Results 101 to 110 of about 62,130 (264)

Graph attention, learning 2-opt algorithm for the traveling salesman problem

Complex & Intelligent Systems
In recent years, deep graph neural networks (GNNs) have been used as solvers or helper functions for the traveling salesman problem (TSP), but they are usually used as encoders to generate static node representations for downstream tasks and are ...
Jia Luo, Herui Heng, Geng Wu
doaj   +1 more source

A Novel Graph Reinforcement Learning-Based Approach for Dynamic Reconfiguration of Active Distribution Networks with Integrated Renewable Energy

Energies
The dynamic reconfiguration of active distribution networks (ADNDR) essentially belongs to a complex high-dimensional mixed-integer nonlinear stochastic optimization problem.
Hua Zhan, Changxu Jiang, Zhen Lin
doaj   +1 more source

Transient Cytoskeletal Anisotropy Encodes Short‐Term Mechanical Memory in Glioblastoma Cells

Advanced Materials, EarlyView.
The same mechanical deformation can produce distinct cytoskeletal states depending on loading history. Experiments and constitutive modeling reveal that transient actin–vimentin anisotropy stores mechanical information and governs short‐term mechanical memory in glioblastoma cells.
Clara Gomez‐Cruz, Matthieu Gelin, Lucas Pradeau‐Phélut, Arrate Muñoz‐Barrutia, Sandrine Etienne‐Manneville, Daniel Garcia‐Gonzalez   +5 more
wiley   +1 more source

A Method for UAV Path Planning Based on G-MAPONet Reinforcement Learning

Drones
To address the issues of efficiency and robustness in UAV trajectory planning under complex environments, this paper proposes a Graph Multi-Head Attention Policy Optimization Network (G-MAPONet) algorithm that integrates Graph Attention (GAT), Multi-Head
Jian Deng, Honghai Zhang, Yuetan Zhang, Mingzhuang Hua, Yaru Sun   +4 more
doaj   +1 more source

Spatial Control of Light‐Responsive Proteins and Optogenetics Within Hydrogels via Volumetric Bioprinting

Advanced Materials, EarlyView.
Spatiotemporal control over cell behavior within bioprinted constructs remains a key challenge in biofabrication. Volumetric bioprinting using multi‐wavelength light sources permits to activate light‐sensitive intracellular proteins as well as optogenetic gene and protein expression circuits in bioprinted cells, in addition to enabling fast printing of
Davide Ribezzi, Pere Català, Gabriel Größbacher, Paulina Nuñez Bernal, Olaf Nijssen, Sammy Florczak, Wilco Nijenhuis, Nuria Crusellas‐Villorbina, Bram Nijhoff, Paul Delrot, Jos Malda, Andreas Hierholzer, Martin Fussenegger, Lukas C. Kapitein, Riccardo Levato   +14 more
wiley   +1 more source

Progress on the Failure Mechanisms and Optimization Strategies on Lithium Iron Phosphate

Advanced Materials Interfaces, EarlyView.
This review centers on LiFeO4 cathodes, outlining their core advantages and performance limitations, then systematically elucidating failure mechanisms, proposing key optimization strategies, and summarizing future research directions that integrate advanced characterization with intelligent design.
Zheng‐Xin Qian, Tianxiang Li, Zhijiang Liu, Mingzhe Yuan, Xiaoyu Gu, Banglong Wan, Qian Zhao, Zuotong Zha, Hang Ma   +8 more
wiley   +1 more source

Dynamic Graph Algorithms and Graph Sparsification: New Techniques and Connections

CoRR, 2019
Doctoral thesis; abstract shortened to respect the arXiv ...
openaire   +2 more sources

In Situ Change in Contact Angle of a Sessile Droplet on a Magnetoactive Elastomer

Advanced Materials Interfaces, EarlyView.
Contact angles of persistent μL$\mu{\rm L}$‐sized water droplets on a mechanically soft MAE surface under time varying magnetic fields differ from those of newly deposited droplets. The ability to quickly alter the material properties allows one to observe intriguing droplet‐material interactions.
Raphael Kriegl, Alexander Kovalev, Stanislav Gorb, Mikhail Shamonin   +3 more
wiley   +1 more source

Method for coal mine safety risk management based on knowledge graph

Gong-kuang zidonghua
Addressing the challenges of multi-source data fusion and poor real-time early warning capabilities in traditional coal mine safety risk monitoring methods, which result in unsatisfactory performance in real-time risk warning and dynamic response, this ...
DUAN Ruiwei
doaj   +1 more source

Generating Dynamic Graph Algorithms for Multiple Backends for a Graph DSL

CoRR
With the rapid growth of unstructured and semistructured data, parallelizing graph algorithms has become essential for efficiency. However, due to the inherent irregularity in computation, memory access patterns, and communication, graph algorithms are notoriously difficult to parallelize.
Nibedita Behera, Ashwina Kumar, Atharva Chougule, Mohammed Shan P. S, Rushabh Nirdosh Lalwani, Rupesh Nasre   +5 more
openaire   +2 more sources