Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding

Megan Lee, Seung Ha Hwang, Inhyeok Choi, Shreyas Darade, Mengchun Zhang, Kateryna Shapovalenko

TL;DR

ASEN is introduced, a hybrid architecture that combines spectral and temporal feature streams via multiplicative fusion, requiring cross-modal agreement for features to propagate, demonstrating that multiplicative multimodal fusion enables effective cross-subject generalization.

Abstract

Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral representations offer more stable features for cross-subject transfer than temporal waveforms. Through correlation analyses across three EEG paradigms (SSVEP, P300, and Motor Imagery), we find that spectral features exhibit consistently higher cross-subject similarity than temporal signals. Motivated by this observation, we introduce ASPEN, a hybrid architecture that combines spectral and temporal feature streams via multiplicative fusion, requiring cross-modal agreement for features to propagate. Experiments across six benchmark datasets reveal that ASPEN is able to dynamically achieve the optimal spectral-temporal balance depending on the paradigm. ASPEN achieves the best unseen-subject accuracy on three of six datasets and competitive performance on others, demonstrating that multiplicative multimodal fusion enables effective cross-subject generalization.

ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding

TL;DR

ASEN is introduced, a hybrid architecture that combines spectral and temporal feature streams via multiplicative fusion, requiring cross-modal agreement for features to propagate, demonstrating that multiplicative multimodal fusion enables effective cross-subject generalization.

Abstract

Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral representations offer more stable features for cross-subject transfer than temporal waveforms. Through correlation analyses across three EEG paradigms (SSVEP, P300, and Motor Imagery), we find that spectral features exhibit consistently higher cross-subject similarity than temporal signals. Motivated by this observation, we introduce ASPEN, a hybrid architecture that combines spectral and temporal feature streams via multiplicative fusion, requiring cross-modal agreement for features to propagate. Experiments across six benchmark datasets reveal that ASPEN is able to dynamically achieve the optimal spectral-temporal balance depending on the paradigm. ASPEN achieves the best unseen-subject accuracy on three of six datasets and competitive performance on others, demonstrating that multiplicative multimodal fusion enables effective cross-subject generalization.
Paper Structure (26 sections, 34 equations, 5 figures, 15 tables)

This paper contains 26 sections, 34 equations, 5 figures, 15 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Datasets
  5. Domain Characterization
  6. Signal Processing
  7. Model Architecture
  8. Experiments
  9. Baselines
  10. Ablations
  11. Results
  12. Analysis
  13. Mechanism of Multiplicative Spectral-Temporal Gating
  14. Visualizing Decision Boundaries
  15. Conclusion and Outlook
  16. ...and 11 more sections

Figures (5)

  • Figure 1: ASPEN architecture. Raw EEG is processed through parallel temporal and spectral streams, combined via multiplicative fusion before classification.
  • Figure 2: Cross-session (left) and cross-subject (right) correlation comparison between temporal and spectral representations. Spectral features exhibit consistently higher cross-subject similarity across all datasets.
  • Figure 3: Detailed view of temporal stream, spectral stream, and multiplicative fusion components.
  • Figure 4: Stream contributions and feature correlation ($\rho$) across datasets. Low correlation values confirm that streams capture distinct information.
  • Figure 5: Grad-CAM visualization of feature importance for P300 classification. Correct prediction (top) shows focused attention on physiologically relevant low-frequency bands. Misclassification (bottom) reveals scattered attention towards high-frequency noise artifacts.