Below is a collection of work and projects that I enjoyed doing and would like to share with those who are interested. Much of what's shown here represents my deep interest in data driven projects, and encapsulates the skillset I continue to cultivate to support my career and growth into data science. These projects are only a select few, and of course is not everything I've done over my many years of programming, analysis, and software development.
This static report was entered in a data visualization and design challenge
hosted by the Pacific Data Hub. The challenge proposes an open-ended
question of exploring provided datasets pertaining to different
themes, and challenges participants to use that data to visualize key
points and issues that they would like to highlight.
For my entry, I focused on the sparse health care coverage across the
Tonga regions. Landing on this topic required several iterations and many hours of
explorations as data for different regions and themes proved to be sparese.
In addition to the data provided, I pulled additional open-
source data recorded by the World Health Organization in order to provide
a baseline comparison across the adjacent, relatively-comparable area
(specifically the Western Pacific.)
The static report was designed in Figma, with nearly all colorschemes, heatmaps,
and visualizations exported using the Python library Seaborn. The challenge itself
entailed several hours of iteration, design, question formulation, and processing, but
was ultimately a fun side-project outside of my regular working hours.
Published research project that focuses on utilizing machine learning models to enable ML feature type inference. The work I was fortunate to contribute to the lab heavily focused on gathering and cleaning data from multiple, disparate datasets, and processing these datasets to be used in training machine learning models. Many thanks to UCSD, the STARS research program, and Dr. Arun Kumar and his Data Analytics Lab for the opporutnity to do such work.
This was my first first-authored research project (as-in I was the lead in conducting experiments, writing the code, and writing the paper from draft-to- publication). The work outlined in this paper utilizes object detection methods taken from the field of computer vision. We use detection models to help quantify objects-of-interest (here, we count mosquitos) in an effort to support biomedical research.
My second first-authored research paper. This work revolved around wearable technology, with a goal of measuring the feasability of utilizing simple, low cost sensors to measure head movement. The larger, long term objective was to see if such sensors could be used in measuring repetitive strain injuries, and if such inexpensive sensors can be embedded for assistance. This was my introduction to working with microcontrollers and utilizing them to collect data from human movement.
This was a fun personal project to explore the athlete data collected by OpenPL. As a brief primer, OpenPL collects data from powerlifting meets, allowing for tracked and up-to-date data on powerlifters and the evergrowing niche community of powerlifting. As a powerlifter myself, I was curious as to how other people start out in the sport and what those numbers have looked like over the past few years.