LAKERS TOGETHER: Find out how we're moving forward.
Research at GVSU
The effects of big data are profound. Everything from tracking disease across the world, managing cities and crisis situations, employing marketing techniques to specify individual consumers, targeting business solutions, and winning elections are just a few of the ways that our society has been changed by big data.
Below is a sampling of the "Big Data" research projects currently underway at Grand Valley. The projects on this page are organized by major topic: Applied Science and Engineering; Economics and Finance; Digital Studies; Human Performance & Health; The Environment and Sustainability; and Miscellaneous.
Edward Aboufadel, Ph.D., Professor of Mathematics
- Mathematics – applied mathematics, including data-intensive projects and wavelet-based projects. A recent project involved detecting potholes using data collected from smartphone accelerometers.
Wael Mokhtar, Ph.D., Associate Professor and Director, School of Engineering
- In his research, Dr. Mokhtar uses Computational Fluid Dynamics (CFD) to study fluid flow applications. His current research includes: vehicle aerodynamics, drag reduction tools, wind tunnel testing, and bio-fluid flow simulation. More information can be found in: http://faculty.gvsu.edu/mokhtarw/index.htm
Rachel Powers, PhD, Associate Professor of Chemistry
- Research in the Powers lab involves the structure-based discovery and design of novel beta-lactamase inhibitors. The three-dimensional structures of beta-lactamase in complexes with inhibitors are determined by X-ray crystallography and rely on diffraction data sets measured at the Advanced Photon Source at Argonne National Laboratory.
Jeffrey Ward, PhD, Associate Professor of Engineering
- Improvement and use of a Plasma Fluid Finite Difference Time Domain numerical model to predict plasma interactions with in-situ electromagnetic probes and antennas for use in ionospheric sensing and communications, and industrial applications.
Joerg Picard, PhD, Assistant Professor of Finance
- Using high performance computing to analyze high frequency market data.
Laura Kapitula, Ph.D., Associate Professor of Statistics
- Professor Kapitula’s research interests include statistical computing, educational evaluation and measurement, hierarchical modeling, influence diagnostics, biostatistics and statistics education. She is currently working on developing influence diagnostics for modeling health care costs and understanding how differential variability of teacher effect estimates result in unfair outcomes for high stakes decisions. She has worked collaboratively in a diverse set of areas including: education, medicine, transportation research, human computer interaction, epidemiology and psychology.
Mario Fific, Ph.D., Assistant Professor of Psychology
- Develops computational models of how short-term memory processing distributes its resources, elucidating the relationship between short term story and attention. Other work develops computational models of how people decide to stop collecting evidence and proceed with making a decision, as when we stop reading recommendations and decide to make a purchase. Quantitative model optimization and model-fitting are used to develop and test these computational cognitive models.
Daniel Frobish, Ph.D., Associate Professor of Statistics
- Predicting Survival Probabilities based on Gene Expression Levels – The goal is to build a statistical model that can be used to predict a patient’s survival probability as a function of time, based on his/her gene expression profile. Because there are tens of thousands of genes in human beings, there are many, many more variables (gene expression levels) than the typical sample size, which presents significant challenges in developing a model. My research is focused on determining optimal methods to efficiently sort through the large number of genes to find the ones with most predictive ability.
Deborah Herrington, Ph.D., Associate Professor of Chemistry
- Evaluation of Target Inquiry (TI) Professional Development Model – collaborative research with Dr. Ellen Yezierski, Miami University, evaluating the impacts of TI on teachers and their students. This evaluation involves combining qualitative analysis of classroom observational video, teacher interviews, and program artifacts with Hierarchical Linear Modeling (HLM) of multiple student pre and post-test measures.
Sok Kean Khoo, Ph.D., Distinguished Associate Professor of Molecular Genomics
- Next-Generation Sequencing (NGS) Data Analyses – Collaborative research with Michigan State University Department of Epidemiology & Biostatistics and Pediatrics & Human Development and Wayne State University Institute of Environmental Health Sciences using NGS technology on bloodspot samples to investigate molecular etiology of cerebral palsy.
Jonathan P. Leidig, Ph.D., Associate Professor of Computing and Information Systems
- Modeling, simulation, and digital libraries - Scalable computing applications are utilized to model and simulate experiments involving the spread of diseases in humans and animals. Current scientific research is data-intensive and requires digital libraries to be developed that can preserve and provide access to large volumes of scientific content.
Kirkhof College of Nursing faculty
- Storage and statistical analysis of HIPAA data
Kin Ma, Wanxiao Sun, and Gang Wu, Ph.Ds, Professor of Geography and Sustainable Planning
- High performance computing applied to geography.
Charlyn Partridge, Ph. D., Annis Water Resources Institute
- High performance computing related to ecological research.
Paul Stephenson, Ph.D., Professor of Statistics
- Biosurveillance – Research on developing a Group Control Chart for Monitoring Michigan Geospatial Data and Simulating its Performance
- Modeling of Fire Data – Statistical Analysis regarding the potential of Independent Occurrences of Serious Residential Fires
David Zeitler, Ph.D., Associate Professor of Statistics
- Big Data Ignite (BDI). Program co-chair for the annual Big Data Ignite conference and member of the advisory board. Working with BDI researchers building understanding of the application of big data in west Michigan businesses.
- Collaborative research with WMU Computer Science and Statistics faculty developing advanced statistical techniques for robust modeling useful in machine learning applications.
- Application of high performance statistical computing, Bayesian techniques and reproducible research particularly to varied aspects of Biological and Health Sciences related work including biomedical engineering, neuroscience and physical therapy research.
Jeroen Wagendorp, Ph.D, Professor of Geography and Sustainable Planning
- R web modules for local K-12 schools to illustrate statistical concepts
John Gabrosek, Professor, Statistics
- Coding in R for data visualizations of large, multivariate data sets, following principles of effective graphics design and communication of statistical results to a non-mathematical audience. Interested in the further incorporation of software into the statistics classroom.
Dave Huizen, Program Director, Occupational Health and Safety Management
- Occupational safety instructional videos (using high performance computing)
Jerry Scripps, Ph.D., Associate Professor of Computing and Information Systems
- Computer Science: current research in the area of mining large networks. These are typically social networks or other networks that have the properties of social networks. Sizes range from a few hundred nodes to hundreds of thousands of nodes. Currently working on projects of community finding in networks and analysing massive mobile phone data sets for improving public health services.
Jeffrey Kelly Lowenstein, Ph. D., Assistant Professor of Communications
- Gaming the Lottery: An international investigation into the global lottery industry involving close to 40 people from 10 countries working in journalism and civic tech organizations in Africa, Europe and the United States.
Patrick D. Anderson, Ph.D., Visiting Assistant Professor of Philosophy
- Surveillance—using deontological moral theories to explore the ethics of data-based surveillance in the public (“national security state surveillance") and private ("surveillance capitalism”) sectors.
- Sousveillance—assessing the possibilities of a genuine “watching from below,” as opposed to "watching from above” (surveillance), in the context of consumer wearables and cloud computing.
- Weaponized Drones—using deontological and utilitarian moral theories to question the US government practice of killing people based on metadata.
- Research Ethics—exploring the ethics of research that relies upon databases derived from social media use, and examining the implications for standards of informed consent and the lack of IRB oversight for private sector research.