This article presents dielectric elastomer switch (DES) materials, based on composite thin films. Alignment of graphite flakes due to their physical confinement within the thin films lead to much stronger piezoresistive responses than bulk composites, while their durability exceeds that of conventional liquid‐based DES materials.
Lingyu Liu +3 more
wiley +1 more source
Semi-Supervised Fatty Liver Classification Using Attention-Based Graph Neural Network Models. [PDF]
Kim SY, Wang S, Sohn KA, Choe EK.
europepmc +1 more source
Formation Control of Multi‐Agent System with Local Interaction and Artificial Potential Field
This article proposes a local interaction‐based formation control method for Multi‐Agent system, integrating consensus and leader‐follower strategies with a stress response mechanism—artificial potential field to reduce communication overhead and enable obstacle avoidance. Experimental results on triangular, square, and hexagonal formations confirm its
Luoyin Zhao +3 more
wiley +1 more source
Heterogeneous graph neural network-based prediction of immune-related adverse events. [PDF]
He X +7 more
europepmc +1 more source
Auto‐Routing Fluidic Printed Circuit Boards
This work introduces (STREAM) software tool for routing efficiently advanced macrofluidics, an open‐source software tool for automating the design of 3D‐printable fluidic circuit boards. STREAM streamlines tube routing and layout, enabling the rapid fabrication of fluidic networks for soft robotics, lab‐on‐a‐chip devices, microfluidics, and biohybrid ...
Savita V. Kendre +3 more
wiley +1 more source
MPHGNN: metapath-guided heterogeneous graph neural network for miRNA-drug resistance association prediction. [PDF]
Huang G, Peng Y, Wu S, Wei H, Liu S.
europepmc +1 more source
When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks
Chen, Zihan, Yu, Lanyu
openalex +1 more source
Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat +4 more
wiley +1 more source
Graph neural network-driven text classification for fire-door defect inspection in pre-completion construction. [PDF]
Wang S.
europepmc +1 more source

