TY - GEN
T1 - Cognitive workload classification using cardiovascular measures and dynamic features
AU - Magnusdottir, Eydis H.
AU - Johannsdottir, Kamilla R.
AU - Bean, Christian
AU - Olafsson, Brynjar
AU - Gudnason, Jon
N1 - Funding Information: This work is sponsored ISAVIA, Icelandair and the Icelandic Center for Research (RANNIS) under the project Monitoring cognitive workload in ATC using speech analysis, Grant No 130749051. Publisher Copyright: © 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Monitoring cognitive workload has the potential to improve performance and fidelity in human decision making through a real-time monitoring model. Multiple studies have shown a successful binary classification of high and low workload using various methods and often focused on multiple physiological signals. A more detailed detection of cognitive workload is needed for a meaningful and reliable workload monitoring tool. This study focuses on trinary workload classification of parameters extracted from the cardiovascular system. The experiment was validated with the use of a database containing 96 participants performing tasks designed to induce slight variations in cognitive workload. Two distinct supervised learning classifying methods were used and their likelihood score used for the classification schemes of (1) each heartbeat and (2) each task screen. The results show that the support vector classifier outperforms the random forest with the average misclassification rate of 20.44% using the whole screen classification scheme instead of individual heartbeat classification.
AB - Monitoring cognitive workload has the potential to improve performance and fidelity in human decision making through a real-time monitoring model. Multiple studies have shown a successful binary classification of high and low workload using various methods and often focused on multiple physiological signals. A more detailed detection of cognitive workload is needed for a meaningful and reliable workload monitoring tool. This study focuses on trinary workload classification of parameters extracted from the cardiovascular system. The experiment was validated with the use of a database containing 96 participants performing tasks designed to induce slight variations in cognitive workload. Two distinct supervised learning classifying methods were used and their likelihood score used for the classification schemes of (1) each heartbeat and (2) each task screen. The results show that the support vector classifier outperforms the random forest with the average misclassification rate of 20.44% using the whole screen classification scheme instead of individual heartbeat classification.
UR - https://www.scopus.com/pages/publications/85047168552
U2 - 10.1109/CogInfoCom.2017.8268269
DO - 10.1109/CogInfoCom.2017.8268269
M3 - Conference contribution
T3 - 8th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2017 - Proceedings
BT - 8th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2017
Y2 - 11 September 2017 through 14 September 2017
ER -