Date of Award
Industrial and Manufacturing Systems Engineering
Bio-signals, Estimation Model, Functional Data Analysis, Human Driver, Mental Workload, Psycho-physiological
Yong Hoon Kim
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recent studies have focused on accurately estimating mental workload using machine learning algorithms and extracting features from psycho-physiological measures. However, feature extraction leads to the loss of valuable information and often results in binary classifications that lack specificity in the identification of optimum mental workload levels. This study investigates the feasibility of using raw psycho-physiological data (EEG, facial EMG, ECG, EDA, pupillometry) combined with Functional Data Analysis (FDA) to estimate mental workload of human drivers. A driving scenario with five tasks was employed, and subjective ratings were collected using the modified Bedford workload scale. Results demonstrate that the FDA applied to nine different combinations of raw psycho-physiological signals achieved a maximum 90% accuracy, outperforming extracted features by 73%. This study shows that mental workload of human drivers can be accurately estimated without utilizing the burdensome feature extraction. The approach proposed in this study offers promise for mental workload assessment in real-world applications.
Eniyandunmo, David OLORUNFEMI, "Applying Functional Data Analysis to Estimate the Mental Workload of the Human Driver" (2024). Electronic Theses and Dissertations. 9165.