-
Hybrid recommendation model improved interior design package suggestions
A hybrid machine learning recommendation system for interior design services balances customization with cost constraints, achieving 83.62% accuracy in predicting user preferences.
-
Signals of Success and Struggle: Early Prediction and Physiological Signatures of Human Performance across Task Complexity
Early eye movement and heart rate signals predict user performance in complex tasks. High performers show targeted gaze, adjusted visual sampling, and stable cardiac activation.
-
Hydrological ML accuracy depends on training data quantity and quality
Analysis of how information quantity and quality in training data affect machine learning prediction accuracy for hydrological variables, using information theory and mechanistic model integration.
