Robust Analysis for Resilient AI System
This work addresses data contamination issues for industrial AI systems, establishing robust regression as a tool for resilience, but it is incremental as it builds on existing robust methods.
The paper tackles the problem of severe data outliers in Manufacturing Industrial Internet systems by proposing DPD-Lasso, a robust regression method that integrates Density Power Divergence with Lasso regularization, resulting in reliable and stable performance on both clean and outlier-contaminated data in an Aerosol Jet Printing testbed.
Operational hazards in Manufacturing Industrial Internet (MII) systems generate severe data outliers that cripple traditional statistical analysis. This paper proposes a novel robust regression method, DPD-Lasso, which integrates Density Power Divergence with Lasso regularization to analyze contaminated data from AI resilience experiments. We develop an efficient iterative algorithm to overcome previous computational bottlenecks. Applied to an MII testbed for Aerosol Jet Printing, DPD-Lasso provides reliable, stable performance on both clean and outlier-contaminated data, accurately quantifying hazard impacts. This work establishes robust regression as an essential tool for developing and validating resilient industrial AI systems.