My career has been marked by multiple interdisciplinary research in various disciplines including logistics, clinical medicine, cloud computing, and cybersecurity education. This is a selection of papers on which I worked that highlights some work in these areas.
Machine Learning and Cloud Computing
Comparative Analysis of Cloud Storage Options for Diverse Application. (2021)
Antu AD, Kumar A, Kelley R, Xie B. (2022) Comparative Analysis of Cloud Storage Options for Diverse Application Requirements. In: Ye K., Zhang LJ. (eds) Cloud Computing – CLOUD 2021. CLOUD 2021. Lecture Notes in Computer Science, vol 12989. Springer, Cham. https://doi.org/10.1007/978-3-030-96326-2_6.
Abstract: Machine learning approaches to modeling of epidemiologic data are becoming increasingly more prevalent in the literature. These methods have the potential to improve our understanding of health and opportunities for intervention, far beyond our past capabilities. This article provides a walkthrough for creating supervised machine learning models with current examples from the literature. From identifying an appropriate sample and selecting features through training, testing, and assessing performance, the end-to-end approach to machine learning can be a daunting task. We take the reader through each step in the process and discuss novel concepts in the area of machine learning, including identifying treatment effects and explaining the output from machine learning models.
Choosing the Right Compute Resources in the Cloud: An analysis of the compute services offered by Amazon, Microsoft, and Google. (2021)
Kelley R, Antu AD, Kumar A, Xie B, “Choosing the Right Compute Resources in the Cloud: An analysis of the compute services offered by Amazon, Microsoft, and Google.” CyberC, , 2020 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, October 2020.
Abstract: In this paper we present a comparison of the various compute resources offered Amazon Web Services, Microsoft Azure, and Google Cloud Platform. We further identify several platform features including geographic availability, security and compliance, operating system support, container support, and serverless computing support that are directly comparable and provide recommendations and guidance for choosing a platform.
Machine Learning in Epidemiology and Health Outcomes Research. (2020)
Wiemken TL, Kelley RR, “Machine Learning in Epidemiology and Health Outcomes Research,” Annu. Rev. Public Health, Oct. 2019, doi: https://10.1146/annurev-publhealth-040119-094437.
Abstract: Machine learning approaches to modeling of epidemiologic data are becoming increasingly more prevalent in the literature. These methods have the potential to improve our understanding of health and opportunities for intervention, far beyond our past capabilities. This article provides a walkthrough for creating supervised machine learning models with current examples from the literature. From identifying an appropriate sample and selecting features through training, testing, and assessing performance, the end-to-end approach to machine learning can be a daunting task. We take the reader through each step in the process and discuss novel concepts in the area of machine learning, including identifying treatment effects and explaining the output from machine learning models.
Clinical Research in Pneumonia: Role of Artificial Intelligence. (2019)
Wiemken TL, Kelley RR, Mattingly WA, Ramirez JA. “Clinical Research in Pneumonia: Role of Artificial Intelligence” The University of Louisville Journal of Respiratory Infections 3, no. 1 (2019): 1.
Abstract: We propose adding machine learning, a branch of artificial intelligence, as a new methodology to analyze study results in pneumonia clinical research. Currently, few investigators use these methods as a replacement for traditional frequentist statistical methodologies.
Cybersecurity Education
The Impact of a GenCyber Camp on In-service Teachers’ TPACK. (2022)
Thomas K , Ivy J, Cook K, and Kelley R. “The Impact of a GenCyber Camp on In-service Teachers’ TPACK” Accepted with revisions to the Journal of CyberSecurity Education, Research, and Practice.
Abstract:The GenCyber Teacher Camp is a weeklong professional development designed to prepare middle and high school teachers with the skills necessary to teach their students the GenCyber Principles and Concepts and ignite in students a passion for cybersecurity that will lead them to pursue higher-education degrees and professions in the field. Over the course of the weeklong camp, teachers from across the state attended focused sessions promoting inquiry-based learning, discourse, and collaborative learning. These activities assisted teachers in interactively reflecting on best practices in STEM education while learning and applying the content of GenCyber Principles and Concepts within the context of their own field of study. For example, participants worked through a series of ethical and moral dilemmas related to cyber citizenship and technology, examined cyber vulnerabilities, and planned how they could increase students’ awareness and understanding of the issues. Additional activities throughout the week included Micro:bit encoding, Sphero programming, 3D printing, cyber law with a guest speaker from a local law firm, cybersecurity as a career with a guest speaker from a local bank, and cyber-crime with guest speakers from the FBI.
Incorporating Cyber Principles into Middle and High School Curriculum. (2021)
Ivy J, Kelley R, Cook K, and Thomas K, “Incorporating Cyber Principles into Middle and High School Curriculum”, IJCSES, vol. 4, no. 2, pp. 3-23, Nov. 2020. doi https://doi.org/10.21585/ijcses.v4i2.10
Abstract:Although many practicing teachers have not experienced teacher preparation programs that teach cyber security (Pusely & Sadera, 2011) or are familiar with cyber principles (Authors), embedding these ideas into instruction in a variety of content areas is essential for promoting cyber literacy and citizenship. This study explores a professional development program that provided middle and high school teachers across disciplines with opportunities to explore, first as learners and then as educators, cyber citizenship and programming concepts with explicit connections to the cybersecurity principles and concepts. Participating teachers experienced inquiry-based learning, focused classroom discourse, and collaborative learning that centered on GenCyber Cybersecurity First Principles and GenCyber Cybersecurity Concepts (GenCyber, 2019). Results indicated the professional development enabled teachers to iteratively reflect on best practices in cyber education while learning and applying the content of GenCyber Principles within the context of their own field of study.
Data Visualization
Visual Grids for Managing Data Completeness in Clinical Research Data Sets. (2014)
Kelley RR, Mattingly WA, Wiemken TL, Khan MS; Coats D, Curran D, Chariker JH, Ramirez JA. Visual Grids for Managing Data Completeness in Clinical Research Datasets. Journal of Biomedical Informatics. 2014 Dec 30. PMID: 25554683.
Abstract: Missing data arise in clinical research datasets for reasons ranging from incomplete electronic health records to incorrect trial data collection. This has an adverse effect on analysis performed with the data, but it can also affect the management of a clinical trial itself. We propose two graphical visualization schemes to aid in managing the completeness of a clinical research dataset: the binary completeness grid (BCG) for single patient observation, and the gradient completeness grid (GCG) for an entire dataset. We use these tools to manage three clinical trials. Two are ongoing observational trials, while the other is a cohort study that is complete. The completeness grids revealed unexpected patterns in our data and enabled us to identify records that should have been purged and identify missing follow-up data from sets of observations thought to be complete. Binary and gradient completeness grids provide a rapid, convenient way to visualize missing data in clinical datasets.
Real-time Enrollment Dashboard for Multisite Clinical Trials (2015)
W. A. Mattingly, R. R. Kelley, T. L. Wiemken, J. H. Chariker, P. Peyrani, B. E. Guinn, et al., “Real-Time Enrollment Dashboard For Multisite Clinical Trials,” Contemp Clin Trials Commun, vol. 1, pp. 17-21, Oct 30 2015.
OBJECTIVE: Achieving patient recruitment goals are critical for the successful completion of a clinical trial. We designed and developed a web-based dashboard for assisting in the management of clinical trial screening and enrollment.
MATERIALS AND METHODS: We use the dashboard to assist in the management of two observational studies of community-acquired pneumonia. Clinical research associates and managers using the dashboard were surveyed to determine its effectiveness as compared with traditional direct communication.
RESULTS: The dashboard has been in use since it was first introduced in May of 2014. Of the 23 staff responding to the survey, 77% felt that it was easier or much easier to use the dashboard for communication than to use direct communication.
CONCLUSION: We have designed and implemented a visualization dashboard for managing multi-site clinical trial enrollment in two community acquired pneumonia studies. Information dashboards are a useful tool for clinical trial management. They can be used as a standalone trial information tool or included into a larger management system. A demo of this system is no longer available.
PodPocket (2011)
Lake Cumberland District Health Department. ‘PODPocket’ mobile app and standard guidance help Kentucky counties establish PODs. Center for Infectious Diseases Research and Policy (CIDRAP).
PODPocket was a short development project I worked on while still a post-doc in 2011. We never published on the project, but we did receive a mention in a press release from the Barren River District Health Department with whom the project originated. The goal of the project was to develop mobile and web-based access to Job Action Sheets used by emergency response staff for Point-of-Dispense (POD) for distributing vaccines, food, water, and other supplies in the event of a pandemic or natural disaster. The press release and demo of the project are below:
A collaborative, team-based approach as part of the Kentucky Public Health Leadership Institute brought staff together from two local health departments (Barren River District Health Department and Lake Cumberland District Health Department) along with the Kentucky Department for Public Health Strategic National Stockpile Coordinator. This team developed standardized guidance and, with support from the University of Louisville, created a Web-based app called “PODPocket” to assist counties across the state in establishing and running Points of Dispensing. The app provides just-in-time training and numerous tools for reference and use in a portable, accessible format. Planners minimized staff orientation and training time and were able to better incorporate technology into their mass dispensing practices.