AI Tool Designs DNA Sequences to Fold Genomes in Desired 3D Patterns
A new computational framework, Akita Semifreddo, combines a fast genome folding model with sequence optimization to design DNA with specified ...
Tag: deep learning
Latent diffusion balances diabetic retinopathy data and boosts screening models
A class-conditional latent diffusion model generated high-resolution synthetic retinal images that balanced diabetic retinopathy classes and improved validation accuracy across ...
Dynamic Convolution Meets Continuous-Time Networks in New Intrusion Detection Model
Researchers report that a hybrid model combining dynamic convolution, a Kolmogorov-Arnold network and a closed-form continuous-time neural network outperformed classical ...
Checkpoint ensembles from ordinary training runs rival specialized noisy-label detectors
Researchers show that ensembles of checkpoints from a standard training run can detect mislabeled training data as accurately as specialized ...
Plasma Protein Signatures Predict Rheumatoid Arthritis Years Before Symptoms Appear
A UK Biobank study of 47,537 people identified 213 plasma proteins linked to rheumatoid arthritis onset and built a deep ...
Deep learning maps fog, haze and sea fog across eastern China and tests pollution cuts
A deep learning framework combining satellite, meteorological and PM2.5 data classifies and quantifies fog, fog-haze, haze and sea fog over ...
AI Screening of Routine Chest X-Rays for Osteoporosis Is Cost-Effective Only If Patients Follow Through
A cost-utility analysis finds that deep learning-based opportunistic osteoporosis screening using routine chest radiographs is cost-effective for Taiwanese postmenopausal women ...
Self-supervised AI rebuilds missing fetal heart rate signals from Tanzanian labor recordings
A self-supervised transformer model trained on more than 4,400 fetal heart rate recordings from Tanzanian hospitals can reconstruct missing signal ...
Smartphone AI app guides strawberry nitrogen fertigation from leaf photos alone
Researchers in Meghalaya, India, field-tested an Android app that predicts strawberry plant nitrogen status from smartphone leaf photos and converts ...
Deep Learning Model Reaches 98.39% Accuracy in Cotton Leaf Disease Classification
A hybrid ConvNeXt and Random Walk Grey Wolf Optimizer framework classified six categories of cotton leaf conditions with 98.39% accuracy ...
Lightweight AI model spots tiny grape leaf diseases on mobile devices
Researchers report a lightweight YOLOv10n-based detector that cuts model size and computation by roughly a third while maintaining near-baseline accuracy ...
NIH-funded project develops unified AI platform for brain imaging analysis
A Lehigh-led team received a four-year, $2.8 million NIH grant to develop UniBrain, a unified AI platform for streamlining brain-imaging ...
AI Reads Orchid Stem Powder to Tell Lookalike Species Apart
A new deep learning framework detects species-specific microscopic structures in orchid stem powder with 93.35 percent mean average precision across ...
Multimodal AI Reads Leaves Three Ways to Catch Hidden Citrus Greening Infection
A multimodal deep learning framework combining RGB photographs, hyperspectral reflectance, and SPAD chlorophyll readings detected molecularly confirmed symptomless citrus huanglongbing ...
CT biomarkers assess immunotherapy response and surgical planning in lung cancer
A 2026 mini review finds that CT is established for anatomical assessment and surgical planning after neoadjuvant immunotherapy in resectable ...
AI Spots Which Pig Is Coughing in Crowded Pens, Even at Night
A multimodal audiovisual deep learning system identified coughing pigs in group-housed pens with an average mAP of 0.96 and worked ...
Hybrid domain adaptation method defends deep learning models against multi-targeted adversarial examples
Researchers report a hybrid adversarial domain adaptation method combining logit correlation and gradient randomization that improved accuracy by 2 to ...
Self-Teaching AI Untangles Critically Endangered Gibbon Calls From Rainforest Noise
Researchers developed MC-RemixIT, a self-supervised AI framework that separates Hainan gibbon calls from complex rainforest noise without clean reference recordings ...
AI Reads Nematode Body Shapes to Identify Devastating Crop Parasites
A hybrid deep learning framework that fuses handcrafted morphological measurements with convolutional image features identified two destructive root-knot nematode species ...
AI Moves Into Vascular Surgery, But Most Models Still Await Real-World Proof
A new review of thirty studies finds artificial intelligence showing strong potential across minimally invasive vascular surgery, from risk prediction ...
POPULAR NEWS
-
Case Report Explores Caplacizumab in Late-Diagnosed Congenital Thrombotic Thrombocytopenic Purpura
-
Multitask Cambrian Model Improves Protein Melting Temperature Prediction
-
Vasopressors Exert Divergent Immunomodulatory Effects Across a Spectrum in Septic Shock
-
Study Identifies Key Drivers Shaping Salmonid Gill Microbiomes in Aquaculture