Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Feature extraction of event-related potentials using wavelets: An application to human performance monitoring
Autore:
Trejo, LJ; Shensa, MJ;
Indirizzi:
NASA,ford, Res Ctr, Human Factors Div, Human Informat Proc Res Branch, Stan NASA Stanford CA USA 94305 tors Div, Human Informat Proc Res Branch, Stan USN,ACommand Control & Ocean Surveillance Ctr, RDT&E Div, Washington, DC US USN Washington DC USA ean Surveillance Ctr, RDT&E Div, Washington, DC US
Titolo Testata:
BRAIN AND LANGUAGE
fascicolo: 1, volume: 66, anno: 1999,
pagine: 89 - 107
SICI:
0093-934X(199901)66:1<89:FEOEPU>2.0.ZU;2-9
Fonte:
ISI
Lingua:
ENG
Keywords:
wavelet; event-related potential; ERP; principal components; feature extraction; linear regression; neural networks; human performance monitoring; signal detection; vision;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Social & Behavioral Sciences
Life Sciences
Citazioni:
19
Recensione:
Indirizzi per estratti:
Indirizzo: Trejo, LJ NASA,ford, Res Ctr, Human Factors Div, Human Informat Proc Res Branch, Stan NASA Stanford CA USA 94305 Human Informat Proc Res Branch, Stan
Citazione:
L.J. Trejo e M.J. Shensa, "Feature extraction of event-related potentials using wavelets: An application to human performance monitoring", BRAIN LANG, 66(1), 1999, pp. 89-107

Abstract

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 DWTwas 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. In addition, the DWT-based models were more resistant to model degradation due to over-fitting than PCA-based models. 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 high-power DWT coefficients trained with fewer iterations, generalized to new data better, and were moreresistant to overfitting 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. (C) 1999 Academic Press.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 03/04/20 alle ore 09:08:00