SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG

R Kobler, J Hirayama, Q Zhao… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Electroencephalography (EEG) provides access to neuronal dynamics non-invasively with
millisecond resolution, rendering it a viable method in neuroscience and healthcare …

Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space

P Rajpura, H Cecotti, YK Meena - Journal of Neural Engineering, 2024‏ - iopscience.iop.org
Objective. This review paper provides an integrated perspective of Explainable Artificial
Intelligence (XAI) techniques applied to Brain-Computer Interfaces (BCIs). BCIs use …

Tensor-cspnet: A novel geometric deep learning framework for motor imagery classification

C Ju, C Guan - IEEE Transactions on Neural Networks and …, 2022‏ - ieeexplore.ieee.org
Deep learning (DL) has been widely investigated in a vast majority of applications in
electroencephalography (EEG)-based brain–computer interfaces (BCIs), especially for …

Feel your reach: An EEG-based framework to continuously detect goal-directed movements and error processing to gate kinesthetic feedback informed artificial arm …

GR Müller-Putz, RJ Kobler, J Pereira… - Frontiers in Human …, 2022‏ - frontiersin.org
Establishing the basic knowledge, methodology, and technology for a framework for the
continuous decoding of hand/arm movement intention was the aim of the ERC-funded …

SPDIM: Source-Free Unsupervised Conditional and Label Shifts Adaptation in EEG

S Li, M Kawanabe, RJ Kobler - arxiv preprint arxiv:2411.07249, 2024‏ - arxiv.org
The non-stationary nature of electroencephalography (EEG) introduces distribution shifts
across domains (eg, days and subjects), posing a significant challenge to EEG-based …

Controlling the Fréchet variance improves batch normalization on the symmetric positive definite manifold

RJ Kobler, J Hirayama… - ICASSP 2022-2022 IEEE …, 2022‏ - ieeexplore.ieee.org
Symmetric positive definite (SPD) matrices, and in particular co-variance matrices as data
descriptors find widespread application in various fields but also pure machine learning …

Effects of cognitive distraction on upper limb movement decoding from EEG signals

W Fei, L Bi, J Wang, S **a, X Fan… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Objective: Hand movement decoding from electroencephalograms (EEG) signals is vital to
the rehabilitation and assistance of upper limb-impaired patients. Few existing studies on …

Review of training-free event-related potential classification approaches in the world robot contest 2021

H Wu, D Wu - Brain Science Advances, 2022‏ - journals.sagepub.com
Recently, rapid serial visual presentation (RSVP), as a new event-related potential (ERP)
paradigm, has become one of the most popular forms in electroencephalogram signal …

Rcoco: contrastive collective link prediction across multiplex network in riemannian space

L Sun, M Li, Y Yang, X Li, L Liu, P Zhang… - International Journal of …, 2024‏ - Springer
Link prediction typically studies the probability of future interconnection among nodes with
the observation in a single social network. More often than not, real scenario is presented as …

Bayesian scalar-on-network regression with applications to brain functional connectivity

X Ju, HG Park, T Tarpey - arxiv preprint arxiv:2401.16749, 2024‏ - arxiv.org
This paper presents a Bayesian regression model relating scalar outcomes to brain
functional connectivity represented as symmetric positive definite (SPD) matrices. Unlike …