Comparison of linear, nonlinear, and feature selection methods for EEG signal classification

By Deon Garrett, David A. Peterson, Charles Anderson, Michael H. Thaut. IEEE transactions on neural systems and rehabilitation engineering, 2003

662 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c334271678a186732edab0f50d9d2040f10db87b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation. (2017, neutral): “The mathematical algorithms for discrete classification include linear discriminant analysis (LDA) (259, 288, 629), support vector machine (56, 288, 780), ANNs (359), multilayer perceptron (43, 75), hidden Markov models (603, 655), k nearest neighbors classifier (177), and nonlinear Bayesian classif”
Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review (2020, methodology): “Whereas, LDA is used to reduce dimensions of feature sets by finding linear combinations of feature vectors [26].”
A review of channel selection algorithms for EEG signal processing (2015, methodology): “To classify these signals, for example, we have two choices: to work on a subset of channels selected based on certain criteria or to work on all channels [5].”
Brain Computer Interfaces, a Review (2012, methodology): “SVM has been used to classify feature vectors for binary [239,240] and multiclass problems [228,230].”
Brain–computer interface systems: progress and prospects (2007, methodology): “Translation algorithms vary widely in complexity, from linear methods, such as stepwise discriminant analysis or weighted frequency summation, to nonlinear neural and adaptive logic networks [18,41,57,60,83,87–90] .”
Comparative Analysis of Spectral Approaches to Feature Extraction for EEG-Based Motor Imagery Classification (2008, methodology): “SVMs havealsobeen heavilyused in BCI research [ 11 ], [26].”
A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals (2007, methodology): “Feature selection/dimensionality reduction method Reference ID Genetic algorithm (GA) (Flotzinger et al 1994, Garrett et al 2003, Graimann et al 2003a, 2004, Peterson et al 2005, Scherer et al 2004, Schroder et al 2003, Tavakolian et al 2004, Yom-Tov and Inbar 2001, 2002) Principal component…”
Multiclass Support Vector Machines for EEG-Signals Classification (2007, methodology): “[25] used decision-directed acyclic graphs (DDAGs) for application of the SVMs to the multiclass EEG (spontaneous EEG during five mental tasks) signals classification problem.”