Prevention of Road Accident by Implementing the Driver Drowsiness Detection and Driver Alert System

Raju, S. Razaul Karim; Sikder, Md. Abu Bakkar; Chowdhury, Rishikesh · 2026 · Crossref

DOI: 10.38032/scse.2026.4.183

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the critical issue of driver fatigue, a significant contributor to road accidents, fatalities, and economic losses, particularly in Bangladesh where traffic incidents account for nearly one percent of the GDP. The authors propose a low-cost, real-time Driver Drowsiness Detection and Alert System designed to prevent accidents by monitoring the driver’s physical state and initiating corrective actions before a crash occurs. The primary motivation is to overcome the limitations of existing advanced vehicle systems by providing a simple, camera-free, sensor-based solution that actively controls the vehicle upon detecting drowsiness. The methodology involves the development of a prototype system using an infrared (IR) eye-blink sensor integrated into spectacles. The system utilizes an ATMEGA328P-PU microcontroller to process data from the IR transmitter and receiver, which detect the open and closed states of the driver’s eyes. During initialization, the system records baseline values for open eyes (252) and closed eyes (438) to calculate a personalized threshold value (345). The system continuously monitors eye-blink patterns, recording ten values per second. If more than five of these ten values exceed the threshold, indicating a closed-eye state consistent with drowsiness, the system triggers an alert. This alert includes an audible buzzer, a visual "Danger" or "User is Drowsing" message on an LCD display, and the automatic stopping of the vehicle, simulated in the prototype by halting a DC motor controlled by an L293D IC. The vehicle can only resume operation once the driver’s eye state returns to normal. The experimental results demonstrate that the system achieved an accuracy of 80.56%. The evaluation involved 12 participants, each tested three times, resulting in 36 total observations. In 29 of these instances, the system correctly identified the driver’s condition, while it failed in six cases. The study notes that the system’s accuracy was higher during nighttime conditions compared to daylight. The decision-making logic relies on comparing real-time sensor readings against the calculated threshold; values below the threshold indicate a normal state, while values above indicate drowsiness. The significance of this work lies in its potential to reduce traffic accidents by providing an immediate, automated response to driver fatigue. By actively stopping the vehicle and alerting both the driver and surrounding individuals, the system aims to mitigate the severe consequences of drowsy driving, such as high-speed impacts and loss of vehicle control. The authors conclude that this intelligent, adaptive system offers a viable, cost-effective approach to enhancing road safety and driver alertness, with future plans to incorporate image processing scanners to further improve detection accuracy.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• drowsiness detection algorithms
• drowsiness
• dms validation
• microsleep

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: physiological data
• Methodological Resource: tool software, measurement protocol