Interpretable machine learning for shoreline forecasting. [PDF]
Al Najar M, Wilson DG, Almar R.
europepmc +1 more source
Unveiling a Bulk WTaV Multicomponent Alloy With Superior Thermal Properties and Manufacturability
ABSTRACT Many tungsten (W)‐based medium and high entropy alloys (HEA) demonstrate superior microstructural stability and enhanced mechanical properties as compared to pure W, effectively rendering them as viable candidate materials for extreme environments such as nuclear fusion, aerospace applications, and so on.
Ishtiaque K. Robin +11 more
wiley +1 more source
SuperARC: a test for artificial superintelligence based on compressed modelling, recursive prediction and problem complexity. [PDF]
Hernández-Espinosa A +3 more
europepmc +1 more source
Pathway activity inference for multiclass disease classification through a mathematical programming optimisation framework. [PDF]
Yang L +3 more
europepmc +1 more source
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
Symbolically Regressing Fish Biomass Spectral Data: A Linear Genetic Programming Method With Tunable Primitives. [PDF]
Huang Z +5 more
europepmc +1 more source
Whole‐genome analysis of 1,054 chickens reveals three ancestral sources (NWC, SYA, and SHF) with distinct temporal entry patterns into the Tibetan Plateau. Route‐specific selection scans, calibrated against a demographic null, suggest complementary functional enrichments—vascular homeostasis (NWC), calcium signaling and cardiac adaptation (SYA), and ...
Zongyi Zhao +7 more
wiley +1 more source
Automated production cutting optimization for minimizing material waste of pipelines in prefabricated MEP systems based on integer programming. [PDF]
Fan X, Yang L, Zhao X.
europepmc +1 more source
Cross‐Modal Denoising and Integration of Spatial Multi‐Omics Data with CANDIES
In this paper, we introduce CANDIES, which leverages a conditional diffusion model and contrastive learning to effectively denoise and integrate spatial multi‐omics data. We conduct extensive evaluations on diverse synthetic and real datasets, CANDIES shows superior performance on various downstream tasks, including denoising, spatial domain ...
Ye Liu +5 more
wiley +1 more source

