TEFAR: a lightweight, configurable framework for semi-automatic artefact component classification in EEG and TMS-EEG
- 1Royal Holloway, University of London
Abstract
Independent component analysis (ICA) is widely used to remove artefacts from EEG and TMS-EEG recordings, but the components that correspond to artefacts are usually identified by manual inspection, which is subjective and difficult to reproduce. Existing automated classifiers are either designed for ordinary EEG and do not target the artefacts specific to concurrent transcranial magnetic stimulation, or are built on EEGLAB, so none is available for FieldTrip-based pipelines. We present TEFAR, a lightweight, configurable framework for semi-automatic artefact-component classification that applies the same detectors to ordinary EEG and TMS-EEG. TEFAR is built on FieldTrip and requires no additional MATLAB toolboxes. Each artefact class (line noise, blinks, lateral eye movements, cranial muscle, cardiac activity, and the TMS decay and recharge artefacts) is identified from the spectral, spatial, or temporal signature that its components are known to express. Detection thresholds use robust statistics (the median and the median absolute deviation rather than the mean and standard deviation), so that a single dominant artefact component cannot raise the threshold that is meant to detect it. In 30 ground-truth simulations, TEFAR reached a specificity of 1.000 and a sensitivity of 0.96-0.97 for both profiles. An application of TEFAR to real EEG and TMS-EEG recordings is the next step and will be reported separately.
Related
- Automatic bridge crack detections: A lightweight segmentation model for UAV inspection
- A lightweight privacy-aware federated vision transformer for tomato leaf disease classification
- MaxCAT-Net: Hybrid Transformer-Based Skin Lesion Classification and Lightweight Segmentation with Calibration and Cross-Dataset Validation
- CodonBench: separating gene context, exon position, and variant-specific component in synonymous-variant classification
- Attention-enhanced YOLOv8n-CLS for lightweight and efficient tomato leaf disease classification
BibTeX
@misc{dimitriadou2026tefar,
title = {{TEFAR: a lightweight, configurable framework for semi-automatic artefact component classification in EEG and TMS-EEG}},
author = {C. Dimitriadou and N. Furl},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.22.751113},
url = {https://www.biorxiv.org/content/10.64898/2026.09.22.751113v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - TEFAR: a lightweight, configurable framework for semi-automatic artefact component classification in EEG and TMS-EEG
AU - C. Dimitriadou
AU - N. Furl
PY - 2026
DA - 2026/09/22
PB - bioRxiv
DO - 10.64898/2026.09.22.751113
UR - https://www.biorxiv.org/content/10.64898/2026.09.22.751113v1
AB - Independent component analysis (ICA) is widely used to remove artefacts from EEG and TMS-EEG recordings, but the components that correspond to artefacts are usually identified by manual inspection, which is subjective and difficult to reproduce. Existing automated classifiers are either designed for ordinary EEG and do not target the artefacts specific to concurrent transcranial magnetic stimulation, or are built on EEGLAB, so none is available for FieldTrip-based pipelines. We present TEFAR, a lightweight, configurable framework for semi-automatic artefact-component classification that applies the same detectors to ordinary EEG and TMS-EEG. TEFAR is built on FieldTrip and requires no additional MATLAB toolboxes. Each artefact class (line noise, blinks, lateral eye movements, cranial muscle, cardiac activity, and the TMS decay and recharge artefacts) is identified from the spectral, spatial, or temporal signature that its components are known to express. Detection thresholds use robust statistics (the median and the median absolute deviation rather than the mean and standard deviation), so that a single dominant artefact component cannot raise the threshold that is meant to detect it. In 30 ground-truth simulations, TEFAR reached a specificity of 1.000 and a sensitivity of 0.96-0.97 for both profiles. An application of TEFAR to real EEG and TMS-EEG recordings is the next step and will be reported separately.
ER -