RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification

TL;DR

RatioWaveNet introduces a trainable wavelet front end to enhance the robustness and interpretability of EEG motor-imagery classification, especially for challenging subjects, by combining multi-resolution analysis with advanced neural architectures.

Contribution

It proposes a novel, learnable wavelet transform front end integrated with a Transformer backbone, improving BCI robustness and interpretability for EEG motor-imagery tasks.

Findings

Improves worst-subject accuracy on BCI datasets.

Maintains computational efficiency with modest overhead.

Enhances robustness across subjects and seeds.

Abstract

Brain-computer interfaces (BCIs) based on motor imagery (MI) translate covert movement intentions into actionable commands, yet reliable decoding from non-invasive EEG remains challenging due to nonstationarity, low SNR, and subject variability. We present RatioWaveNet, which augments a strong temporal CNN-Transformer backbone (TCFormer) with a trainable, Rationally-Dilated Wavelet Transform (RDWT) front end. The RDWT performs an undecimated, multi-resolution subband decomposition that preserves temporal length and shift-invariance, enhancing sensorimotor rhythms while mitigating jitter and mild artifacts; subbands are fused via lightweight grouped 1-D convolutions and passed to a multi-kernel CNN for local temporal-spatial feature extraction, a grouped-query attention encoder for long-range context, and a compact TCN head for causal temporal integration. Our goal is to test whether this principled wavelet front end improves robustness precisely where BCIs typically fail - on the hardest subjects - and whether such gains persist on average across seeds under both intra- and inter-subject protocols. On BCI-IV-2a and BCI-IV-2b, across five seeds, RatioWaveNet improves worst-subject accuracy over the Transformer backbone by +0.17 / +0.42 percentage points (Sub-Dependent / LOSO) on 2a and by +1.07 / +2.54 percentage points on 2b, with consistent average-case gains and modest computational overhead. These results indicate that a simple, trainable wavelet front end is an effective plug-in to strengthen Transformer-based BCIs, improving worst-case reliability without sacrificing efficiency.