Advances in Neuroimaging and Brain-Computer Interfaces

The field of neuroimaging and brain-computer interfaces is rapidly advancing with innovative methods and techniques being developed to improve the analysis and interpretation of neurological data. Recent developments have focused on improving the accuracy and efficiency of electroencephalography (EEG) and functional MRI (fMRI) data analysis, as well as enhancing the performance of brain-computer interfaces. Notably, new architectures and frameworks have been proposed to address the challenges of EEG and fMRI data analysis, including the use of graph neural networks, variational autoencoders, and transformer-based models. These advancements have the potential to improve our understanding of neurological disorders and develop more effective treatments.

Some noteworthy papers in this area include: The paper on Semi-disentangled spatiotemporal implicit neural representations of longitudinal neuroimaging data for trajectory classification, which presents a novel method for representing aging trajectories across the entire brain. The paper on Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification, which proposes a unified architecture for EEG classification that achieves state-of-the-art performance across multiple paradigms. The paper on Variational Mixture of Graph Neural Experts for Alzheimer's Disease Biomarker Recognition in EEG Brain Networks, which introduces a novel framework for EEG-based biomarker recognition that achieves superior performance and provides interpretable insights.

Sources

Assessment of different loss functions for fitting equivalent circuit models to electrochemical impedance spectroscopy data

Semi-disentangled spatiotemporal implicit neural representations of longitudinal neuroimaging data for trajectory classification

Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification

Optimal monophasic, asymmetric electric field pulses for selective transcranial magnetic stimulation (TMS) with minimised power and coil heating

Multi-Task Learning with Feature-Similarity Laplacian Graphs for Predicting Alzheimer's Disease Progression

FusionGen: Feature Fusion-Based Few-Shot EEG Data Generation

Interpretable Machine Learning for Cognitive Aging: Handling Missing Data and Uncovering Social Determinant

Variational Mixture of Graph Neural Experts for Alzheimer's Disease Biomarker Recognition in EEG Brain Networks

TFGA-Net: Temporal-Frequency Graph Attention Network for Brain-Controlled Speaker Extraction

NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models

EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis

Scaling Vision Transformers for Functional MRI with Flat Maps

Built with on top of