Three-Branch AI Fusion Reaches 99.3% Accuracy in White Blood Cell Classification
A hybrid deep learning model fusing MobileNetV3, DenseNet121, and DINOv2 achieved up to 99.3% accuracy in classifying five types of ...
A hybrid deep learning model fusing MobileNetV3, DenseNet121, and DINOv2 achieved up to 99.3% accuracy in classifying five types of ...
Researchers report an IoT-and-deep-learning framework that captured nearly 3,000 music recordings and achieved 94% accuracy in recognising traditional music patterns ...
A new review of 75 studies proposes a unified data-driven framework linking polymer 3D printing defects, multi-sensor monitoring, and machine ...
A retrospective study of 512 ICU patients reports a multimodal deep-learning framework that segments CT lesions in ventilator-associated pneumonia and ...
A newly proposed Cross-Channel Temporal Correlation Transformer outperformed twelve mainstream forecasting models on 24-hour temperature prediction tasks across six Chinese ...
Food safety monitoring has a data problem that has little to do with how much data exists.
A new personalized federated learning framework uses Transformer-based dynamic aggregation and adaptive regularization to improve colorectal cancer CT image classification ...
A Chinese research team reports a new asymmetric U-Net with hybrid attention and residual dilated convolution that achieved Dice scores ...
A self-supervised CNN framework with Grad-CAM heatmaps reached up to 94.38% validation accuracy on a 2,137-image cotton leaf disease dataset.
Researchers in Egypt report that replacing reconstruction-based pre-training with hierarchical supervised contrastive learning and a per-access-point attention gate improves Wi-Fi ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine