TriPat‑XFE: a triangle pattern‑based explainable feature engineering framework for EEG classification

doi:10.1016/j.neuroscience.2025.12.004

TriPat‑XFE: a triangle pattern‑based explainable feature engineering framework for EEG classification

2025-12-05

0

PRE

AI

DOI：10.1016/j.neuroscience.2025.12.004

Original

Original request for help

Save

Abstract

En 中文

• TriPat introduces a linear triangle-based transformer for EEG features • TriPat-XFE achieves 100% accuracy on Stress and Psychosis datasets. • DLob provides symbolic EEG explanations with connectome diagrams. • CWINCA and tkNN enhance feature selection and classification stability. • TriPat-XFE outperforms SOTA with low cost and high interpretability.

TriPat‑XFE: a triangle pattern‑based explainable feature engineering framework for EEG classification

Abstract

Journal

Organization