Results 111 to 120 of about 204,888 (292)
Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan +8 more
wiley +1 more source
ABSTRACT The demand for off‐the‐shelf biocompatible bone substitutes has driven the development of numerous independent in vitro technologies to generate products resembling physiological tissues. Due to technical challenges and overly simplified cultivation approaches/niches, the end‐products are often uniformly shaped and inferior to native bone ...
Franziska Braun +10 more
wiley +1 more source
By overcoming the fixed‐path limitations of conventional machine learning, a heterogeneous graph neural network fundamentally reconstructs material data representation. Integrating variable processing sequences with intrinsic elemental features, this framework enables exploratory optimization across high‐dimensional spaces.
Jie Yin +12 more
wiley +1 more source
This study presents an anatomical landmark‐guided DRL framework for autonomous wireless capsule endoscopy navigation. Using a lightweight edge‐contour‐depth fusion module, it achieves over 97% coverage across diverse gastric anatomies. To ensure reliability, a two‐stage sim‐to‐real pipeline with an adaptive dynamic programming controller mitigates ...
Haoxuan Wu +16 more
wiley +1 more source
This work provides a practical guide for neuroengineers to design advanced neural interfaces, embracing and tailoring the concept of functional disorder. By bridging 2D and 3D in vitro models, this work highlights how non‐periodic, spatially heterogeneous, multiscale nanotopography can enable more physiologically relevant platforms for studying neural ...
F. Maita +4 more
wiley +1 more source
A Data‐Driven Inverse Design Methodology for Magnetic Soft Millirobots Navigating in Confined Spaces
A data‐efficient inverse design framework automates the optimization of magnetic soft millirobots for confined‐space navigation. Integrating a physics‐based Cosserat rod model with Bayesian optimization efficiently identifies high‐performance geometries.
Ziyu Ren +5 more
wiley +1 more source
We present the MyoRobot 3.0, an advanced platform that combines high‐resolution imaging with automated mechanical testing to improve the accuracy of single muscle fibre analysis. The system tracks fibre diameter changes during stretch, preventing major stress miscalculations.
Michael Haug +5 more
wiley +1 more source
State-Driven Adaptive Deep-Unfolded PGA Algorithm for Hybrid Beamforming in MIMO-JCAS Systems. [PDF]
Liu F, Wang Z, Gao Y, Yao Z.
europepmc +1 more source
This work reports a thermally safe, photothermally reprogrammable magnetic soft robot with its reprogramming temperature tuned to ∼39.5°C for biocompatibility. It achieves multimodal locomotion (max speed of 1.8 BL/s) and integrates liquid‐metal capacitive sensing to monitor self‐motion and detect environmental changes in simulated gastric environments,
Liu Yang +5 more
wiley +1 more source
DRL-Based Beam Split Alleviation for Movable Antenna-Enabled Near-Field Wideband Communications. [PDF]
Zhang T, Jiang R, Dai H, Zhou C, Xu Y.
europepmc +1 more source

