Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting

Mehran Shabanpour, Sadaf Khademi, Konstantinos N Plataniotis, Arash Mohammadi

Abstract

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.

DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting

Abstract

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.
Paper Structure (4 sections, 7 equations, 3 figures, 1 table)

This paper contains 4 sections, 7 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. The $\text{DECODE}$ Framework
  3. Experimental Results
  4. Conclusion

Figures (3)

  • Figure 1: Architecture of the proposed dual-conditioned diffusion model for event-specific EEG forecasting. The DECODE framework integrates semantic guidance from natural language event descriptions (top path) with history-based temporal conditioning (bottom path) through a hierarchical diffusion process. Text descriptions are encoded via frozen BERT-large and projected to a shared embedding space, while historical EEG signals undergo forward diffusion before processing through encoder-decoder transformers with interpretable decomposition.
  • Figure 2: Representative EEG forecasting results for electrodes P7 and Pz, with historical signal (blue) providing temporal context up to timestep 1000 and the model generating probabilistic forecasts (orange) compared to ground truth (purple). The topographic map shows grand-average voltage distribution (0-500 ms post-stimulus) with red indicating positive and blue indicating negative potentials.
  • Figure 3: Mean Absolute Error (MAE) over time across the 75-timestep prediction horizon.