A Driver Fatigue Recognition System, Based on an Artificial Neural Network
Megtekintés/
Metaadat
Teljes megjelenítés
Link a dokumentumra való hivatkozáshoz:
Gyűjtemény
Absztrakt
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.