Intelligent Drowsiness Detection System for Enhanced Road Safety: an IoT-Based Approach with Machine Learning

EasyChair Preprint 15902

Abstract

With the increasing prevalence of accidents caused by driver drowsiness, there is a growing need for innovative solutions to enhance safety on roads. This paper introduces an IoT-based Smart Drowsiness Detection System that leverages machine learning algorithms to detect and mitigate the risks associated with driver fatigue. The system employs a network of sensors, including facial recognition cameras and physiological sensors, integrated into the Internet of Things framework. The machine learning component of the system analyzes real-time data from these sensors to identify patterns indicative of drowsiness. By continuously learning and adapting to individual driver behavior, the system can provide timely alerts and interventions, such as alarms or seat vibrations, to awaken the drowsy driver and prevent potential accidents. Beyond the realm of transportation, the proposed system has the versatility to be implemented in various contexts where drowsiness poses a safety risk, including industrial settings and healthcare. This paper discusses the design, implementation, and evaluation of the IoTbased Smart Drowsiness Detection System, highlighting its potential to significantly enhance safety and reduce the incidence of accidents associated with driver fatigue.

Keyphrases: Driver fatigue, Drowsiness Detection, Facial Recognition, IoT, Safety Innovation, Smart System, Versatility, alarm systems, machine learning, physiological sensors, transportation safety

@booklet{EasyChair:15902,
  author    = {T Venkatesan and Naveena Sekar and Aadhish Mugunthan and S A Nandha},
  title     = {Intelligent Drowsiness Detection System for Enhanced Road Safety: an IoT-Based Approach with Machine Learning},
  howpublished = {EasyChair Preprint 15902},
  year      = {EasyChair, 2025}}