Under PNNL’s Applied Statistics & Computational Modeling division:-Design and deploy innovative machine learning algorithms and feature engineering schema-Use text mining techniques on open source data to understand nuclear energy landscapes -Develop software toolkits enabling accessible, reproducible, cutting edge research-Utilize ensemble and deep learning methods for predictive analyses on high volume data-Clean, process, and aggregate data sources across multiple time points and research techniques -Translate sponsor needs into statistical solutions deployed as live web applications-Dynamically mentor interns, peers, and students in both technical and professional areas-Work collaboratively, outputting statistical analyses on streaming data to live JavaScript visualizations-Develop and maintain multiple web applications built with Shiny

Business Statistics Lab-Demystified introductory statistics through hands-on experience with Microsoft Excel-Solidified core classroom concepts with discussion and interactivity-Explored statistical programming with R for students that have never coded before

-Innovate and develop accurate statistical methods for outlier detection and predictingsample analyte concentrations-Optimize search algorithms for parametrizing multiplex ELISA microarrays-Design optimal dilution schema for minimizing costs while maintaining extremely highaccuracy-Deliver coded algorithms and push progress on Github

Math 1060 (Trigonometry)-Independently lectured two sections totaling 87 undergraduate students-Wrote, proctored, graded, and reviewed student tests and quizzes-Developed online homework problem sets in WileyPlus-Maintained regular office hours to meet with studentsMath 1050 (College Algebra)-Prepared classroom materials for discussion-Independently led three laboratory sections totaling 120 undergraduate students-Proctored, graded, and reviewed student tests and quizzes-Maintained regular office hours to meet with students*Excellence In Teaching Award --2014

Under PNNL’s Applied Statistics & Computational Modeling division:-Employed Naive Bayes and SVM classifiers to build predictive models on NMR Data-Developed and maintained code as part of a collaborative project team member-Utilized parallelization techniques to improve speed and meet project goals

-Prepared bench stations for specified experiments- Prepared stock solutions- Assisted 35+ students with questions and procedures-Graded lab quizzes

This research was supported by NSF award OCI-1005117 and by Marshall University. The Big Green computational cluster was supported by NSF award EPS-0918949.-Generated large data sets of numerically simulated black hole collisions with the Einstein field equations and high performance platform computing.-Modeled black hole collisions with high power computing in a Linux based environment using C++ and the Cactus framework. -Visualized black hole collisions into animated 2D PyPlots and 3D VisIt clips-Negotiated professionally with a specialized scientific community for assistance with visualizationprogramming

-Compiled and organized monthly reports of in-network providers- Generated personalized reports for each provider -Evaluated provider applications and resolve inconsistencies before submission to the credentialing committee- Maintained a disciplined schedule without direct supervision- Used database software Xcelys

-Supported client in developing basic cognitive functions-Independently responsible for helping client with ADL