Assessing Continuous Operator Workload With a Hybrid Scaffolded Neuroergonomic Modeling Approach

Abstract

Objective: We aimed to predict operator workload from neurological data using statistical learning methods to fit neurological-to-state-assessment models.Background: Adaptive systems require real-time mental workload assessment to perform dynamic task allocations or operator augmentation as workload issues arise. Neuroergonomic measures have great potential for informing adaptive systems, and we combine these measures with models of task demand as well as information about critical events and performance to clarify the inherent ambiguity of interpretation.Method: We use machine learning algorithms on electroencephalogram (EEG) input to infer operator workload based upon Improved Performance Research Integration Tool workload model estimates.Results: Cross-participant models predict workload of other participants, statistically distinguishing between 62% of the workload changes. Machine learning models trained from Monte Carlo resampled workload profiles can be used in place of deterministic workload profiles for cross-participant modeling without incurring a significant decrease in machine learning model performance, suggesting that stochastic models can be used when limited training data are available.Conclusion: We employed a novel temporary scaffold of simulation-generated workload profile truth data during the model-fitting process. A continuous workload profile serves as the target to train our statistical machine learning models. Once trained, the workload profile scaffolding is removed and the trained model is used directly on neurophysiological data in future operator state assessments.Application: These modeling techniques demonstrate how to use neuroergonomic methods to develop operator state assessments, which can be employed in adaptive systems.

Applications of EEG indices for the quantification of human cognitive performance: A systematic review and bibliometric analysis

“…That study concluded that only FD could be used to evaluate human mental workload. Several computational intelligence algorithms have been used to classify and detect mental workload levels, such as SVM [72,138,[190][191][192], ANN [193][194][195], and random forest (RF) [196].…”

“…Furthermore, a queuing network-based computational neuroergonomic architecture [234] is a potential approach to the development of recognition and adaptive systems that can make correct decisions in a short period of time [235]. Although some researchers have predicted current human states using machine learning algorithms, the successful application of such algorithms has been limited [236]. Another shortcoming is the lack of designs with ecological validity.…”

A Curvilinear Effect of Mental Workload on Mental Effort and Behavioral Adaptability: An Approach With the Pre-Ejection Period

“…Physiological measures are frequently used to classify the level of mental effort (Borghetti, Giametta, & Rusnock, 2017;Marinescu et al, 2018). Different physiological measures, such as skin conductance, temperature, heart rate (HR), or pupil dilatation, are frequently used to establish the level of sympathetic nervous system activity (Capa, Audiffren, & Ragot, 2008).…”

Human in Focus: Future Research and Applications of Ubiquitous User Monitoring

“…Human monitoring enables computer systems to interpret and predict the human cognitive or physical states. For example, random forest classification algorithms have been successfully applied to predict driver drowsiness based on steering angles of the vehicle (McDonald, Lee, Schwarz, & Brown, 2013) and operator workload based on EEG (Borghetti, Giametta, & Rusnock, 2017). Human monitoring is essential to adaptive automation.…”