Non-Contact Phenotypic Measurement and Body Mass Prediction of <i>Penaeus japonicus</i> Based on Skeletonization and Multi-View Comparison. [PDF]
Du X, Qu J, Yin B.
europepmc +1 more source
Abstract Continuous, high‐frequency monitoring is essential to capture rapid phenological transitions and dynamic crop responses to the environment. However, most phenotyping platforms lack the temporal resolution and automation required for consistent, season‐long trait assessment.
Worasit Sangjan +5 more
wiley +1 more source
Dynamics and Forecasting of Emergency Department Presentations: An Integrative Approach Based on Statistical Analysis and Time-Series Models. [PDF]
Sas LM +7 more
europepmc +1 more source
Comparative machine learning approach on Maxwell tetra hybrid nanofluid with porous and bioconvection over 3d rotating stretching sheet. [PDF]
Soniya P, De P.
europepmc +1 more source
Cooling holes provide a simple passive cooling strategy for polymer spur gears, reducing maximum operating temperature by up to 9.39% while introducing a measurable gear mesh stiffness penalty. A validated response‐surface model reveals how hole size and location govern this thermal–mechanical trade‐off, enabling design optimization for thermally and ...
Abderrahim Baccar +5 more
wiley +1 more source
Accelerating Sustainable Epoxy Resin Development Through Bayesian Optimization and Inverse Design
Development of a machine learning framework for the optimization of the Tg of partially bio‐based epoxy resin formulations in a 13‐component design space using Bayesian optimization, active learning, random design, and inverse design. The results show that the BO effectively navigates high‐dimensional formulation spaces, and the final ML model could ...
Natalie Wunder +3 more
wiley +1 more source
Frequency-Guided Dynamic Hypergraph Learning for Traffic Flow Forecasting. [PDF]
Li W, Wang B, Li G, Ma Y, Jiang B.
europepmc +1 more source
Transformer‐Based Contextual Modeling for Predicting Calories From Recipes
A transformer‐based regression model with token‐level attention pooling is proposed for predicting calorie content directly from unstructured recipe text. By fine‐tuning RoBERTa in an end‐to‐end manner, attention is learned to be focused on calorie‐relevant tokens such as ingredients, fats, and cooking methods.
Md. Siam Ansary, Amina Brinto
wiley +1 more source
Characteristics of Abdominal Movement Signals Measured by a Wireless Abdomen-Worn Sensor During Home Sleep Apnea Testing: Pilot Observational Study. [PDF]
Dang TH +5 more
europepmc +1 more source
Through a PRISMA‐guided review of 42 studies, this work compares deep learning, ensemble machine learning, and statistical/econometric models for long‐term energy demand forecasting, showing that model choice should balance accuracy, interpretability, data availability, and policy relevance.
Nor Afiza Mohd Noor +4 more
wiley +1 more source

