In the area of multi-scale modeling of manufacturing processes: (a) Models for understanding the mechanisms of forming and joining of lightweight materials. This new understanding enables the development of advanced processes which remove limitations of current state-of-the-art capabilities that exhibit limited formability of high strength lightweight alloys, and limited reproducibility of joining quality; (b) Innovative multi-scale finite element models for ultrasonic welding of battery tabs (resulting in models adopted by GM for designing and manufacturing batteries for the Chevy Volt), and multi-scale models for ultrasonic welding of short carbon fiber composites (resulting in models adopted by GM for designing and manufacturing assemblies made of carbon fiber composites with metallic parts); (c) Data-driven algorithms of prediction geometrical and microstructural integrity of the incremental formed parts. Machine learning is used for developing fast and robust methods to be integrated into the designing process and replace finite element simulations.
Alex Gorodetsky’s research is at the intersection of applied mathematics, data science, and computational science, and is focused on enabling autonomous decision making under uncertainty. He is especially interested in controlling, designing, and analyzing autonomous systems that must act in complex environments where observational data and expensive computational simulations must work together to ensure objectives are achieved. Toward this goal, he pursues research in wide-ranging areas including uncertainty quantification, statistical inference, machine learning, control, and numerical analysis. His methodology is to increase scalability of probabilistic modeling and analysis techniques such as Bayesian inference and uncertainty quantification. His current strategies to achieving scalability revolve around leveraging computational optimal transport, developing tensor network learning algorithms, and creating new multi-fidelity information fusion approaches.
Sample workflow for enabling autonomous decision making under uncertainty for a drone operating in a complex environment. We develop algorithms to compress simulation data by exploiting problem structure. We then embed the compressed representations onto onboard computational resources. Finally, we develop approaches to enable the drone to adapt, learn, and refine knowledge by interacting with, and collecting data from, the environment.
Our work is interdisciplinary in nature and we connect three fields, chemistry, physics and materials science. Our goal is to develop theoretical tools that give access to directly experimentally relevant quantities. We develop and apply codes that describe two types of electronic motion (i) weakly correlated electrons originating from the delocalized “wave-like” s- and p-orbitals responsible for many electron correlation effects in molecules and solids that do not contain transition metal atoms (ii) strongly correlated electrons residing in the d- and f-orbitals that remain localized and behave “particle-like” responsible for many very interesting effects in the molecules containing d- and f-electrons (transition metal nano-particles used in catalysis, nano-devices with Kondo resonances and molecules of biological significance – active centers of metalloproteins). The mutual coupling of these two types of electronic motion is challenging to describe and currently only a few theories can properly account for both types of electronic correlation effects simultaneously.
Available research projects in the group involve (1) working on a new theory that is able to treat weakly and strongly correlated electrons in molecules with multiple transition metal centers with applications to molecular magnets and active centers of enzymes (2) developing a theory for weakly correlated electrons that is able to produce reliable values of band gaps in semiconductors and heterostructures used in solar cells industry (3) applying the QM/QM embedding theories developed in our group to catalysis on transition metal-oxide surfaces and (4) applying the embedding formalism to molecular conductance problems in order to include correlation effects.
Current research includes a project funded by Toyota that uses Markov Models and Machine Learning to predict heart arrhythmia, an NSF-funded project to detect Acute Respiratory Distress Syndrome (ARDS) from x-ray images and projects using tensor analysis on health care data (funded by the Department of Defense and National Science Foundation).
Dr. Lee’s research in data science concerns biological questions in systems biology and network medicine by developing algorithms and models through a combination of statistical/machine learning, information theory, and network theory applied to multi-dimensional large-scale data. His projects have covered genomics, transcriptomics, proteomics, and metabolomics from yeast to mouse to human for integrative analysis of regulatory networks on multiple molecular levels, which also incorporates large-scale public databases such as GO for functional annotation, PDB for molecular structures, and PubChem and LINCS for drugs or small compounds. He previously carried out proteomics and metabolomics along with a computational derivation of dynamic protein complexes for IL-3 activation and cell cycle in murine pro-B cells (Lee et al., Cell Reports 2017), for which he developed integrative analytical tools using diverse approaches from machine learning and network theory. His ongoing interests in methodology include machine/deep learning and topological Kolmogorov-Sinai entropy-based network theory, which are applied to (1) multi-level dynamic regulatory networks in immune response, cell cycle, and cancer metabolism and (2) mass spectrometry-based omics data analysis.
Professor Gull works in the general area of computational condensed matter physics with a focus on the study of correlated electronic systems in and out of equilibrium. He is an expert on Monte Carlo methods for quantum systems and one of the developers of the diagrammatic ‘continuous-time’ quantum Monte Carlo methods. His recent work includes the study of the Hubbard model using large cluster dynamical mean field methods, the development of vertex function methods for optical (Raman and optical conductivity) probes, and the development of bold line diagrammatic algorithms for quantum impurities out of equilibrium. Professor Gull is involved in the development of open source computer programs for strongly correlated systems.
Dr. Veerapaneni’s research group develops fast and scalable algorithms for solving differential and integral equations on complex moving geometries. Application areas of current interest include large-scale simulations of blood flow through arbitrary confined geometries, electrohydrodynamics of soft particles and heat flow on time-varying domains.
Jieping Ye, PhD, is Associate Professor of Computational Medicine and Bioinformatics in the Medical School at the University of Michigan, Ann Arbor.
The Ye Lab has been conducting fundamental research in machine learning and data mining, developing computational methods for biomedical data analysis, and building informatics software. We have developed novel machine learning algorithms for feature extraction from high-dimensional data, sparse learning, multi-task learning, transfer learning, active learning, multi-label classification, and matrix completion. We have developed the SLEP (Sparse Learning with Efficient Projections) package, which includes implementations of large-scale sparse learning models, and the MALSAR (Multi-tAsk Learning via StructurAl Regularization) package, which includes implementations of state-of-the-art multi-task learning models. SLEP achieves state-of-the-art performance for many sparse learning models, and it has become one of the most popular sparse learning software packages. With close collaboration with researchers at the biomedical field, we have successfully applied these methods for analyzing biomedical data, including clinical image data and genotype data.
Dr. Song interested in the development and application of theories and methodologies from Data Science to solve scientific problems arising from medical and public health sciences, in particular from the fields of environmental health sciences and nutritional sciences. People from his lab are strongly interested in interdisciplinary research in the areas of statistics, operation research, and machine learning, with the core interest in the statistical foundation of big data analytics, and with target applications in processing and analyzing big data from various applied sciences, including asthma, environmental health sciences, nephrology, and nutritional sciences. His research projects have been funded by NIH, NSF and DARPA funding agencies. Visit Song Lab webpage for detail: http://www.umich.edu/~songlab/
Judy Jin, PhD, is Professor of Industrial and Operations Engineering in the College of Engineering at the University of Michigan, Ann Arbor.
Prof. Jin’s research focuses on the development of new data fusion methodologies for improving system operation and quality with the emphasis on fusion of data and engineering knowledge collected from disparate sources by integrating multidisciplinary methods. Her research has been widely applied in both manufacturing and service industry by providing techniques for knowledge discovery and risk-informed decision making. Key research issues are being pursued:
- Advanced quality control methodologies for system monitoring, diagnosis and control with temporally and spatially dense operational/sensing data.
- Multi-scale data transform and high order tensor data analysis for modeling, analysis, classification, and making inferences of multistream sensing signals.
- Optimal sensor distribution and hierarchical variable selection methods for system abnormal detection and sensor fusion decisions, which integrates the causal probability network model, statistical change detection, set-covering algorithm, and hierarchical lasso regression.
- A unified approach for variation reduction in multistage manufacturing processes (MMPs) using a state space model, which blend the control theory with advanced statistics for MMPs sensing, monitoring, diagnosis and control, integrative design of process tolerance and maintenance policy considering the interaction between product quality and tool reliability.
Data science applications: (a) Smart manufacturing with sensor fusion, process monitoring, diagnosis and control (e.g., metal forming including stamping, forging, casting and rolling), assembly, ultrasonic welding, photovoltaic thin film deposition. (b) Travel time estimation and traffic prediction for intelligent transportation systems. (c) Multi-stream data analysis of human motion/vehicle crash testing data for improving vehicle design and safety. (d) Risk informed decision support for healthcare and clinical decisions. (e) Customer behavior modeling for fraud detection in healthcare and telecommunication. (f) Human decision-making behavior modeling in a dynamic/emergency environment.