From left: Kris De Brabanter, Steve Vardeman, Lizhi Wang, Sarah Ryan, Sigurdur Olafsson, K. Jo Min (above), Guiping Hu (below), Qing Li, and Danial Davarnia
Operations Research and Analytics is the application of advanced analytical methods to make better data-driven decisions with less risk. Faculty in this area use mathematical and computer models that incorporate simulation, optimization, probability and statistics to understand complex systems and improve system performance.
The following are examples of initiatives in this area:
Nonparametric Statistics & Applications
• Nonparametric regression when errors are correlated
• Model selection methods for regression and density estimation
• Asymptotic analysis
Research Projects
• Combining Fluid Dynamics, Statistics and Pattern Recognition in Bloodstain Pattern Analysis, to Quantify Spatial Uncertainty and Remove Human Bias
• Correlated data analysis
• Long term memory processes
Deterministic and Stochastic Models
• Production decision making under uncertainty
• Renewable energy system design and analysis Data Analytics and Optimization
• Data-driven shop floor scheduling and planning
• Resource planning and management for agriculture and plant breeding
Research Projects
• Engineering Crops for Genetic Adaptation to Changing Environments, supported by NSF
• FactBoard: Real-Time Data Driven Visual Decision Support System for the Factory Floor, supported by DMDII
• Data Driven Highway Infrastructure Resilience Assessment, supported by MTC
• Development and Evaluation of Improved Strategies for Genomic Selection, supported by USDA
Statistical Machine Learning and data analytics
• Bayesian Hierarchical Modeling
• Clustering and classification
• Medical data analytics
• Quality assurance
• Data analytics in additive manufacturing (AM)
Research projects
• Similarity evaluation between surface topography data in AM
• Quality assurance and anomaly detection in AM
• Anomaly detection in the swine disease
• Readmission prediction
• Recurrent-event change-point detection and testing
K. Jo Min
John B. Slater Fellow in Sustainable Design & Manufacturing
Associate Professor
Stochastic Optimal Control
• Engineering valuation of projects under uncertainty
• Optimal timing/Impulse control
• Real options Sustainability Modeling
• Renewable energy generation and transmission planning
• Closed-loop supply chains
• Valuation of remanufacturing and supply contracts
Research Projects
• Valuation of Blockchain “ilities” such as traceability and irrefutability
• Engineering valuation of complex projects under uncertainties
• Complex project teaching & learning materials/visualization aids
Optimization
• Heuristic methods for discrete optimization Data Analytics
• Predictive plant phenomics
• Data-driven production scheduling
• Data mining of incident reporting databases
• Sports analytics Optimization/Data analytics
• Optimization-based methods for input engineering in data mining
Research Projects
• Decision support for plant breeding
• Expert system to improve data collection from law enforcement
• Predicting the hardness of new materials
Optimization Under Uncertainty
• Data analytics for formulating and verifying stochastic process models
• Risk considerations in capital investment and operational planning
Research Projects
• DataFEWSion Traineeship for Innovations at the Nexus of Food Production, Renewable Energy and Water Quality
• Analysis of Power System Operational Uncertainty from Gas System Dependence
• Closed Loop Supply Chain Design for Uncertain Carbon Regulations and Random Product Flows
Steve Vardeman
University Professor
Liberal Arts and Sciences Kingland Data Analytics Faculty Fellow
Statistical Machine Learning
• Predictive Analytics
• Basic Theory for “Big Data” Methods Engineering Statistics
• Statistics and Metrology
• Process Monitoring
• Reliability and Warranty Data Analysis Statistical Methods for Physical Sciences
• Directional and Orientational Data Analysis
Research Projects
• Precision Agriculture
• EBSD and Crystal Orientations
• Service Life Prediction from Warranty Data
• Spectral-Temporal Event Modeling
Methodology
Stochastic, robust, bilevel, discrete optimization Applications
TEAM (Transportation, Energy, Agriculture,
and Manufacturing) systems
Recent Projects
• (Transportation) Assessing and enhancing
transportation network resiliency
• (Energy) Strengthening electric power networks through transmission planning
• (Agriculture) Advanced analytics of genomic data for improving plant and animal breeding
• (Manufacturing) Real-time data driven visual decision support system for the factory floor