Data scarcity is a critical bottleneck for machine learning in applied chemistry. We show that physics‐informed descriptors enable a simple linear model to predict the deblocking temperatures of capped diisocyanates to within 11 °C from just 19 measurements, demonstrating that embedding physical insight into descriptors, rather than relying on ...
Remsha Rafiq +9 more
wiley +1 more source
MA-Pose and DMMS-GCN: skeleton-based martial-arts category recognition with edge-device deployment. [PDF]
Wang L, Zhang R, Xu H, Guo S.
europepmc +1 more source
A 3D Multitask Graph Neural Network Framework for Ames Mutagenicity Prediction
Our proposed multitask graph neural network model has a high predictive accuracy for Ames mutagenicity. By operating directly on molecular graph representations instead of traditional molecular descriptors, and predicting strain‐specific results, the model outperforms most existing benchmarks.
Abigail E. Teitgen +3 more
wiley +1 more source
A Hybrid Convolutional, Mamba and Spiking Neural Network Architecture Search for Seizure Prediction. [PDF]
Yu B +5 more
europepmc +1 more source
This article reviews the current state of bioinspired soft robotics. The article discusses soft actuators, soft sensors, materials selection, and control methods used in bioinspired soft robotics. It also highlights the challenges and future prospects of this field.
Abhirup Sarker +2 more
wiley +1 more source
Unsupervised deep learning framework for early detection of wellbore trajectory deviation in drilling operations. [PDF]
Singh P +7 more
europepmc +1 more source
Collaborative Visual Localization for Modular Self‐Reconfigurable Robots
Relative localization in modular self‐reconfigurable robots is challenged by hardware limitations, constrained fields of view, and sensor faults. This paper, based on the SnailBot platform, presents a vision‐based collaborative localization method that combines ArUco markers with learning‐based algorithms to enable robust pose estimation from ...
Guanqi Liang +4 more
wiley +1 more source
Short-term metro passenger flow forecasting via decoupled spatio-temporal modeling with a diffusion-convergence graph and Swin-Enhanced LSTM. [PDF]
Feng Y +7 more
europepmc +1 more source
Accelerating Materials Discovery: A Review of Machine Learning in X‐Ray Absorption Spectroscopy
This review systematically details how machine learning transforms X‐ray absorption spectroscopy (XAS) analysis. It covers advanced deep learning architectures for structure‐spectra mapping and inverse tasks, while discussing key challenges like the simulation‐to‐reality gap.
Melaku Lake Tegegne +5 more
wiley +1 more source
On-chip non-volatile all-optical residual neural network accelerator. [PDF]
Quan Z +6 more
europepmc +1 more source

