CLARE: Cognitive Load Assessment in REaltime with Multimodal Data

Abstract

We present a novel multimodal dataset for Cognitive Load Assessment in REal-time (CLARE). The dataset contains physiological and gaze data from 24 participants with self-reported cognitive load scores as ground-truth labels. The dataset consists of four modalities, namely, Electrocardiography (ECG), Electrodermal Activity (EDA), Electroencephalogram (EEG), and Gaze tracking. To map diverse levels of mental load on participants during experiments, each participant completed four nine-minutes sessions on a computer-based operator performance and mental workload task (the MATB-II software) with varying levels of complexity in one minute segments. During the experiment, participants reported their cognitive load every 10 seconds. For the dataset, we also provide benchmark binary classification results with machine learning and deep learning models on two different evaluation schemes, namely, 10-fold and leave-one-subject-out (LOSO) cross-validation. Benchmark results show that for 10-fold evaluation, the convolutional neural network (CNN) based deep learning model achieves the best classification performance with ECG, EDA, and Gaze. In contrast, for LOSO, the best performance is achieved by the deep learning model with ECG, EDA, and EEG.

Used in syntheses

• The Science of Durable Learning

Questions this source addresses

• How does the timing of practice change what we remember?
• When does mixing different kinds of practice help us learn?
• When should an intelligent tutor make learning harder?
• Why do some things we learn stay with us?
• How was ground-truth cognitive load established in the CLARE experiments, and how did the MATB-II task vary workload complexity across sessions?
• What physiological and behavioral modalities does the CLARE dataset combine to capture real-time cognitive load, and why use multiple signal types together?
• Which sensor combination and model architecture performed best under 10-fold cross-validation versus leave-one-subject-out (LOSO) evaluation, and what does that difference imply about generalizing cognitive load classifiers to new individuals?
• Why do CNN-based deep learning models outperform other approaches for binary cognitive load classification on this multimodal dataset?