DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shabanpour, Mehran, Khademi, Sadaf, Plataniotis, Konstantinos N, Mohammadi, Arash
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917350412910592
author Shabanpour, Mehran
Khademi, Sadaf
Plataniotis, Konstantinos N
Mohammadi, Arash
author_facet Shabanpour, Mehran
Khademi, Sadaf
Plataniotis, Konstantinos N
Mohammadi, Arash
contents Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural dynamics and the semantic context of behavioral tasks. We present the Dual-Enhanced COnditioned Diffusion (DECODE) for EEG, a novel framework that unifies semantic guidance from natural language descriptions with temporal dynamics from historical signals to generate event-specific neural responses. DECODE leverages pre-trained language models to condition the diffusion process on rich textual descriptions of cognitive events, while maintaining temporal coherence through history-based Langevin dynamics. Evaluated on a real-world driving task dataset with five distinct behaviors, DECODE achieves sub-microvolt prediction accuracy (MAE = 0.626 microvolt) over 75 timestep horizons while maintaining well-calibrated uncertainty estimates. Our framework demonstrates that natural language can effectively bridge high-level cognitive descriptions and low-level neural dynamics, opening new possibilities for zero-shot generalization to novel behaviors and interpretable BCIs. By generating physiologically plausible, event-specific EEG trajectories conditioned on semantic descriptions, DECODE establishes a new paradigm for understanding and predicting context-dependent neural activity.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16885
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
Shabanpour, Mehran
Khademi, Sadaf
Plataniotis, Konstantinos N
Mohammadi, Arash
Signal Processing
Computation and Language
Human-Computer Interaction
Machine Learning
Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural dynamics and the semantic context of behavioral tasks. We present the Dual-Enhanced COnditioned Diffusion (DECODE) for EEG, a novel framework that unifies semantic guidance from natural language descriptions with temporal dynamics from historical signals to generate event-specific neural responses. DECODE leverages pre-trained language models to condition the diffusion process on rich textual descriptions of cognitive events, while maintaining temporal coherence through history-based Langevin dynamics. Evaluated on a real-world driving task dataset with five distinct behaviors, DECODE achieves sub-microvolt prediction accuracy (MAE = 0.626 microvolt) over 75 timestep horizons while maintaining well-calibrated uncertainty estimates. Our framework demonstrates that natural language can effectively bridge high-level cognitive descriptions and low-level neural dynamics, opening new possibilities for zero-shot generalization to novel behaviors and interpretable BCIs. By generating physiologically plausible, event-specific EEG trajectories conditioned on semantic descriptions, DECODE establishes a new paradigm for understanding and predicting context-dependent neural activity.
title DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
topic Signal Processing
Computation and Language
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2603.16885