Deep Models for Engagement Assessment With Scarce Label Information

TL;DR

This paper introduces two deep learning models that effectively assess engagement levels from EEG data even with limited labeled samples, outperforming traditional features in accuracy.

Contribution

The study proposes novel deep classifier and autoencoder models pretrained on unlabeled EEG data, fine-tuned with scarce labels, improving engagement assessment accuracy.

Findings

Deep models outperform original EEG features in engagement classification.

Models achieve over 86% accuracy with 20% labeled data.

Deep representations are more effective with scarce labels.

Abstract

Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with limited label information for engagement assessment do not perform well because of overfitting. In this paper, we proposed two deep models (i.e., a deep classifier and a deep autoencoder) for engagement assessment with scarce label information. We recruited 15 pilots to conduct a 4-h flight simulation from Seattle to Chicago and recorded their electroencephalograph (EEG) signals during the simulation. Experts carefully examined the EEG signals and labeled 20 min of the EEG data for each pilot. The EEG signals were preprocessed and power spectral features were extracted. The deep models were pretrained by the unlabeled data and were fine-tuned by a different proportion of the labeled data (top 1%, 3%, 5%, 10%, 15%, and 20%) to learn new representations for engagement assessment. The models were then tested on the remaining labeled data. We compared performances of the new data representations with the original EEG features for engagement assessment. Experimental results show that the representations learned by the deep models yielded better accuracies for the six scenarios (77.09%, 80.45%, 83.32%, 85.74%, 85.78%, and 86.52%), based on different proportions of the labeled data for training, as compared with the corresponding accuracies (62.73%, 67.19%, 73.38%, 79.18%, 81.47%, and 84.92%) achieved by the original EEG features. Deep models are effective for engagement assessment especially when less label information was used for training.