Association between Generalization Performance and Interpretability in Deep Learning for Cognitive Load Recognition with Frontal EEG
Cognitive load recognition with electroencephalography (EEG) by deep neural network (DNN) has been gathering attention for well-being applications in daily life; However, generalization performance for untrained data has not been investigated thoroughly. We hypothesized that generalization performance may depend on psychophysiological plausibility, and evaluated the performance using interpretable DNNs. The results suggested that a model with highly salient features throughout the EEG frequency bands associated with cognitive load have high generalization performance.
Related PublicationsView All
Development of a model to estimate pleasant and unpleasant affective states
Naoya Sazuka, Koki Katsumata, Yota Komoriya, Takeyuki Oba*, Hideki Ohira*We aimed to build a model to estimate pleasant and unpleasant affective states. Affective states of pleasure o […]
Slow EEG Fluctuation Reflects Cognitive Load and Affective Arousal
Naoya Sazuka, Koki Katsumata, Yota Komoriya, Takeyuki Oba*, Hideki Ohira*We previously showed that fluctuations of the EEG alpha power at a very low frequency range reflects ability t […]