# Motor imagery EEG classification via wavelet-packet synthetic augmentation and entropy-based channel selection

## TL;DR

This paper introduces a framework to improve motor imagery EEG classification by reducing sensor count and boosting accuracy using wavelet-based methods.

## Contribution

A unified framework combining wavelet-packet augmentation and entropy-based channel selection for MI EEG classification.

## Key findings

- The method achieves 86.81% and 86.64% mean accuracy on BCI Competition IV 2a and PhysioNet datasets.
- It reduces the number of sensors by 27% while maintaining high classification performance.
- Results show significant improvements over baseline models using all 22 channels (p < 0.01).

## Abstract

Motor-imagery (MI) brain–computer interfaces often suffer from limited EEG datasets and redundant channels, hampering both accuracy and clinical usability. We address these bottlenecks by presenting a unified framework that simultaneously boosts classification performance, reduces the number of required sensors, and eliminates the need for extra recordings.

A three-stage pipeline is proposed. (1) Wavelet-packet decomposition (WPD) partitions each MI class into low-variance “stable” and high-variance “variant” trials; sub-band swapping between matched pairs generates synthetic trials that preserve event-related desynchronization/synchronization signatures. (2) Channel selection uses wavelet-packet energy entropy (WPEE) to quantify both spectral-energy complexity and class-separability; the top-ranked leads are retained. (3) A lightweight multi-branch network extracts multi-scale temporal features through parallel dilated convolutions, refines spatial patterns via depth-wise convolutions, and feeds the fused spatiotemporal tensor to a Transformer encoder with multi-head self-attention; soft-voted fully-connected layers deliver robust class labels.

On BCI Competition IV 2a and PhysioNet MI datasets the proposed method achieves 86.81 and 86.64% mean accuracies, respectively, while removing 27% of sensors. These results outperform the same network trained on all 22 channels, and paired t-tests confirm significant improvements (p < 0.01).

Integrating WPD-based augmentation with WPEE-driven channel selection yields higher MI decoding accuracy with fewer channels and without extra recordings. The framework offers a computationally efficient, clinically viable paradigm for enhanced EEG classification in resource-constrained settings.