A Driver Fatigue Recognition System, Based on an Artificial Neural Network

Abstract

The paper proposes a method for monitoring the state of a driver, based on the use of neural networks.An intelligent automated system based on a fuzzy inference algorithm has been developed.The relevance of the study is considered.It is carried out a review of studies on this topic and the history of the problem development.Ensuring road safety, is one of the priority State tasks, for the Republic of Kazakhstan.The goal of the study based on the review was set: the development of an automated system for monitoring the driver's condition using artificial neural network (ANN).The theoretical-empirical method was chosen as the research method.As a result of the study, an ANN containing 3 layers was developed: an input layer of 7 elements, a hidden layer of 14 elements, and an output layer of 2 elements.Based on the constructed model, the software "Intellectual system for monitoring the state of a person during work associated with increased danger" was developed.All considered methods and algorithms are implemented in the software package in C#.The obtained results are discussed, and it is concluded that the developed ANN-based assessment model is able to reliably assess driver fatigue and can be applied in real conditions.

More by Bauyrzhan Smakanov

• MODELING DRIVER STATE MONITORING BASED ON A THEORETICAL AND EMPIRICAL APPROACHHerald of Kazakh-British technical university · 2026
• Methods for Driver Fatigue Detection Using Computer Vision and Machine LearningInternational Congress on Human-Computer Interaction, Optimization and Robotic Applications · 2026
• A Hybrid Computer Vision Framework for Real-Time Driver Fatigue and Distraction Detection Using Deep LearningEngineered Science · 2026
• NEURAL NETWORK DEVELOPMENT AND TRAINING FOR RECOGNIZING THE STATE OF A DRIVERВестник КазАТК · 2023 · Citations: 1