Researchers have developed an Automated Data Processing (ADP) framework to optimize machine learning model and feature selection for predicting warpage in fused deposition modeling (FDM). The framework uses a reinforcement learning-inspired approach, evaluating model-feature combinations across numerous datasets and updating selections based on predictive accuracy and F1-scores. By integrating Shapley-based Explainable AI (SHAP XAI) for feature importance, the ADP framework successfully identified optimal configurations, improving the test-set AUC from 0.9248 to 0.9731 and increasing the mean reward by over 50% compared to using all features. AI
IMPACT This research demonstrates a method to improve predictive accuracy in manufacturing processes by optimizing ML model and feature selection, potentially leading to more efficient quality control.
RANK_REASON Academic paper detailing a novel methodology for machine learning model and feature selection. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
