Published 2026 | Version v2
Journal article Open

Design and Construction of a Microcontroller-based Driver's Anti Sleep Device with Multiple Alert Mechanisms

Description

Introduction: Driver drowsiness is a critical causative factor in the alarming rate of road traffic accidents globally. This accounted for a significant portion of the 10,027 crashes and 5,081 fatalities recorded in 2023. Existing mitigation strategies are largely ineffective, and advanced technological solutions are often prohibitively expensive and ill-suited for the local vehicle and environmental conditions. This research addresses the pressing need by leveraging embedded systems engineering to design, implement, and test a cost-effective, real-time Driver Anti-Sleep System (DASS) prototype.

Methodology: The system is architected around an ESP32 microcontroller, which serves as the central processing unit. It employs an ESP32-CAM module for real-time visual monitoring, utilizing computer vision techniques and the Eye Aspect Ratio (EAR) algorithm to detect signs of drowsiness, such as prolonged eye closure. Upon detection, a multi-modal alert subsystem is activated, comprising a buzzer for audio alerts, a vibration motor for haptic feedback, and a SIM800L GSM module to send SMS alerts to pre-configured emergency contacts. A 16 by 2 Liquid Crystal Display (LCD) system status. The system was evaluated based on key engineering metrics, including detection accuracy and response latency.

Result(s): Results reveals 96.7%, and 91.3% detection accuracy and at 1.2s and 1.5s response time, for sleep and drowsiness, respectively.

Recommendation(s): This system provides a critical means for enhancing road safety and provides a foundational framework for future integration with Advanced Driver-Assistance Systems (ADAS) and IoT-based fleet management solutions. It is recommended for adoption by commercial transport operators. Future work should focus on further optimization and large-scale deployment.

Files

2_JSEE3477.pdf

Files (409.3 kB)

Name Size Download all
md5:9f63a78ad00351558fddc904f27a73bf
409.3 kB Preview Download