Scientific Research Publishing

KAN-Transformer Fusion with Mixture of Experts for Temporal Imputation of Spatiotemporal Air Pollution Data ()

The Kolmogorov-Arnold Network (abbr. KAN) is a novel neural network architecture inspired by the Kolmogorov-Arnold ...
The American Journal of Managed Care

Predicting Severe Diabetes Complications Using Administrative Claims Data in Maryland

Predictive risk scores created using administrative claims and publicly available social determinants of health data strongly ...
IEEE

Approximate Nonlinear Model Predictive Control With Safety-Augmented Neural Networks

Abstract: Model predictive control (MPC) achieves stability and constraint satisfaction for general nonlinear systems but requires computationally expensive online optimization. This brief studies ...
jhuapl

Johns Hopkins APL-Led Team Releases Predictive Space Weather Model to Public

A predictive space weather model designed to simulate how solar storms affect Earth has been publicly released for researchers in the broader scientific community — as well as the general public — to ...
EurekAlert!

Model-based control of a continuum manipulator with online Jacobian error compensation using Kalman filtering

(A) 3D model of the manipulator structure, consisting of 3 continuum segments. The manipulator operates in the plane. (B) Close-up view of the revolute joint between adjacent disks. (C) Diagram ...
IEEE

Practical Nonlinear Model Predictive Control With Kolmogorov–Arnold Network Models

Abstract: This paper presents a novel approach to practical nonlinear model predictive control (PNMPC) using Kolmogorov–Arnold networks (KANs) as prediction models. KANs are based on the ...
C&EN

Molecular-Level Control of Exciton and Nonlinear Optical Properties in 1D Hybrid Antimony Halides via Cation Steric Design

The Beijing Municipal Key Laboratory of New Energy Materials and Technologies, School of Materials Sciences and Engineering, University of Science and Technology Beijing, Beijing 100083, China ...