Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet

TL;DR

This study compares a transparent fuzzy-reasoning EEG classification method with a deep learning benchmark, highlighting trade-offs between interpretability and generalization in motor imagery BCI systems.

Contribution

It provides a comparative analysis of ANFIS-FBCSP-PSO and EEGNet on EEG classification, offering practical guidance for system selection based on interpretability or robustness.

Findings

Fuzzy-neural model outperforms in within-subject accuracy

Deep model shows better cross-subject generalization

Study guides BCI system choice based on design goals

Abstract

Achieving both accurate and interpretable classification of motor-imagery EEG remains a key challenge in brain-computer interface (BCI) research. In this paper, we compare a transparent fuzzy-reasoning approach (ANFIS-FBCSP-PSO) with a well-known deep-learning benchmark (EEGNet) using the publicly available BCI Competition IV-2a dataset. The ANFIS pipeline combines filter-bank common spatial pattern feature extraction with fuzzy IF-THEN rules optimized via particle-swarm optimization, while EEGNet learns hierarchical spatial-temporal representations directly from raw EEG data. In within-subject experiments, the fuzzy-neural model performed better (68.58% +/- 13.76% accuracy, kappa = 58.04% +/- 18.43), while in cross-subject (LOSO) tests, the deep model exhibited stronger generalization (68.20% +/- 12.13% accuracy, kappa = 57.33% +/- 16.22). The study therefore provides practical guidance for selecting MI-BCI systems according to the design goal: interpretability or robustness across users. Future investigations into transformer-based and hybrid neuro-symbolic frameworks are expected to further advance transparent EEG decoding.