IEEE

Anomnet: a Hybrid Framework for Multivariate Time Series Anomaly Detection Using Attention-Augmented State Space Models

Abstract: Anomaly detection in multivariate time series plays a crucial role in diverse applications, from monitoring system performance to detecting financial fraud. Conventional deep learning ...
IEEE

A Dynamic Gated Fusion Diffusion Model (DGFDiff) for Multivariate Time Series Imputation in Aluminum Electrolysis Process

Abstract: Data missing significantly impairs the performance of data-driven models in the aluminum electrolysis industry. The process parameters in aluminum electrolysis are characterized by complex ...
BMJ

Trends in burden of atrial fibrillation over three decades: a population-based study

Background Atrial fibrillation (AF) is a common sustained cardiac arrhythmia with increasing prevalence and incidence worldwide. However, long-term trends in AF prevalence, incidence, associated risk ...
The Lancet

Long COVID associated with SARS-CoV-2 reinfection among children and adolescents in the omicron era (RECOVER-EHR): a retrospective cohort study

aCenter for Health AI and Synthesis of Evidence, University of Pennsylvania, Philadelphia, PA, USA bGraduate Group in Applied Mathematics and Computational Science, School of Arts and Sciences, ...
The Lancet

Weight trajectories and access to weight management services in individuals with severe mental illness in the UK: a population-based, matched cohort study

eDepartment of Biochemistry and Molecular Biology II, Faculty of Pharmacy, Centre for Biomedical Research, Institute of Nutrition and Food Technology, Biosanitary Research Institute Granada, ...