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
Optimizing XGBoost via mSMA_plus: A Novel Meta-Heuristic Approach for High-Precision Multiclass Dry Bean Classification. [PDF]
Subaşi N.
europepmc +1 more source
Sustainable Synaptic Device with Two‐Dimensional Ferroelectric Materials for Neuromorphic Computing
α‐In2Se3 based FeSFETs can be utilized as sustainable devices through polarization switching governed by both out‐of‐plane and in‐plane polarizations. Upon reaching a fatigued state, current annealing enabled by conductance modulation can significantly enhance the endurance of FeSFETs.
Jaewook Yoo +12 more
wiley +1 more source
PEtab-GUI: a graphical user interface to create, edit, and inspect PEtab parameter estimation problems. [PDF]
Jost PJ +3 more
europepmc +1 more source
Synaptic κ‐Ga2O3 Photodetectors for Privacy‐Enhancing Neuromorphic Computing
We report on a single‐element neuromorphic sensor based on the persistent photoconductivity (PPC) of κ‐phase Ga2O3 capable of sensing ultraviolet light and harnessing intrinsic data privacy. The approach establishes a materials‐enabled pathway toward compact, intelligent, and privacy‐enhancing optoelectronic hardware for next‐generation edge systems ...
Yanqing Jia +13 more
wiley +1 more source
EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning. [PDF]
Anand B, Grama A.
europepmc +1 more source
A physics‐based framework resolving graphite phase‐separation dynamics establishes a predictive, degradation‐aware fast‐charging methodology for commercial Li‐ion batteries. The resulting model‐informed protocol achieves 20%–80% state‐of‐charge in 14 min while matching the long‐term degradation of a commercial 25‐minute EV strategy.
Marco Lagnoni +10 more
wiley +1 more source
Developing a Gudermannian neural network for solving the Painlevé model-II in the context of nonlinear optics. [PDF]
Faisal S +4 more
europepmc +1 more source
WS2‐based in‐memory sensing reservoir computing integrates sensing, memory, and computation in one compact device. It achieves ∼94% N‐MNIST, ∼93% eye motion perception, and ∼89% speech recognition with ultra‐low energy (∼25.5 fJ/spike). The system shows stability at 95% humidity, endurance over 1.5M cycles, and supports synaptic plasticity, enabling ...
Dayanand Kumar +9 more
wiley +1 more source
The Epi training kit pilot: an inclusive Spanish-language e-learning approach to epidemiology and data science in Latin America and the Caribbean. [PDF]
Gómez-Bermeo L +4 more
europepmc +1 more source

