Tag: deep learning

A newly published study describes a unified YOLOv11–EfficientViT neural network that jointly detects traffic lights and signs and recognizes traffic ...

An enhanced RT-DETR-ResNet18 framework raises detection accuracy for camouflaged soybean pests, reaching 77.4% mAP@0.5 across 12 pest categories.

Researchers trained a reinforcement learning controller entirely on a neural-operator digital twin and deployed it on the MuVacAS vacuum prototype ...

A diffusion-based text-to-speech model trained on eight dysarthric TORGO speakers generated 6,120 synthetic UA-Speech utterances that improved speaker-independent intelligibility classification ...

A systematic review of 120 papers finds deep learning DDoS detectors excel in experiments but struggle in real-world cloud environments, ...

A new EEG study combined entropy-optimized symbolic signal analysis with a bidirectional LSTM network to distinguish children with ADHD from ...

A simulator-based hybrid quantum-classical framework reported 98.5% accuracy in predicting cross-border e-commerce marketing effectiveness, outperforming classical baselines on synthetic transaction ...

A preliminary case series found that an AI facial analysis application agreed with a single dermatologist on 83 percent of ...

A systematic review of 78 papers examines how machine learning methods support demand forecasting and inventory decision-making.

A new deep learning framework called RCNNricePPI predicts rice protein-protein interactions from amino acid sequences, achieving an accuracy of 0.8996 ...

A systematic review of 306 studies finds most machine learning crash severity models ignore class imbalance and a large share ...

UniLoopNet predicts enhancer–promoter, enhancer–enhancer, CTCF-mediated, and stripe-associated chromatin interactions from DNA sequence using a multi-task deep learning framework.

Every year, tens of millions of mammograms are performed worldwide, and many of them contain a quiet clue about a ...

A systematic review of 45 studies finds that the most accurate AI models in high-stakes domains are often the least ...

A new review maps how artificial intelligence is transforming mosquito identification, disease forecasting, and vector control worldwide.

A new promptable diffusion-enhanced framework achieved 98.1% classification accuracy and a 93.2% Dice score for explainable brain tumor segmentation and ...

A dual-path attention fusion network combining Swin Transformer and frozen DINOv2 features reached 99.24% accuracy on a leakage-screened hold-out test ...

A published study reports that a Big Bang-Big Crunch optimized Peephole LSTM model classified course records in a 10,000-record dataset ...

A new AI framework combining attention-enhanced YOLOv8 and Bald Eagle Optimization achieved 98.94% accuracy in detecting transmission and distribution faults ...

A hybrid deep learning framework for classifying cataract, diabetic retinopathy, glaucoma, and normal retinas dropped from 99.24 percent internal accuracy ...