Results 251 to 260 of about 1,587,623 (364)
CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance. [PDF]
Zhang Z +5 more
europepmc +1 more source
ABSTRACT Fractal geometry describes complex, self‐similar patterns that repeat across spatial scales and is increasingly recognized as relevant in anatomical research. Indeed, the fractal organization is consistently observed in respiratory, cardiovascular, gastrointestinal, nervous, renal, hepatic, and dermatological systems.
Immacolata Belviso +7 more
wiley +1 more source
Power quality disturbance identification using hybrid deep learning in renewable energy systems. [PDF]
Peruman PM, Ayyar K.
europepmc +1 more source
ABSTRACT Fluctuating chronic conditions (FCC) in young adults aged 18–30 years, such as type 1 diabetes (T1D), sickle cell disease (SCD), and inflammatory bowel disease (IBD), present unique self‐management challenges due to unpredictable symptom patterns that disrupt daily life.
Reham Almabadi +3 more
wiley +1 more source
HAARN: A Deep Neural Network-Based Intelligent Control Method for High-Altitude Adaptability of Heavy-Load UAV Power Systems. [PDF]
Zhou H +6 more
europepmc +1 more source
Uncertainty Calibration in Molecular Machine Learning: Comparing Evidential and Ensemble Approaches
ABSTRACT Machine learning (ML) models are increasingly used in quantum chemistry, but their reliability hinges on uncertainty quantification (UQ). In this study, we compare two prominent UQ paradigms—deep evidential regression (DER) and deep ensembles—on the QM9 and WS22 datasets, with a specific emphasis on the role of post hoc calibration.
Bidhan Chandra Garain +3 more
wiley +1 more source
A Study on Tool Breakage Detection Technology Based on Current Sensing and Non-Contact Signal Analysis. [PDF]
Lai CH, Huang SH, Wu TE, Lai CC.
europepmc +1 more source
Partial identification with categorical data and nonignorable missing outcomes
Abstract Nonignorable missing outcomes are common in real‐world datasets and often require strong parametric assumptions to achieve identification. These assumptions can be implausible or untestable, and so we may wish to forgo them in favour of partially identified models that narrow the set of a priori possible values to an identification region.
Daniel Daly‐Grafstein, Paul Gustafson
wiley +1 more source
Prediction of PEMFC life based on IGJO-TCN-BiGRU-Attention. [PDF]
Zhao J +5 more
europepmc +1 more source

