Real-time Mental Workload Detection and Alert System with Brain Computer Interface for Augmenting Human Performance at Work

John, Alka Rachel

Real-time Mental Workload Detection and Alert System with Brain Computer Interface for Augmenting Human Performance at Work

John, Alka Rachel

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (6.45 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	John, Alka Rachel
dc.date.accessioned	2024-03-25T23:13:44Z
dc.date.available	2024-03-25T23:13:44Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/177141
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	One of the key factors that impact the efficiency of human operators in complex, interactive work environments is the level of mental workload. When an operator is overwhelmed with mental demands, it can negatively impact their performance and lead to mistakes, which can harm the system’s efficiency and safety. To ensure optimal performance, it is important to find a balance and avoid both overload and underload conditions, as the operator’s performance can suffer in both situations. This work explored the feasibility of employing electroencephalogram (EEG) data in measuring the workload of human operators in safety-critical work environments. Two safety-critical environments were considered: a stationary Air Traffic Control (ATC) and a more dynamic physical Human Robot Collaboration (pHRC) environment with uncontrolled, real-world physical interactions with an abrasive blasting robot. Further, we explored the error awareness of operators engaged in a physical interaction with the robot in under varying workload conditions. We successfully uncovered EEG spectral power, eye, and heart rate variability correlates of mental workload variations for simple tasks of air traffic controllers, providing a comprehensive understanding of the workload demands in ATC tasks. Our preliminary findings in the ATC experiment pave the way to develop intelligent closed-loop mental workload aware systems for ATC. The systematic investigation into the impact of workload variations on operator’s performance in a pHRC settings revealed that both task and physical performance degraded with increasing workload. Our study successfully isolated and retrieved the biomarkers of workload variations in a pHRC despite strenuous physical activity. Error awareness was found to deteriorate with increasing workload, exposing the significance of measuring and maintaining the human user’s workload at an optimal level to ensure the safe and reliable use of BCI technology for intuitive physical human-robot collaboration. Therefore, this research posits that the mental workload of a human operator can be predicted in real-time from physiological signals, and the estimated workload information can be used to provide safety alerts, enhancing the safety measures in place in many work environments. By utilizing newly discovered biomarkers, a tool can be developed to detect workload variations and estimate error processing capacity, facilitating a mental workload-related safety alert system for real-world applications. Thus, this research aims to demonstrate the potential of creating an intelligent system that can detect mental workload in order to improve safety and efficiency in complex work environments.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/177141/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2023 Alka Rachel John
dc.rights	au.edu.uts.lib/nph
dc.title	Real-time Mental Workload Detection and Alert System with Brain Computer Interface for Augmenting Human Performance at Work	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

One of the key factors that impact the efficiency of human operators in complex, interactive work environments is the level of mental workload. When an operator is overwhelmed with mental demands, it can negatively impact their performance and lead to mistakes, which can harm the system’s efficiency and safety. To ensure optimal performance, it is important to find a balance and avoid both overload and underload conditions, as the operator’s performance can suffer in both situations. This work explored the feasibility of employing electroencephalogram (EEG) data in measuring the workload of human operators in safety-critical work environments. Two safety-critical environments were considered: a stationary Air Traffic Control (ATC) and a more dynamic physical Human Robot Collaboration (pHRC) environment with uncontrolled, real-world physical interactions with an abrasive blasting robot. Further, we explored the error awareness of operators engaged in a physical interaction with the robot in under varying workload conditions. We successfully uncovered EEG spectral power, eye, and heart rate variability correlates of mental workload variations for simple tasks of air traffic controllers, providing a comprehensive understanding of the workload demands in ATC tasks. Our preliminary findings in the ATC experiment pave the way to develop intelligent closed-loop mental workload aware systems for ATC. The systematic investigation into the impact of workload variations on operator’s performance in a pHRC settings revealed that both task and physical performance degraded with increasing workload. Our study successfully isolated and retrieved the biomarkers of workload variations in a pHRC despite strenuous physical activity. Error awareness was found to deteriorate with increasing workload, exposing the significance of measuring and maintaining the human user’s workload at an optimal level to ensure the safe and reliable use of BCI technology for intuitive physical human-robot collaboration. Therefore, this research posits that the mental workload of a human operator can be predicted in real-time from physiological signals, and the estimated workload information can be used to provide safety alerts, enhancing the safety measures in place in many work environments. By utilizing newly discovered biomarkers, a tool can be developed to detect workload variations and estimate error processing capacity, facilitating a mental workload-related safety alert system for real-world applications. Thus, this research aims to demonstrate the potential of creating an intelligent system that can detect mental workload in order to improve safety and efficiency in complex work environments.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177141