Results 231 to 240 of about 74,320 (358)

A Periodic Error Correction Method for Terahertz Coded‐Aperture Imaging

open access: yesAdvanced Intelligent Systems, EarlyView.
A physics‐constrained unsupervised learning framework with periodic error correction is proposed for terahertz coded‐aperture imaging. The method improves reconstruction robustness against noise and model mismatch, while reducing reliance on large‐scale labeled data.
Hongxu Wu   +8 more
wiley   +1 more source

Performance tracking in female youth soccer through wearables and subjective assessments. [PDF]

open access: yesFront Sports Act Living
Kranzinger S   +3 more
europepmc   +1 more source

Multi‐Risk‐Level Sarcopenia‐Prone Screening via Machine Learning Classification of Sit‐to‐Stand Motion Metrics from Wearable Sensors

open access: yesAdvanced Intelligent Systems, EarlyView.
A machine learning approach utilizes micro inertial measurement units (μIMUs) for noninvasive sarcopenia screening through a sit‐to‐stand test. With 53 older participants wearing IMUs, 510 features are extracted across four motion phases. Five algorithms (support vector machine, K‐nearest neighbors, decision tree, linear discriminant analysis, and ...
Keer Wang   +11 more
wiley   +1 more source

Mainstream Artificial Intelligence Technologies in Contemporary Ophthalmology

open access: yesAdvanced Intelligent Systems, EarlyView.
This review explores the latest artificial intelligence (AI) technologies in ophthalmology, focusing on four key data types: medical imaging, electronic health records, robotic‐assisted surgery, and genomics. It examines the structural features, use cases, clinical goals, and evaluation metrics of various AI algorithms, while also introducing emerging ...
Shiqi Yin   +9 more
wiley   +1 more source

A Fuzzy Risk Assessment Approach Based on Z‐Numbers for Enhancing Safety and Human‐Robot Collaboration in Automotive Sector

open access: yesAdvanced Intelligent Systems, EarlyView.
A novel risk assessment approach that integrates the fuzzy set theory and Z‐numbers with multicriteria decision‐making techniques (Delphi, decision‐making trial and evaluation laboratory, analytic network process, and VIseKriterijumska Optimizacija I Kompromisno Resenje) to manage uncertainty and prioritize human–robot collaboration risks. A real‐world
Emine Bozkus, İhsan Kaya
wiley   +1 more source

Adapting Image‐Based Models for 1D Data via Spider Plot Transformation and Transfer Learning

open access: yesAdvanced Intelligent Systems, EarlyView.
A novel method enables the use of pretrained image‐based neural networks for complex 1D data, including Raman and mid‐infrared spectra, electrocardiograms, and mass spectrometry. 2D spider plots with false‐color fill enable transfer lerning, therefore enhancing data augmentation and model explainability across diverse spectral and time series datasets.
Azadeh Mokari   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy