Motor-intent decoding from synthetic EEG data using denoising diffusion probabilistic models

Mustapha Deji Dere

doi:10.1016/j.eswa.2025.130134

Motor-intent decoding from synthetic EEG data using denoising diffusion probabilistic models

2025-10-26

0

PRE

AI

DOI：10.1016/j.eswa.2025.130134

Original

Original request for help

Save

Abstract

En 中文

• Diffusion model generated motor imagery EEG data better than VAE and GAN. • Diffusion model outperforms other positive pair augmentation for contrastive learning. • Synthetic data augmentation benefits decoder to reduce classification error. • Ensemble models with base classifiers outperforms state-of-the-art in EEG decoding.

Motor-intent decoding from synthetic EEG data using denoising diffusion probabilistic models

Abstract

Journal

Organization

Cited Papers