Synthetic EEG Generation using Diffusion Models for Motor Imagery Tasks
This addresses data scarcity for EEG-based BCIs, but it is incremental as it applies an existing method (diffusion models) to a new domain (EEG generation).
The study tackled the challenge of data scarcity in EEG-based Brain-Computer Interfaces by generating synthetic EEG signals for motor imagery tasks using Diffusion Probabilistic Models, achieving classification accuracies above 95% with low error and high correlation to real data.
Electroencephalography (EEG) is a widely used, non-invasive method for capturing brain activity, and is particularly relevant for applications in Brain-Computer Interfaces (BCI). However, collecting high-quality EEG data remains a major challenge due to sensor costs, acquisition time, and inter-subject variability. To address these limitations, this study proposes a methodology for generating synthetic EEG signals associated with motor imagery brain tasks using Diffusion Probabilistic Models (DDPM). The approach involves preprocessing real EEG data, training a diffusion model to reconstruct EEG channels from noise, and evaluating the quality of the generated signals through both signal-level and task-level metrics. For validation, we employed classifiers such as K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNN), and U-Net to compare the performance of synthetic data against real data in classification tasks. The generated data achieved classification accuracies above 95%, with low mean squared error and high correlation with real signals. Our results demonstrate that synthetic EEG signals produced by diffusion models can effectively complement datasets, improving classification performance in EEG-based BCIs and addressing data scarcity.