Tag: deep learning

Researchers trained a deep learning model on raw noisy traffic windows to predict expert-filtered targets, cutting forecast errors against the ...

A multi-scale 3D-CNN tuned by a quantum-inspired metaheuristic optimizer classified eight basketball tactical patterns from player tracking data with 94.3% ...

Researchers report a dual-branch gated U-Net that removes motion artifacts from wearable ECG recordings while measurably preserving P and T ...

A deep learning framework that fuses construction schedules with wall-deflection monitoring data cut long-term prediction errors for diaphragm walls at ...

The framework, developed by Rabita Hasan and Sheikh Md.

A deep learning model trained on PET/CT data segmented the heart muscle on non-contrast CT scans without manual adjustment, improving ...

A systematic review of 57 studies finds that AI-enabled Pharma 4.0 tools after COVID-19 concentrated on early-stage drug discovery metrics, ...

A physics-guided deep learning model trained on five years of monitoring data from the 1,650-metre Xihoumen Bridge predicts wind-induced buffeting ...

Two studies show glioblastoma cells follow predictable paths between states, and reprogramming a single regulator improved survival in mouse models.

A lightweight deep learning system recognizes eating, standing, and lying in dairy cows and tracks each animal at 52.1 frames ...

A CT-based AI system reduced benign interventions among treated kidney lesions from 40.3 percent to 16.4 percent in a randomized ...

A meta-learning framework called RobPicker corrects annotation errors and reweights rare species, improving particle picking and 3D density map resolution ...

Deep learning measurements of right atrial volume and coronary calcification on routine non-contrast chest CT independently predicted mortality in 620 ...

Researchers have developed DynamicFusionNet, a decoder that adaptively fuses features across layers, scales and views to improve medical image segmentation ...

A wrist-worn motion sensor and a compact neural network detected prosthetic hand contact with 99.1 percent accuracy in lab tests.

Machine learning and robotic synthesis are accelerating the search for catalysts that convert methane directly into ethylene, though researchers say ...

A hierarchical two-stage deep learning pipeline screens neonatal brain MRI for myelination delay before classifying structural pathologies such as HIE ...

Researchers at Ningbo University developed PestFG-RTDETR, a transformer-based detector that improves small pest detection in dense trap-captured images with higher ...

A new open-set recognition network flags tomato leaf images from disease classes it was never trained on, outperforming standard baselines ...

A comprehensive review details how deep neural networks are automating every stage of cryo-electron microscopy, from particle picking to high-resolution ...