Cross-Subject Statistical Shift Estimation for Generalized Electroencephalography-based Mental Workload Assessment

TL;DR

A way to measure the statistical (marginal and conditional) shift observed on data obtained from different users and use this measure to quantitatively assess the effectiveness of different adaptation strategies is proposed.

Abstract

Assessment of mental workload in real-world conditions is key to ensure the performance of workers executing tasks that demand sustained attention. Previous literature has employed electroencephalography (EEG) to this end despite having observed that EEG correlates of mental workload vary across subjects and physical strain, thus making it difficult to devise models capable of simultaneously presenting reliable performance across users. Domain adaptation consists of a set of strategies that aim at allowing for improving machine learning systems performance on unseen data at training time. Such methods, however, might rely on assumptions over the considered data distributions, which typically do not hold for applications of EEG data. Motivated by this observation, in this work we propose a strategy to estimate two types of discrepancies between multiple data distributions, namely marginal and conditional shifts, observed on data collected from different subjects. Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies. In particular, we consider EEG data collected from individuals performing mental tasks while running on a treadmill and pedaling on a stationary bike and explore the effects of different normalization strategies commonly used to mitigate cross-subject variability. We show the effects that different normalization schemes have on statistical shifts and their relationship with the accuracy of mental workload prediction as assessed on unseen participants at training time.

Figures (8)

• Figure 1: Boxplots with 30 independent estimates of the aggregate cross-subject conditional shift across different normalization strategies for participants which performed physical activity using a treadmill. Lower values represent smaller estimated conditional shift.
• Figure 2: Boxplots with 30 independent estimates of the aggregate cross-subject conditional shift across different normalization strategies for participants which performed physical activity using a bike. Lower values represent smaller estimated conditional shift.
• Figure 3: Pair-wise cross-subject conditional shift with non-normalized and whitened features computed from subjects that performed physical activity on the treadmill.
• Figure 4: Pair-wise cross-subject conditional shift with non-normalized and whitened features computed from subjects that performed physical activity on the bike.
• Figure 5: Boxplots with 30 independent estimates of the aggregate cross-subject marginal shift across different normalization strategies for participants which performed physical activity using a treadmill. Lower values represent smaller estimated marginal shifts.