Tag: deep learning

A new machine learning model called DBFP combines LSTM networks, attention mechanisms, and non-linear regularization to predict which software features ...

A systematic review of 91 studies shows AI-based medication recognition advancing rapidly through detection, OCR, and few-shot learning, while external ...

A new FCN-GRU-Attention deep learning model with a confidence correction mechanism identifies overlapping composite power quality disturbances with over 99 ...

A systematic review of 52 studies finds that artificial intelligence achieves strong technical performance across segmentation, planning, reconstruction, applicator selection, ...

A systematic review of 74 studies reveals that AI-driven maintenance for mining processing machinery remains narrow, vibration-obsessed, and disconnected from ...

A hybrid deep learning framework predicts learner assessment outcomes from engagement data captured in the first quarter of online courses, ...

A comprehensive review in Molecular Systems Biology traces how deep learning, foundation models, and emerging modalities are reshaping image-based profiling, ...

Researchers have built SpudNet5-R3, a lightweight explainable convolutional neural network that detects potato early and late blight with up to ...

A hybrid Transformer-BiLSTM deep learning framework with a dual nature-inspired feature selection method reports up to 99 percent accuracy in ...

A leakage-controlled multimodal AI model combining PET/CT radiomics, deep-learning features, metabolic parameters and blood-based indices achieved moderate preoperative prediction of ...

A sweeping review of 1,081 studies from 2014 to 2024 shows convolutional neural networks rapidly becoming the world's leading tool ...

A new deep-learning network called MFANet modestly outperformed leading models at segmenting liver tumors on CT scans even when some ...

A five-center study shows deep learning models, especially nnU-Net, predict aggressive meningioma grades from MRI more reliably across hospitals than ...

Researchers have trained a deep neural network on 130,000 simulated samples to predict the reflection coefficients of an eight-port terahertz ...

Researchers have built a 10.97-million-parameter neural network that classifies brain tumors on MRI with 99.2 percent accuracy while quantifying its ...

Researchers have developed S2Fusion, a local-to-global framework that improves infrared and visible image fusion through cross-modal dynamic kernels and a ...

A scholarly exchange in Pediatric Radiology over a deep learning model for detecting neonatal pneumothorax highlights the gap between overall ...

Researchers in China built a multimodal AI framework combining clinical data, CT enterography radiomics and deep learning on double-balloon enteroscopy ...

Tanzanian researchers trained deep neural networks to classify nitrogen status in maize leaves from smartphone photos, achieving over 93 percent ...

A new adversarial deep learning system called ABox-PC digitally reconstructs the occluded surfaces of greenhouse tomatoes from single-view 3D scans, ...