Tag: deep learning

A contactless deep learning framework estimated window-averaged zygomaticus major sEMG envelope amplitude from facial video with a mean correlation of ...

Deep learning models trained on sparse expert annotations can segment anatomical structures in pediatric swallowing endoscopy videos from unseen patients, ...

Researchers have identified riddled basin geometry as a dynamical mechanism causing deep neural networks to produce divergent training outcomes despite ...

A systematic review of 65 studies finds AI models for PCOS ultrasound diagnosis report high accuracy but suffer from substantial ...

A comprehensive expert review concludes that manual chamber counting and microscopic examination remain the gold standards for cerebrospinal fluid cytology, ...

A compact residual network called MSERNet removes JPEG compression artifacts from ovarian and carotid ultrasound images while preserving tissue textures ...

A review of 42 studies finds speech emotion systems degrade by an average of 8.6 percent and facial systems by ...

Researchers have developed an image-driven deep learning framework that couples plant classification and segmentation with proxy indicators to quantify weed ...

A deep learning model analyzing diagnostic biopsies accurately predicts whether esophageal adenocarcinoma patients will respond to preoperative radiochemotherapy.

Researchers report that replacing Adam's squared-gradient second moment with the mean absolute deviation yields smoother training, fewer oscillations and faster ...

A systematic review of 124 studies finds that AI-based electric motor monitoring often reports high accuracy but lacks leakage-free validation ...

In response to these persistent vulnerabilities, a research team led by Dorjan Hitaj, Fabio De Gaspari, Flavio Corsetti, Giulio Pagnotta, ...

Researchers report that a transfer learning framework called TL-CDVD reached an average accuracy of 88.8 percent and an F1-score of ...

Researchers developed LiteSGNet, an ultra-lightweight automatic modulation classification network that achieves up to 66.11% accuracy on benchmark tests using 9.62K ...

Colorectal cancer prognosis has long been judged mainly by tumor stage and spread, but the immune cells living inside and ...

A single attention-gated multi-task network achieved classification and segmentation accuracy comparable to separate dedicated models on breast ultrasound images while ...

A feature attention mechanism embedded in a deep network restored apple sugar-prediction accuracy across three harvest years using only a ...

Researchers validated a disease-specific deep learning architecture that accurately automates metabolic tumor volume segmentation in Hodgkin lymphoma positron-emission tomography scans.

Researchers report that their enhanced YOLOv8n model, MFF-YOLO, improves SAR ship detection accuracy on two benchmark datasets by combining multi-scale ...

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