Presentation
Mental Workload Classification Using Electrocardiogram Data
SessionPoster Session 1
DescriptionMental workload is a critical factor in human performance, particularly in high-stakes environments like aviation and healthcare. Excessive cognitive demands can impair decision-making, leading to safety risks. This study investigates the use of ECG-derived features for classifying mental workload levels using machine learning models. ECG data was collected from participants engaged in a virtual flight task with varying workload conditions. We applied five machine learning models—Logistic Regression, Random Forest, Support Vector Machine, Extreme Gradient Boosting, and Gradient Boosting—to classify mental workload in a binary framework (easiest vs. most difficult levels). Results show that RF outperformed the others, achieving the highest F1 score of 66.7%. These findings highlight the potential of ECG-based classification for real-time mental workload monitoring, with implications for improving safety and performance in critical applications. Further exploration of multimodal approaches could enhance classification accuracy and robustness.
Event Type
Poster
TimeTuesday, October 14th5:30pm - 6:30pm CDT
LocationRiverside East