Machine learning identifies leukemia drug candidates and vulnerable target
A machine-learning pipeline identified AML-selective small molecules and implicated glutathione reductase as a vulnerability that can be exploited in laboratory ...
Tag: Machine Learning
Causal AI improves cross-domain dance scoring in 125-dancer study
A causal and invariant-learning system reduced cross-domain dance quality-scoring error by 38.7% in a machine-learning study involving 125 dancers and ...
Chicago taxi-demand model reports higher spatial equity with modest accuracy cost
A Chicago study combining missing-data reconstruction, LSTM forecasting and RHP-based regularization reported up to 50% better spatial equity with an ...
Tumor vessel patterns linked to survival in colorectal cancer
A prospective cohort study of 837 colorectal cancer patients linked distinct tumor blood-vessel features with colorectal cancer-specific mortality.
Hybrid LLM and SHAP framework explains cyberbullying predictions
A study of 5,000 Turkish tweets found that SHAP offered detailed feature attributions while local LLM explanations were clearer, with ...
CMS search tightens limits on quantum black holes at LHC
A CMS analysis found no quantum black holes or sphalerons in 2016–2018 LHC data while setting model-dependent limits and introducing ...
New spin-out IMS Solutions to commercialize groundbreaking ‘steroid fingerprint’ technology
A new university spin-out is developing steroid-signature tests for adrenal cancer and metabolic ovarian syndrome, with regulatory certification and clinical ...
Machine learning predicts next-year fitness assessment failure in university students
A longitudinal study at one Chinese university found that annual fitness measurements helped predict subsequent-year assessment failure, although performance varied ...
Machine learning trims AI proficiency survey without independent validation
A leakage-aware machine-learning pipeline used 17 of 30 questionnaire items to reproduce AI proficiency categories for 600 Moroccan university students ...
Fireworks-Optimized Clustering and SVM Tested for Enterprise Budget Control
A two-module computational system combined Fireworks-optimized K-means clustering with AHP-weighted SVM classification, achieving 93.67% held-out accuracy in a single-company departmental ...
Physics-informed AI reduces operational CO₂ in façade design study
A computational study found climate-dependent double-skin façade designs that reduced operational CO₂ emissions by 13–23% in Tashkent and 8–20% in ...
Higher Platelet-to-White Blood Cell Ratio Linked to Survival in HFpEF
In a retrospective study of critically ill adults with HFpEF, a higher early platelet-to-white blood cell ratio was independently associated ...
Zambian HIV records expose data gaps that can distort AI
A six-facility assessment of 246,053 Zambian HIV records found pervasive gaps, implausible values and denominator-dependent outcomes that could allow AI ...
Vertical-Axis Wind Turbines Need Power, Noise and Load Designed Together, Review Finds
A critical review finds that dynamic stall, vortex shedding and blade-wake interaction simultaneously govern the power, cyclic loading and noise ...
Machine Learning Pushes Flexible Pressure Sensors Toward Intelligent Perception
A review in the Journal of Materials Science maps how microstructured flexible pressure sensors made from materials such as PDMS ...
Clinically guided machine learning stratifies dental implant risk in European dataset
TBLPSO achieved reported accuracy of 96.1% on a European dental implant dataset by combining clinical subgrouping, expert-informed optimization and selective ...
How You Picture the Wind Changes What AI Predicts in Offshore Wind Farms
A study of the Lillgrund offshore wind farm shows that the best way to represent rotor-plane wind fields for machine-learning ...
Four-Layer AI Shield Brings Near-Real-Time Phishing Defense to Android Phones
A new multilayered machine learning framework combines URL, message, app and network analysis with adaptive user training to detect Android ...
Vision Transformer Reads Persian Miniatures With 93.85% Accuracy in Style Classification Test
A lightweight Vision Transformer fine-tuned with AdamW and cosine scheduling classified Persian miniature paintings by school with 93.85% mean accuracy, ...
Hopf-inspired generative adversarial network augments univariate time series with bifurcation dynamics
A new generative adversarial framework embeds Hopf bifurcation dynamics and Lyapunov-based regularization into its generator, reporting improved distributional similarity, temporal ...
POPULAR NEWS
-
Macrolide Derivative Combined With SPR741 Targets Drug-Resistant Enterobacterales in Silkworm Model
-
Histone Gene Dysregulation Identified as Biomarker Candidate in Premature Ovarian Insufficiency
-
SmartPE boosts prime editing efficiency in dicot crops
-
Review Examines In Situ Electrochemical Techniques for Active Hydrogen in Nitrate Reduction