Results 161 to 170 of about 2,050,088 (230)
A Critical Assessment of Bonding Descriptors for Predicting Materials Properties
The impact of new bonding descriptors in machine learning models for predicting material properties is assessed. Improvements are validated using significance tests, and new, intuitive descriptors for screening lattice thermal conductivity and projected force constants are introduced.
Aakash Ashok Naik +6 more
wiley +1 more source
Matrix‐assisted laser desorption/ionization imaging‐based identification of reliable small molecule markers across heterogeneous glioblastoma cohorts is challenging with intensity‐only methods. We present spatially informed feature selection (SIFS), a spatially informed framework that prioritizes molecules consistently colocalizing with histopathology.
Shad A. Mohammed +15 more
wiley +1 more source
This research demonstrates that the combination of domain knowledge–based multiple regression, multi‐objective Bayesian optimization, and generative models is a suitable prediction tool for candidates of high refractive index polymers, even with the constraints in the model trained on limited data. The experimental validation can reproduce the proposed
Takuya Yokoo +3 more
wiley +1 more source
In Situ Contact Angle Measurement for Autonomous Spin Coating in Self‐Driving Labs
A vision‐based add‐on transforms commercial spin coaters into autonomous modules of Self‐Driving Labs. Combining a width‐scaled U‐Net with classical geometric analysis, the system simultaneously measures contact angles and estimates substrate pose using a single camera.
Sven Fischer, Micha Hiegle, Holger Röhm
wiley +1 more source
Machine learning serves as a central engine for the intelligent characterization of two‐dimensional materials by integrating multimodal techniques, including optical microscopy, spectroscopy, electron microscopy, and scanning probe microscopy (SPM). This unified framework enables automated, high‐throughput, and quantitative extraction of structural ...
Zhi‐Long Cao, Jia‐Xu Yan
wiley +1 more source
Data‐Efficient Cycle‐Level Capacity Prediction Using 1D Deep Convolutional Network
We introduce DeepBat, a deep learning framework featuring a 1D convolutional backbone designed to extract latent degradation patterns from a microstructurally diverse electrode dataset. By learning complex formulation–performance relationships, the model accurately predicts long‐term specific discharge capacity using limited early‐cycle data, providing
Tao Huang +16 more
wiley +1 more source
Current Standards of Monitoring Models in Healthcare Settings
AI/ML‐enabled medical devices are entering clinical practice faster than monitoring standards mature. This review highlights gaps in postmarket surveillance, limited use of predetermined change‐control plans, and the need for ongoing performance tracking, drift detection, explainability, and workflow‐aware governance to support safer, more reliable ...
Alan Kay +5 more
wiley +1 more source
We present CatTransVAE, a catalyst‐specialized chemical language model (CLM) built on a transformer variational autoencoder (VAE), developed through pretraining on general compounds followed by fine‐tuning on diverse catalyst databases. A template‐guided generation framework is introduced to enable controlled catalyst design under structural ...
Apakorn Kengkanna, Masahito Ohue
wiley +1 more source
Crystal Structure Prediction of Inorganic Materials: A Benchmark and Modern Evaluation
Predicting a crystal’s structure from composition alone is a long‐standing challenge in materials discovery. The CSP180 benchmark of 180 inorganic crystals evaluates thirteen crystal structure prediction algorithms requiring no density functional theory (DFT) against DFT‐based baselines across twelve metrics.
Lai Wei +9 more
wiley +1 more source
Physics‐Guided Modeling of Temperature‐Dependent Electrical Conductivity of Functional Oxides
This complete workflow presents an automated, data‐driven screening of functional oxides based on their predicted electrical conductivity. A curated dataset is fed into TriCondNet, a charge‐transport, physics‐guided neural network that classifies an input composition's conduction mechanism and then simulates its conductivity–temperature profile.
Elias Assaad +6 more
wiley +1 more source

