Interpretable AI Model Predicts 28-Day Mortality in Sepsis-Linked Kidney Injury
An interpretable XGBoost model achieved an AUC of 0.881 for predicting 28-day mortality in critically ill patients with sepsis-associated acute ...
Tag: Machine Learning
AI Reads Student Records to Predict English Proficiency in Vocational Colleges
A new interpretable AI framework combining large language model embeddings with structured educational data predicted vocational college students' English proficiency ...
BERT-EmoShiftNet Fusion Enhances Stress Dialogue Recognition
A new BERT-EmoShiftNet fusion framework achieves 85.0% accuracy in recognizing psychological stress by integrating semantic, speech, and visual data in ...
Machine learning models flag higher cancer risk from routine health data
Machine learning models using routine health data showed potential to identify people at higher risk of several common cancers, with ...
Machine learning model turns decades of literature data into a fast route to highly selective organocatalysis
A Tsinghua University team built OrgAIcat, a machine learning framework trained on more than 22,000 literature data points that predicts ...
New Benchmark Tests Whether AI Materials Models Get Physics Right
A Columbia-led team has introduced a physics-aware benchmark showing that machine learning models can predict thermal conductivity accurately while misrepresenting ...
Research report: Wearable sensor-guided hierarchical reinforcement learning for adaptive motor skill correction and injury-risk assessment in physical education
A new open-access study reports that a Fossa Optimizer-tuned Option-Critic hierarchical reinforcement learning model, trained on 7,000 wearable sensor records, ...
Physics-aware AI framework aims to make hydrogen storage materials discovery more reliable
An international team of 69 researchers has proposed a physics-aware AI framework, published in ACS Energy Letters, designed to make ...
Video-Based AI Model Spots Transformer Faults with 96% Accuracy
A new video-based diagnostic model combining the Grey Wolf Optimizer and a neural network identifies faults in oil-immersed transformers online ...
AI Learns to Read the Fine Print of Bacterial and Fungal Leaf Disease
A systematic review of 59 studies finds deep learning dominates fungal leaf disease detection while bacterial diagnosis, generative AI and ...
Explainable AI models track EV battery health over 6G networks
A new study combines LSTM-based deep learning with LIME and SHAP explainability to estimate EV battery state of health across ...
Graph Neural Networks and IoT Data Score Teaching Quality with 98% Accuracy
A new open-access study reports that an attention graph neural network tuned by adaptive optimization reached 98 percent accuracy in ...
IoT Sensors and Hybrid Machine Learning Model Predict Solar Panel Faults Before They Strike
Researchers combined a low-cost IoT monitoring prototype with a Bayesian-optimized XGBoost model that achieved the highest accuracy and fastest computation ...
Graph Neural Network Model Predicts City Traffic Flow and Congestion With High Accuracy
A new open access study reports a spatio-temporal graph convolutional network that predicted traffic flow with 97.99% precision and congestion ...
Mapping Vegetation in Fine Detail Across the Americas
Two large-scale mapping projects used the International Vegetation Classification to produce detailed vegetation and land cover maps for the USA ...
AI Reads a Single EEG Channel to Stage Sleep, With Confidence Checks Built In
A new spectral-temporal deep learning framework reached 0.8469 accuracy on a fixed Sleep-EDF test partition while flagging low-confidence epochs for ...
Weather Data Alone Struggles to Predict Building Heating Demand, Norwegian Machine Learning Study Finds
A study of two Norwegian buildings found that machine learning models predicted electricity consumption far more accurately than heating demand ...
AI shows promise for early diagnosis of mosquito-borne viral infections, review finds
A systematic review and meta-analysis of 43 studies reports pooled diagnostic performance of artificial intelligence models for dengue, chikungunya, and ...
Machine Learning Forecasts Weight Loss and App Engagement in Real-World Digital Obesity Care
Machine learning models using data from a 12-week digital obesity app predicted weight loss best when four-week weight was added, ...
AI imaging models predict stroke bleeding after thrombectomy, review finds
A systematic review of eleven studies reports that AI-driven imaging models predicted post-thrombectomy bleeding with a pooled AUC of 0.891, ...
