TY - JOUR
T1 - Measurement of Mental Workload Using Heart Rate Variability and Electrodermal Activity
AU - Fawwaz, Aisy Al
AU - Rahma, Osmalina Nur
AU - Ain, Khusnul
AU - Ittaqillah, Sayyidul Istighfar
AU - Chai, Rifai
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2024
Y1 - 2024
N2 - Mental workload reflects the cognitive demands placed on individuals when performing tasks, particularly under pressure. As the esports industry continues to expand rapidly, understanding and managing the mental workload of esports athletes is crucial due to its impact on performance. While self-reported measures offer insights into players' subjective experiences, this study integrates these reports with objective physiological data - heart rate variability (HRV) and electrodermal activity (EDA) - to comprehensively assess mental workload. Data from 96 participants over 21 competitive matches were analyzed, revealing significant autonomic responses linked to cognitive demands. Key predictors of workload, such as Tonic Peak Count and Phasic Peak Count, were identified. Using machine learning models like support vector machine (SVM), workload classification achieved an accuracy of 81.97% and an AUC of 0.8824. These results underscore the value of combining physiological and subjective metrics to enable real-time monitoring and provide actionable insights for enhancing performance and well-being in high-pressure esports settings.
AB - Mental workload reflects the cognitive demands placed on individuals when performing tasks, particularly under pressure. As the esports industry continues to expand rapidly, understanding and managing the mental workload of esports athletes is crucial due to its impact on performance. While self-reported measures offer insights into players' subjective experiences, this study integrates these reports with objective physiological data - heart rate variability (HRV) and electrodermal activity (EDA) - to comprehensively assess mental workload. Data from 96 participants over 21 competitive matches were analyzed, revealing significant autonomic responses linked to cognitive demands. Key predictors of workload, such as Tonic Peak Count and Phasic Peak Count, were identified. Using machine learning models like support vector machine (SVM), workload classification achieved an accuracy of 81.97% and an AUC of 0.8824. These results underscore the value of combining physiological and subjective metrics to enable real-time monitoring and provide actionable insights for enhancing performance and well-being in high-pressure esports settings.
KW - Electrodermal Activity
KW - Esports Performance
KW - Heart Rate Variability
KW - Machine Learning Classification
KW - Mental Workload
UR - http://www.scopus.com/inward/record.url?scp=85213280861&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2024.3521649
DO - 10.1109/ACCESS.2024.3521649
M3 - Article
AN - SCOPUS:85213280861
SN - 2169-3536
JO - IEEE Access
JF - IEEE Access
ER -