🧠 Join us for the Brain Models for Multimodal Integration Symposium!
📅 12 September 2025 | ⏰ 12:00–13:15 UTC | 🌐 Virtual Event

Thrilled to co-chair w/ @pierpasorre.bsky.social at the @ohbmofficial.bsky.social Satellite Meeting! Feat. D. Depannemaecker & @gianmarcoduma.bsky.social ma.bsky.social.

These parameter shifts are robust across EEG and MEG, and localize to sensorimotor regions—crucial hubs for motor imagery in BCI.

We introduce mi-NMM: a linear neural mass model that nails power spectral density shapes—both at rest and during motor imagery tasks.
It tracks intra-regional connectivity strength and E/I population dynamics, revealing how training reshapes neural activity.

These parameter shifts are robust across EEG and MEG, and localize to sensorimotor regions—crucial hubs for motor imagery in BCI.

We introduce a linear neural mass modeling approach, mi-NMM, that accurately captures power spectral density shapes in resting state & while performing a motor imagery task. It tracks intra-regional connectivity strength and E/I population dynamics, revealing how training reshapes neural activity.

Key findings:
✅ Neuronal avalanches are robust biomarkers of individual BCI learning.
✅ Features like avalanche duration and spatiotemporal size correlate with BCI performance across sessions.
✅ Longitudinal models using these features achieve up to 91% accuracy in predicting BCI success.

Why it matters?
Up to 30% of users struggle with motor imagery-based BCI, a challenge known as "BCI inefficiency." Current protocols use fixed-length sessions, ignoring individual variability. Our study introduces a novel approach that rely on neuronal avalanches to tackle this issue.

José del R. Millán from the University of Texas presented his latest findings on transfer learning based on Riemannian geometry and transcutaneous electrical spinal stimulation to foster BCI learning.

Reinhold Scherer from the University of Essex provided an overview of co-adaptation methods to address feature variability

Sonja Kleih-Dahms and @settgast.bsky.social from Würzburg University, discussed the use of brain criticality to predict BCI performance in Amyotrophic Lateral Sclerosis

Arthur Desbois from @nerv-lab.bsky.social gave a showcase of HappyFeat, a software designed to guide experimenters during the feature selection process

@fdevicofallani.bsky.social from @nerv-lab.bsky.social presented examples of the use of brain networks as features for BCI rehabilitation in stroke patients.

@pierpasorre.bsky.social from INS, Marseille & Sassari University, demonstrated the interest in using neuronal avalanches to inform BCI.

Maryam Alimardani from Vrije Universiteit Amsterdam presented her findings on the use of functional connectivity in BCI

Two days ago, together with Serafeim Perdikis and @tristanvenot.bsky.social, we had the pleasure of proposing a workshop entitled "Exploring Features to Improve BCI: Challenges and Opportunities." Unable to attend this event? Here is a brief recap 🧵 @bcisociety.bsky.social

Wondering whether aperiodic signals could inform about mechanisms underlying BCI training? Stop by Camilla Mannino's poster today at @bcisociety.bsky.social meeting! ⚡ @nerv-lab.bsky.social @institutducerveau.bsky.social

Key highlights:
✅ Kinectome outperforms PCA in classification accuracy
✅ Resilient to data loss & robust across derived measures
✅ Clear feature interpretability
✅ Potential applications in sports training, physical rehabilitation, and more!

Our research explores how network theory-based coordination properties (the "kinectome") can improve classification performance in movement analysis, offering a more interpretable, generalizable, and adaptable approach compared to traditional methods like PCA.