Advances in Signal Processing and Machine Learning for Biomedical Applications

The field of biomedical signal processing and machine learning is rapidly evolving, with a focus on developing innovative methods for analyzing and interpreting complex biological signals. Recent developments have centered around improving the accuracy and efficiency of signal processing techniques, such as electroencephalography (EEG) and heart rate monitoring. Researchers are exploring new approaches, including adaptive segmentation methods and physics-informed generative models, to enhance the analysis of biomedical signals. These advancements have the potential to improve disease diagnosis, patient monitoring, and treatment outcomes. Noteworthy papers in this area include: Atrial Fibrillation Prediction Using a Lightweight Temporal Convolutional and Selective State Space Architecture, which proposes a novel deep learning model for early prediction of atrial fibrillation. EEGDM: Learning EEG Representation with Latent Diffusion Model, which introduces a self-supervised EEG representation learning method based on latent diffusion models.

Sources

Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning

A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context

Atrial Fibrillation Prediction Using a Lightweight Temporal Convolutional and Selective State Space Architecture

Adaptive Segmentation of EEG for Machine Learning Applications

Physics Informed Generative Models for Magnetic Field Images

EEGDM: Learning EEG Representation with Latent Diffusion Model

Built with on top of