-
Fused deep learning classified early enamel caries with high accuracy
Deep learning framework with quantum-inspired feature fusion achieves 99.33% accuracy for automated enamel caries classification in intraoral photographs with visual explainability.
-
Machine learning models classified TMJ disc displacement well on MRI
Supervised machine learning models detect morphometric patterns of temporomandibular joint disc displacement on 3T MRI, potentially supporting radiologic assessment.
-
Lower bit depth reduced speaker recognition accuracy
Quantization of neural network output tensors reduces storage for speaker recognition databases. Study evaluates bit depth reduction impacts on recognition accuracy across three architectures.
-
Fresh bone samples gave the most reliable age estimates
Study evaluates methylation-based bone age estimation across anatomical types and postmortem conditions, revealing accuracy limitations under forensic scenarios.
-
Muzzle biometrics identified harvested red deer with high accuracy
Automated animal biometrics using muzzle pattern analysis achieves 95% accuracy for red deer identification, enabling verifiable harvest documentation and improved ungulate population management.
-
Graph matching improved IVUS-OCT sequence registration
Graph matching framework for cross-modality intravascular ultrasound and optical coherence tomography sequence registration with simultaneous temporal and rotational alignment.
-
Quantitative Analysis of Polyphenols in Lonicera caerulea Based on Mid-Infrared Spectroscopy and Hybrid Variable Selection
Mid-infrared spectroscopy with hybrid variable selection for quantitative polyphenol analysis in Lonicera caerulea, achieving 92% predictive accuracy in high-dimensional small-sample modeling.
-
Android app matched manual facial index measurements
Validation study of an Android application for measuring facial index in orthodontic diagnosis, comparing digital photographic measurement to traditional manual anthropometry.
