Results 161 to 170 of about 10,821 (279)
A Novel Approach to Energy Management in Electric Steelworks
Feed‐forward neural networks are exploited to estimate electric energy consumptions of the electric arc furnace and ladle furnace processes. The models are used to optimize production schedule so that more energy intensive grades are produced when the cost of energy is lower.
Valentina Colla +12 more
wiley +1 more source
Turbidity‐based digital LAMP offers a low‐cost alternative for nucleic acid quantification, but interpreting bright‐field images is difficult due to weak contrast and noise. We developed NanoFuse‐YOLO11, an AI‐based detection model that automatically identifies positive reaction units in turbidity microscopy images.
Zhu Chen +7 more
wiley +1 more source
Abstract Graph neural networks (GNNs) have revolutionised the processing of information by facilitating the transmission of messages between graph nodes. Graph neural networks operate on graph‐structured data, which makes them suitable for a wide variety of computer vision problems, such as link prediction, node classification, and graph classification.
Amit Sharma +4 more
wiley +1 more source
Fine‐scale spatial variation in eastern grey squirrel melanism across a complex urban landscape
By sampling 197 parks, the study demonstrates how natural geography creates divergence within cities. The findings reveal that the St. Lawrence River and its tributaries act as barriers, disrupting urban melanism clines in grey squirrels. Ultimately, the research indicates that natural features still dictate evolutionary rules in anthropogenic ...
Francis Quang‐Hai Dinh +3 more
wiley +1 more source
Subjective Social Inequalities, Lay Perceptions of Merit and Puzzles of Explanation
ABSTRACT Despite rising socioeconomic inequalities most people see individualised merit as crucial for social success. Drawing on surveys such as the ISSP a wealth of research examines trends in subjective perceptions, the relative importance accorded to merit and non‐merit factors for getting ahead in life and factors which influence lay perceptions ...
Sarah Irwin
wiley +1 more source
Research on the atomic clock signal denoising method based on the hyperbolic tangent smooth threshold function. [PDF]
Liu Q, Ning X, Hu D, Wang L, Wang Z.
europepmc +1 more source
Optimal deep learning activity recognition pipeline using animal bio‐logging data
Abstract Animal activity recognition using supervised machine learning on bio‐logging data has revolutionized behavioural studies on wildlife and livestock over the past decade. These studies' analytic pipelines differ substantially though, being based on various sensors, features, algorithms and hyperparameter values, which has caused suboptimal or ...
Jasper A. J. Eikelboom
wiley +1 more source
A novel hyperbolic tangent-augmented controller framework for temperature control in jacketed continuous stirred tank reactors. [PDF]
Izci D +7 more
europepmc +1 more source
Abstract Purpose To investigate the diagnostic performance of ultrasound, 2‐deoxy‐2‐[18F]fluoro‐D‐glucose positron emission tomography/computed tomography (2‐[18F]FDG PET/CT) and temporal artery biopsy (TAB) in giant cell arteritis (GCA). Methods This was a prospective single‐centre diagnostic accuracy study (ClinicalTrials.gov NCT05248906).
Michael S. Hansen +10 more
wiley +1 more source
Real-time implementation of a new MPPT technique based on Shifted Hyperbolic Tangent Function under various weather conditions. [PDF]
Mahho M, Yılmaz M, Çorapsız MF.
europepmc +1 more source

