Scripts are provided to investigate or apply artifact removal to EEG signals with a focus on a few channels case (i.e., low-density EEG).
These scripts are related to:
- finding optimal parameters for ASR,
- using multivariate empirical mode decomposition (MEMD) with ASR to deal with few channels
You can use any data, but if you are willing to replicate the results of the references below, we suggest:
- MRC EEG data simulator (https://doi.org/10.1111/j.1469-8986.2004.00239.x) + EEGdenoiseNet (https://github.com/ncclabsustech/EEGdenoiseNet)
- SEED-G simulator (https://doi.org/10.3390/s21113632) + EEGdenoiseNet (https://github.com/ncclabsustech/EEGdenoiseNet)
- real data with artifact from https://github.com/stefan-ehrlich/dataset-automaticArtifactRemoval
- EEGLAB version 2021.1
You will find what we did in the following references!
- A. Cataldo, S. Criscuolo, E. De Benedetto, A. Masciullo, M. Pesola, R. Schiavoni, and S. Invitto "A Method for Optimizing the ASR Performance in low-density EEG", IEEE Sensors Journal, 22(21), pp.21257-21265.
- P. Arpaia, E. De Benedetto, A. Esposito, A. Natalizio, M. Parvis, and M. Pesola, "Low-density EEG correction with multivariate decomposition and artifact subspace reconstruction", IEEE Sensors Journal, 2023 (to be published)
- P. Arpaia, E. De Benedetto, A. Esposito, A. Natalizio, M. Parvis, and M. Pesola, "Comparing artifact removal techniques for daily-life electroencephalography with few channels", in IEEE International Symposium on Medical Measurements and Applications, (Taormina, Italy), 2022.