Abstract
The study of the cognitive effects caused by work activities are vital to ensure the well-being of a worker, and this work presents a strategy to analyze these effects while they are carrying out their activities. Our proposal is based on the implementation of pattern recognition techniques to identify emotions in facial expressions and correlate them to a proposed situation awareness model that measures the levels of comfort and mental stability of a worker and proposes corrective actions. We present the experimental results that could not be collected through traditional techniques since we carry out a continuous and uninterrupted assessment of the cognitive situation of a worker.
Highlights
There is no doubt that the technological deployment of the last decades has considerably increased the activities that a person can perform in a company; technology contributes to the generation of new problems such as information overload or affectation in short- and long-term memory.According to the International Ergonomics Association (IEA), ergonomics considers the cognitive processes that are concerned with mental processes, such as perception, memory, reasoning, and motor response, and how they affect the interactions among humans and systems [1].Cognitive ergonomics emphasizes the analysis of mental functions and the design of user-centered systems that support cognitive tasks processes, to reduce the psychological wear [2]
Cognitive ergonomics is focused on the prevention of “human failures,” e.g., when an accident occurs and expert studies fail to detect any mechanical failure or physiological cause which can attribute responsibility; usually, the conclusion is that the accident was due to “human error” and it is at this point only when the traditional methodologies begin to analyze other factors, such as the emotional processes, even though emotions are one of the primary mechanisms in human behavior
Some proposals that interrelate aspects of the affective computing and cognitive ergonomics interaction are presented, e.g., it was beneficial that the relationship between the Ekman and Russell models match with the Endsley’s model for the situation awareness (SA) considerations to define the proposed scenario as a cognitive ergonomics problem
Summary
There is no doubt that the technological deployment of the last decades has considerably increased the activities that a person can perform in a company; technology contributes to the generation of new problems such as information overload or affectation in short- and long-term memory.According to the International Ergonomics Association (IEA), ergonomics considers the cognitive processes that are concerned with mental processes (cognitive ergonomics), such as perception, memory, reasoning, and motor response, and how they affect the interactions among humans and systems [1].Cognitive ergonomics emphasizes the analysis of mental functions and the design of user-centered systems that support cognitive tasks processes, to reduce the psychological wear [2]. According to the International Ergonomics Association (IEA), ergonomics considers the cognitive processes that are concerned with mental processes (cognitive ergonomics), such as perception, memory, reasoning, and motor response, and how they affect the interactions among humans and systems [1]. Several studies have been carried out to address cognitive problems [3,4,5], most of them implementing traditional techniques for data collection, such as surveys or interviews. Some proposals consider the implementation of technological strategies in data collection, they are invasive and could affect the experimental conditions. This work proposes a non-invasive solution by implementing an intelligent pattern recognition algorithm through video analysis or facial emotion recognition (FER), which has had significant advances in the area in the last decade, mainly to the democratization of machine learning and advances in GPU technologies. Deep learning has shown competitive results in the FER analysis, and it is the convolutional neural networks (CNN) that have achieved the best results [6,7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
