EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

KnowEEG: Explainable knowledge driven EEG classification

Amarpal Sahota, Navid Mohammadi Foumani, Raul Santos-Rodriguez, Zahraa S. Abdallah

Neurocomputing · 2027-01 · 710 · 135337

DOI: 10.1016/j.neucom.2026.135337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurocomputing, 2027-01. Verfasst von Amarpal Sahota und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Research and Innovation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electroencephalography (EEG) classification has shown significant promise in applications ranging from neurodegenerative disease detection to brain-computer interfaces (BCIs). Whilst deep learning methods have increasingly dominated the research landscape in recent years; these models remain largely opaque ‘black boxes’ with limited interpretability. In this paper, we revisit the utility of feature-based classification via a systematic pipeline designed to integrate per-electrode signal statistics with cross-brain connectivity metrics. The proposed “KnowEEG” pipeline extracts 783 per-electrode statistical features alongside between-electrode connectivity statistics, utilizing a balanced sampling strategy between high-dimensional per electrode features and connectivity. This feature-based pipeline achieves performance comparable to or exceeding state-of-the-art deep learning models across five diverse classification tasks: emotion detection, mental workload classification, eyes open/closed detection, abnormal EEG classification, and event detection. This performance is achieved without the need for Graphics Processing Unit (GPU) resources. Furthermore, the pipeline provides inherent explainability through feature importance rankings. We demonstrate via the eyes open/closed task that this explainability identifies discriminative biomarkers in the occipital region that are consistent with established neuroscience literature. These results suggest that despite significant advances in deep learning, structured feature engineering remains a high performance and interpretable method for EEG classification.

Förderung

  • UK Research and Innovation

Zitieren

APA

Sahota, A., Foumani, N. M., Santos-Rodriguez, R., & Abdallah, Z. S. (2027). KnowEEG: Explainable knowledge driven EEG classification. Neurocomputing, 710, 135337. https://doi.org/10.1016/j.neucom.2026.135337

Vancouver

Sahota A, Foumani NM, Santos-Rodriguez R, Abdallah ZS. KnowEEG: Explainable knowledge driven EEG classification. Neurocomputing. 2027;710:135337. doi:10.1016/j.neucom.2026.135337

BibTeX
@article{Sahota2027,
  author = {Sahota, Amarpal and Foumani, Navid Mohammadi and Santos-Rodriguez, Raul and Abdallah, Zahraa S.},
  title = {KnowEEG: Explainable knowledge driven EEG classification},
  journal = {Neurocomputing},
  year = {2027},
  volume = {710},
  pages = {135337},
  doi = {10.1016/j.neucom.2026.135337}
}
Kostenlos starten →