Mitigating Microsleep-Related Accidents in Commercial Transport: An IoT-Based Detection and Instant Alert System for Enhancing Driver Safety and Road Security

Microsleep-related accidents pose a critical threat to road safety, particularly in commercial transportation, where long-haul driving and fatigue significantly increase the risk of driver impairment. Existing fatigue monitoring systems primarily rely on facial recognition, blink rate detection, and seat pressure sensors, yet they lack real-time intervention mechanisms and external vehicle alerting. This study proposes an IoT-based microsleep detection and intervention system that integrates steering wheel grip pressure sensors, biometric monitoring, AI-driven prediction models, and adaptive braking mechanisms. Unlike conventional solutions, this system offers a multi-layered alert framework, incorporating internal driver alerts, external vehicle signaling, and automated braking assistance to minimize collision risks. The study adopts a Design Science Research (DSR) approach, focusing on conceptual design and system architecture. A prototype model will be developed to demonstrate the feasibility of real-time microsleep detection using grip sensors and AI-based analysis. The system workflow includes sensorbased data acquisition, AI-driven microsleep classification, automated emergency signaling, and controlled braking interventions. Future validation will involve simulated driving environments and survey-based assessments with commercial drivers to refine its performance. The proposed solution bridges critical gaps in existing microsleep detection systems, addressing the absence of external vehicle warnings, lack of real-time intervention, and insufficient integration of IoTbased smart steering control. This research contributes to smart transport safety innovations, offering an AI-driven, IoTenabled microsleep prevention framework to enhance commercial driver safety. Future work will focus on full-scale deployment, real-world validation, and cloud-based fleet monitoring integration for large-scale accident prevention.