Selecting Salient Features of Psychophysiological Measures
Abstract
Determining operator cognitive or functional state is a critical component of adaptive aiding systems. To determine cognitive state, we must decide which measured features from the human will assist in distinguishing different levels of mental activity. A battery of psychophysiological signals was collected for two levels of cognitive workload from which 43 measures were derived. Three feature-reduction methods, principal component analysis, a weight-based partial derivative method, and a weight-based signal-to-noise ratio were applied, and the results were used as inputs to an artificial neural network for training and classification. Average classification accuracies up to 89.7 percent were achieved and the number of input features required was reduced by up to 84 percent.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2001
- Accession Number
- ADA396165
Entities
People
- Chris A. Russel
- Steve G. Gustafson
Organizations
- Air Force Research Laboratory