Investigation of changes in the operator’s state by analyzing the characteristics of blinking

2021

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.1088/1757-899x/1027/1/012030
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Abstract This paper discusses in detail an approach using the method of automatic blink recognition for assessing the state of the operator using deep convolutional neural networks. It also analyzes the characteristics of blinking to detect the facts of loss of concentration.