Comparison between artificial neural network and multilinear regression models in an evaluation of cognitive workload in a flight simulator

Hannula, Manne; Huttunen, Kerttu; Koskelo, Jukka; Laitinen, Tomi; Leino, Tuomo

doi:10.1016/j.compbiomed.2008.09.007

« Previous Next »Computers in Biology and Medicine
Volume 38, Issue 11 , Pages 1163-1170, November 2008

Comparison between artificial neural network and multilinear regression models in an evaluation of cognitive workload in a flight simulator

Manne Hannula
- Medical Engineering R & D Center, Oulu University of Applied Sciences, Finland
- Department of Otorhinolaryngology, Institute of Clinical Medicine, University of Oulu, Finland
- Corresponding author at: Medical Engineering R & D Center, Oulu University of Applied Sciences, Kotkantie 1, 90250 Oulu, Finland. Tel.: +358504309234.
Kerttu Huttunen
- Department of Otorhinolaryngology, Institute of Clinical Medicine, University of Oulu, Finland
Jukka Koskelo
- Department of Clinical Physiology and Nuclear Medicine, University of Kuopio and Kuopio University Hospital, Finland
Tomi Laitinen
- Department of Clinical Physiology and Nuclear Medicine, University of Kuopio and Kuopio University Hospital, Finland
Tuomo Leino
- Department of Otorhinolaryngology, Institute of Clinical Medicine, University of Oulu, Finland
- Air Force Academy, The Finnish Air Force, Finland

Received 31 January 2008; accepted 16 September 2008.

Abstract

In this study, the performances of artificial neural network (ANN) analysis and multilinear regression (MLR) model-based estimation of heart rate were compared in an evaluation of individual cognitive workload. The data comprised electrocardiography (ECG) measurements and an evaluation of cognitive load that induces psychophysiological stress (PPS), collected from 14 interceptor fighter pilots during complex simulated F/A-18 Hornet air battles. In our data, the mean absolute error of the ANN estimate was 11.4 as a visual analog scale score, being 13–23% better than the mean absolute error of the MLR model in the estimation of cognitive workload.

Keywords: Nonlinear data analysis, Intelligent systems, Heart rate analysis, Psychophysiological stress factors, Cognitive load