Linear and Neural Network Models for Predicting Human Signal Detection Performance From Event-Related Potentials: A Comparison of the Wavelet Transform With Other Feature Extraction Methods

This report describes the development and evaluation of mathematical models for predicting human performance from discrete wavelet transforms (DWT) of event-related potentials (ERP) elicited by task-relevant stimuli. The DWT was compared to principal components analysis (PCA) for representation of ERPs in linear regression and neural network models developed to predict a composite measure of human signal detection performance. Linear regression models based on coefficients of the decimated DWT predicted signal detection performance with half as many free parameters as comparable models based on PCA scores and were relatively more resistant to model degradation due to over-fitting. Feed-forward neural networks were trained using the backpropagation algorithm to predict signal detection performance based on raw ERPs, PCA scores, or high-power coefficients of the DWT. Neural networks based on highpower DWT coefficients trained with fewer iterations, generalized to new data better, and were more resistant to over-fitting than networks based on raw ERPs. Networks based on PCA scores did not generalize to new data as well as either the DWT network or the raw ERP network. The results show that wavelet expansions represent the ERP efficiently and extract behaviorally important features for use in linear regression or neural network models of human performance. The efficiency of the DWT is discussed in terms of its decorrelation and energy compaction properties. In addition, the DWT models provided evidence that a pattern of low-frequency activity (1 to 3.5 Hz) occurring at specific times and scalp locations is a reliable correlate of human signal detection performance. Proceedings of the Fifth Workshop on Neural Networks: Academic/Industrial/NASA/Defense, SPIE Volume 2204 (pp. 153-161). San Diego: Society for Computer Simulation.