Improving pilot mental workload classification through feature exploitation and combination: a feasibility study

DOI10.1016/J.COR.2004.03.022MaRDI QIDQ2387293zbMATH OpenOpenAlexFDO

Authors Jeremy B. Noel, Kenneth W. jun. Bauer, Jeffrey W. Lanning

Publication date 2 September 2005

Published in Computers \& Operations Research (Search for Journal in Brave)

Full work available at URL http://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1025&context=usafresearch

zbMATH Keywords

Artificial neural networkBackpropagationFeature calibrationFeature combinationFeature exploitationFeature identification and classificationFeature saliencyFeature spaceMental workloadPilot workloadSignal-to-noise ratio (SNR)

Mathematics Subject Classification ID

Psychophysics and psychophysiology; perception (91E30) Measurement and performance in psychology (91E45) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Automatic flight overload limiter based on estimates of the pilot's functional state
• Estimating VDT mental fatigue using multichannel linear descriptors and KPCA-HMM
• Fuzzy systems to process ECG and EEG signals for quantification of the mental workload
• A rule-based pilot performance model
• Nonparametric single-trial EEG feature extraction and classification of driver's cognitive responses

Cited in

(2)

• Thermal Imaging for Psychophysiological State Detection in the Human-Machine Interface (HMI) Control System
• Automatic flight overload limiter based on estimates of the pilot's functional state

Describes a project that uses

Uses Software

• SNNAP
• Matlab

This page was built for publication: Improving pilot mental workload classification through feature exploitation and combination: a feasibility study

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2387293)