Modelling and Detection of Driver's Fatigue using Ontology
URL: http://arxiv.org/abs/2208.14694v1
archive: archived pipeline: cataloged verified
Abstract
Road accidents have become the eight leading cause of death all over the world. Lots of these accidents are due to a driver's inattention or lack of focus, due to fatigue. Various factors cause driver's fatigue. This paper considers all the measureable data that manifest driver's fatigue, namely those manifested in the vehicle measureable data while driving as well as the driver's physical and physiological data. Each of the three main factors are further subdivided into smaller details. For example, the vehicle's data is composed of the values obtained from the steering wheel's angle, yaw angle, the position on the lane, and the speed and acceleration of the vehicle while moving. Ontological knowledge and rules for driver fatigue detection are to be integrated into an intelligent system so that on the first sign of dangerous level of fatigue is detected, a warning notification is sent to the driver. This work is intended to contribute to safe road driving.
Summary
Ontology-based fatigue-detection framework that integrates vehicle measurements (steering wheel angle, yaw, lane position, speed, acceleration) with driver physical and physiological data into a shared formal knowledge representation. The authors define classes for vehicular, physical, and physiological measurements and rules over them so that an intelligent system can reason about fatigue from heterogeneous sources and trigger a warning at the first sign of dangerous fatigue.
Key finding
A formal ontology is offered as a way to combine the disparate signals used to detect fatigue (vehicle dynamics, physical posture, physiology) into a single rule-based reasoner, addressing the limitation of prior models that consider only a subset of fatigue indicators.
Methodology
Ontology engineering: classes (Vehicle Measure with SteeringWheelAngle, YawAngle, lane position; physical and physiological subclasses) and rules formalized for fatigue-state inference. Conceptual integration with intelligent-system architecture. No empirical sample reported in the section reviewed.
Sample size: N/A — conceptual / ontology paper, no empirical sample
Quality score: 5 / 5