Skip to content

Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification

Notifications You must be signed in to change notification settings

vrcarva/carvalho-etal-2019

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

50 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification

Vinícius R. Carvalho*, Márcio F.D. Moraes, Antônio P. Braga, Eduardo M.A.M. Mendes Programa de Pós-Graduação em Engenharia Elétrica – Universidade Federal de Minas Gerais – Av. Antônio Carlos 6627, 31270-901, Belo Horizonte, MG, Brasil. Núcleo de Neurociências, Departamento de Fisiologia e Biofísica, Instituto de Ciências Biológicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

*vrcarva@ufmg.br

Scripts to decompose EEG signals from the Bonn University [1] and NSC-ND [2] datasets, according to five methods: Empirical Mode Decomposition (EMD) and its extensions (EEMD, CEEMDAN), Empirical Wavelet Transform (EWT) and Variational Mode Decomposition.

Two datasets:

  1. University of Bonn EEG seizure dataset
  2. Neurology & Sleep Centre, Hauz Khas, New Delhi dataset
    Download EEG data to (1) BonnDataset/data/ and (2) NSC_ND/data/

"main_feats.py" opens and decomposes each EEG into N modes with EMD, EEMD, CEEMDAN, VMD and EWT. Features from each mode are then extracted and written in .csv files.

"main_classify.py" opens .csv files with features generated by "main_feats.py". Samples are split into training/testing sets into 5-folds for cross-validation. Several classifiers are evaluated and mean performance results are presented for 10 iterations.

"main_figs.py" plots figures that appear on the manuscript The following packages are required: numpy, scipy, scikit-learn, pandas, matplotlib, pyEMD, ewtpy, vmdpy, seaborn.

Citation: Vinícius R. Carvalho, Márcio F.D. Moraes, Antônio P. Braga, Eduardo M.A.M. Mendes, Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification, Biomedical Signal Processing and Control, Volume 62, 2020, 102073, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2020.102073.

About

Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages