Literature DB >> 23466267

Characterizing multivariate decoding models based on correlated EEG spectral features.

Dennis J McFarland1.   

Abstract

OBJECTIVE: Multivariate decoding methods are popular techniques for analysis of neurophysiological data. The present study explored potential interpretative problems with these techniques when predictors are correlated.
METHODS: Data from sensorimotor rhythm-based cursor control experiments was analyzed offline with linear univariate and multivariate models. Features were derived from autoregressive (AR) spectral analysis of varying model order which produced predictors that varied in their degree of correlation (i.e., multicollinearity).
RESULTS: The use of multivariate regression models resulted in much better prediction of target position as compared to univariate regression models. However, with lower order AR features interpretation of the spectral patterns of the weights was difficult. This is likely to be due to the high degree of multicollinearity present with lower order AR features.
CONCLUSIONS: Care should be exercised when interpreting the pattern of weights of multivariate models with correlated predictors. Comparison with univariate statistics is advisable. SIGNIFICANCE: While multivariate decoding algorithms are very useful for prediction their utility for interpretation may be limited when predictors are correlated.
Copyright © 2013 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

Entities:  

Mesh:

Year:  2013        PMID: 23466267      PMCID: PMC3676699          DOI: 10.1016/j.clinph.2013.01.015

Source DB:  PubMed          Journal:  Clin Neurophysiol        ISSN: 1388-2457            Impact factor:   3.708


  9 in total

1.  American Electroencephalographic Society guidelines for standard electrode position nomenclature.

Authors: 
Journal:  J Clin Neurophysiol       Date:  1991-04       Impact factor: 2.177

2.  Brain-computer interface (BCI) operation: signal and noise during early training sessions.

Authors:  Dennis J McFarland; William A Sarnacki; Theresa M Vaughan; Jonathan R Wolpaw
Journal:  Clin Neurophysiol       Date:  2005-01       Impact factor: 3.708

3.  BCI Meeting 2005--workshop on BCI signal processing: feature extraction and translation.

Authors:  Dennis J McFarland; Charles W Anderson; Klaus-Robert Müller; Alois Schlögl; Dean J Krusienski
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2006-06       Impact factor: 3.802

4.  Sensorimotor rhythm-based brain-computer interface (BCI): model order selection for autoregressive spectral analysis.

Authors:  Dennis J McFarland; Jonathan R Wolpaw
Journal:  J Neural Eng       Date:  2008-04-22       Impact factor: 5.379

5.  Multivariate decoding and brain reading: introduction to the special issue.

Authors:  John-Dylan Haynes
Journal:  Neuroimage       Date:  2011-04-06       Impact factor: 6.556

6.  Spatial filter selection for EEG-based communication.

Authors:  D J McFarland; L M McCane; S V David; J R Wolpaw
Journal:  Electroencephalogr Clin Neurophysiol       Date:  1997-09

Review 7.  Decoding patterns of human brain activity.

Authors:  Frank Tong; Michael S Pratte
Journal:  Annu Rev Psychol       Date:  2011-09-19       Impact factor: 24.137

Review 8.  Encoding and decoding in fMRI.

Authors:  Thomas Naselaris; Kendrick N Kay; Shinji Nishimoto; Jack L Gallant
Journal:  Neuroimage       Date:  2010-08-04       Impact factor: 6.556

9.  Decoding center-out hand velocity from MEG signals during visuomotor adaptation.

Authors:  Trent J Bradberry; Feng Rong; José L Contreras-Vidal
Journal:  Neuroimage       Date:  2009-06-16       Impact factor: 6.556

  9 in total
  5 in total

Review 1.  Brain-computer interfaces for amyotrophic lateral sclerosis.

Authors:  Dennis J McFarland
Journal:  Muscle Nerve       Date:  2020-06       Impact factor: 3.217

Review 2.  Brain-controlled muscle stimulation for the restoration of motor function.

Authors:  Christian Ethier; Lee E Miller
Journal:  Neurobiol Dis       Date:  2014-10-28       Impact factor: 5.996

3.  Prediction of subjective ratings of emotional pictures by EEG features.

Authors:  Dennis J McFarland; Muhammad A Parvaz; William A Sarnacki; Rita Z Goldstein; Jonathan R Wolpaw
Journal:  J Neural Eng       Date:  2016-12-09       Impact factor: 5.379

4.  EEG Error Prediction as a Solution for Combining the Advantages of Retrieval Practice and Errorless Learning.

Authors:  Ellyn A Riley; Dennis J McFarland
Journal:  Front Hum Neurosci       Date:  2017-03-27       Impact factor: 3.169

5.  Interpreting neural decoding models using grouped model reliance.

Authors:  Simon Valentin; Maximilian Harkotte; Tzvetan Popov
Journal:  PLoS Comput Biol       Date:  2020-01-06       Impact factor: 4.475

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.