimed at improving safety and operational effectiveness. One critical aspect of process industry efficiency is transportation safety, where road accidents account for a substantial number of fatalities and injuries globally. Driver drowsiness is a key contributor to these incidents. While previous studies have focused on detecting drowsiness using biological signals and image processing, there has been limited exploration of mobile applications for this purpose. This study introduces a mobile application which applied modern machine learning techniques to detect driver drowsiness and enhance road safety. Using a convolutional neural network model integrated with Google's machine learning kit, the app analyzes driver behavior through facial recognition to detect yawning, head nodding, and eye blink rates - critical indicators of drowsiness. Developed on the Flutter platform, with real-time data management via Firebase, the application can locate a drowsy driver and notify an emergency contact if the driver fails to respond to an alert within a predefined timeframe. This system showcases the potential of mobile solutions in industrial safety applications, contributing to the broader objectives of Industry 4.0 by enhancing safety protocols and reducing process disruptions due to accidents. These findings offer significant insights for policymakers seeking to adopt innovative solutions in the context of intelligent transportation systems and process efficiency.