Research Interests

Academic Interests

My research interests focus on adapting machine learning algorithms to solve classically difficult problems encountered in the design of experiments statistics sub-discipline. Advances in computing in recent decades have enabled practical application of optimal experimental design paradigm. In optimal design, the researcher can specify cost (via a fixed number of affordable experiments) and rigorously define the properties of a design with high quality. These two considerations can be used in conjunction with an optimization routine to generate the design which gives the experimenter "the most bang for their buck" in practice. My current research thrust is adapting particle swarm optimization, a metaheuristic that has been demonstrated to perform very well on high dimensional multi-modal objectives, to the optimal design problem and comparing my results to designs generated from contemporary leading algorithms, namely the coordinate exchange and genetic algorithms.

Interdisciplinary Interests

I entered the field of statistics via industrial work, e.g. quality control, experimentation, and process optimization. I have a long experience working directly with complicated mass spectrometric techniques, electron microscopy, wet chemistry methods and all related problems including development and validation of new measurement techniques, uncertainty quantification and error propagation (e.g. GUM), and inter-laboratory proficiency testing. I am currently working to build collaborative opportunities both within and without Utah State University in these fields to apply statistics and machine learning approaches to innovate these fields.