Research
Research interests
Additive manufacturing, automation, Bayesian statistics, causal inference, interpretability, machine learning, statistical modeling, statistical shape analysis
News
- 2/7/2019: AI technology addresses parts accuracy, a major manufacturing challenge in 3D printing for $7.3 billion industry [Source 2] [Source 3]
- 11/12/2018 Won 2018 INFORMS paper competition
Publications and presentations
In this paper, we present a methodology based on generalized predictive comparisons to interpret multiple inputs and interesting functional forms of them to learn patterns that are inferred by complex models. We establish interpretable estimands, Fisher consistent estimators, and their corresponding standard errors. We demonstrate the broad scope and significance of our generalized predictive comparison methodology by illustrative simulations and case studies that utilize Bayesian additive regression trees, neural networks, and random forests.
In this paper, a methodology based on new predictive comparisons is specified to identify the relevant inputs, and interpret their conditional and two-way associations with the outcome, that are inferred by machine learning algorithms and models. Fisher consistent estimators, and the corresponding standard errors, for the new predictive estimands are established under a condition on the distributions of the inputs. Illustrative case studies for Bayesian additive regression trees, neural networks, and support vector machines are provided.
Organized and chaired a data mining invited session.
In this paper, we develop a Bayesian methodology for automated and comprehensive deviation modeling that can ultimately help to advance flexible, efficient, and high-quality manufacturing in an AM system.
In this report, we investigated the effects of CitrusiM® on body composition under a Bayesian framework of the Rubin Causal Model.
In this paper, we report on the first systematic, data-driven learning of the process-structure-property relationship in solution-grown tellurene, revealing the process factors’ effects on tellurene’s production yield, dimensions, and transistor-relevant properties, through a holistic approach integrating both the experimental explorations and data analytics.
Presented our research on predictive comparisons for input screening and interpreting complex machine learning models.
Presented our research on automated geometric shape deviation modeling for additive manufacturing systems.
Presented our research on automated geometric shape deviation modeling for additive manufacturing systems.
Presented a poster about our research on automated geometric shape deviation modeling for additive manufacturing systems.