Z-score normalization of EEG power spectral density features decreased cross-subject conditional and marginal shifts, yielding the smallest average generalization gap for mental workload classification.
Feature normalization strategies such as whitening can significantly reduce cross-subject conditional shifts in EEG data, though the effects vary depending on the type of concurrent physical activity.
Assessment of mental workload in real-world conditions is key to ensuring 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.
Albuquerque et al. (Tue,) conducted a other in Mental workload (n=18). Z-score normalization (whitening) vs. No normalization or baseline normalization was evaluated on Cross-subject mental workload classification accuracy (leave-one-subject-out). Z-score normalization of EEG power spectral density features decreased cross-subject conditional and marginal shifts, yielding the smallest average generalization gap for mental workload classification.