AI-BASED DRIVER DROWSINESS DETECTION AND MONITORING SYSTEM FOR ELECTRIC VEHICLES WITH EMAIL AND THINGSPEAK ALERTS

Abstract

Road accidents caused by driver fatigue, drowsiness, and reduced attention have become a major concern in modern transportation systems, particularly in electric vehicles (EVs) where long-distance travel is increasingly common. Driver drowsiness significantly reduces reaction time, decisionmaking ability, and vehicle control, resulting in serious accidents, property damage, and loss of life. Conventional driver monitoring systems primarily rely on manual observation or basic warning mechanisms, which often fail to detect fatigue at an early stage. Recent advancements in Artificial Intelligence (AI), computer vision, Internet of Things (IoT), embedded systems, and cloud computing have enabled the development of intelligent driver monitoring systems capable of continuously analysing driver behaviour and generating real-time safety alerts. This project presents a Smart EV Vehicle Driver Monitoring System Using Eye Blink Detection with E-mail and ThingSpeak Alert. The proposed framework integrates a camera module, Arduino/ESP32 controller, eye blink detection algorithm, ThingSpeak cloud platform, e-mail notification system, buzzer, and GPS module (optional) into a unified intelligent safety system. The camera continuously monitors the driver's eye movements, and the eye blink detection algorithm analyses blink frequency and eye closure duration to identify symptoms of fatigue or drowsiness. When prolonged eye closure or abnormal blinking behaviour is detected, the system immediately activates an audible warning through a buzzer while simultaneously uploading event information to the ThingSpeak cloud platform and transmitting an e-mail alert to registered emergency contacts or fleet administrators. Experimental evaluation demonstrates high eye blink detection accuracy, reliable cloud communication, rapid alert generation, low response time, and stable system performance under different driving conditions. The proposed framework significantly improves driver safety, reduces fatigue-related accidents, enables remote vehicle monitoring, and supports intelligent transportation systems for nextgeneration electric vehicles.