Automatic EEG Signal Preprocessing and Feature Extraction
Updated Fri, 12 Aug 2022 12:29:29 +0000
In this Script a suitable Butterworth band-pass filter (0.5–60 Hz) was employed to eliminate out-of-band noise.
In addition, a 50 Hz notch filter was utilized to eliminate the remaining powerline noise. To make it easier to track future results, we normalized the entire
In the step of feature extraction, linear and nonlinear univariate features, as well as nonlinear multivariate features, were extracted from EEG signals. Individual recording channels and five frequency sub-bands (Delta,Theta, Alpha , Beta and Gamma) underwent spectral analysis of average power. On the basis of the Kaiser window, five Finite Impulse Response (FIR) filters were created to split the original signals into five subbands.
Delta Average Band Power , Theta Average Band Power , Alpha Average Band Power , Beta Average Band Power , Gamma Average Band Power Theta To Beta Ratio(TBR)
Sample Entropy , Shannon Entropy , Dispersion Entropy , MultiScale Sample Entropy
To run this Code, you will need to add the
functions folder to your MATLAB path
And then run the following script
WorkSpace.mat is result of run.
Version 1.0 August 2022 | Copyright (c) 2022 | All rights reserved
Farhad Abedinzadeh torghabeh | Master Student of Biomdeical Engineering
Farhad Abedinzade (2022). Auto EEG Signal Preprocessing and Feature Extraction (https://github.com/farhadabedinzadeh/AutomaticEEGSignalPreprocessingAndLinearNonlinearFeatureExtraction/releases/tag/1.0.0), GitHub. Retrieved August 12, 2022.
Farhad Abedinzadeh (2022). Automatic EEG Signal Preprocessing and Feature Extraction (https://github.com/farhadabedinzadeh/AutomaticEEGSignalPreprocessingAndLinearNonlinearFeatureExtraction/releases/tag/1.0.0), GitHub. Retrieved .
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!