MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations
IEEE Transactions on Biomedical Engineering · 2026-02 · 73 (2) · 945-952
DOI: 10.1109/tbme.2025.3596500 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-02. Verfasst von Ambroise Heurtebise und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Magnetoencephalography, Signal Processing, Computer-Assisted, Machine Learning. Die Arbeit nennt 37 Literaturangaben. Gefördert von: ANR BrAIN, Cambridge Centre for Ageing and Neuroscience, Biotechnology and Biological Sciences Research Council.
Abstract (Originalsprache)
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are analyzed to uncover brain activity dynamics. In magnetoencephalography (MEG), where signals are captured at the scalp level, estimating the brain's underlying sources is crucial, especially in group studies where sources are assumed to be similar for all subjects. Common methods, such as Multi-View Independent Component Analysis (MVICA), assume identical sources across subjects, but this assumption is often too restrictive due to individual variability and age-related changes. Multi-View Independent Component Analysis with Delays (MVICAD) addresses this by allowing sources to differ up to a temporal delay. However, temporal dilation effects, particularly in auditory stimuli, are common in brain dynamics, making the estimation of time delays alone insufficient. To address this, we propose Multi-View Independent Component Analysis with Delays and Dilations (MVICAD$^{2}$), which allows sources to differ across subjects in both temporal delays and dilations. We present a model with identifiable sources, derive an approximation of its likelihood in closed form, and use regularization and optimization techniques to enhance performance. Through simulations, we demonstrate that MVICAD$^{2}$ outperforms existing multi-view ICA methods. We further validate its effectiveness using the Cam-CAN dataset, and showing how delays and dilations are related to aging.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- ANR BrAIN
- Cambridge Centre for Ageing and Neuroscience
- Biotechnology and Biological Sciences Research Council
- Medical Research Council
- University of Cambridge
Zitieren
APA
Heurtebise, A., Chehab, O., Ablin, P., & Gramfort, A. (2026). MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations. IEEE Transactions on Biomedical Engineering, 73(2), 945-952. https://doi.org/10.1109/tbme.2025.3596500
Vancouver
Heurtebise A, Chehab O, Ablin P, Gramfort A. MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations. IEEE Transactions on Biomedical Engineering. 2026;73(2):945-952. doi:10.1109/tbme.2025.3596500
BibTeX
@article{Heurtebise2026,
author = {Heurtebise, Ambroise and Chehab, Omar and Ablin, Pierre and Gramfort, Alexandre},
title = {MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations},
journal = {IEEE Transactions on Biomedical Engineering},
year = {2026},
volume = {73},
number = {2},
pages = {945--952},
doi = {10.1109/tbme.2025.3596500}
}
EUVIMED