Projects

Abstract

Convolutional neural networks are the Machine Learning industry standard for computer vision, and they generally excel at image recognition. The operations performed in a convolutional neural network are mathematic in nature, yet the inner layers of the neural networks are often referred to as a ‘black box’ due to their complex inner workings. Melanoma, a rare but deadly form of skin cancer, can be seen in images, implying the possibility of image recognition using a convolutional neural network. This project aims to develop said network and use its mathematical properties to optimize its performance.

I am working on a team of six students in a simulated work environment adhering to the principles of Scrum. I am the team's Scrum Master. We are rebuilding from scratch an API and backend which will be used by multiple universities' food pantries. The goal of the project is to develop the API which will allow the pantries to quickly access government food-storage data. The project is still under development.

Details and Skills Used

• OpenAPI
• Scrum
• Javascript
• Git:
• Branching
• Issues
• Epics
• Groups & Subgroups
• Boards

Air Quality Analysis

This project examines 600,000 EPA air quality measurements taken over the span of 2000 - 2021. The report and presentation contain time-series visualization, geospatial mapping, non-parametric hypothesis testing, and machine learning methods such as cluster analysis, regression analysis, and classification.

This project demonstrates my skills in:

• Data Mining & Visualization
• Machine Learning (Supervised & Unsupervised)
• Statistical Analysis
• Distribution Analysis

Developing Tools to Study Racial and Human Equity In Higher Education

In the summer of 2021, I and my faculty advisor Dr. Mary Fowler set out to leverage the power of practical learning analytics and the R programming language to develop tools capable of detecting disparity in academic performance metrics across demographics.

Project Details & Skills Used:

• Data Visualization with ggplot2 (R)
• Algorithm Analysis
• Refactored code for efficiency
• Added functionality, customizability to visualizations
• Completed Michigan University MOOC: Practical Learning Analytics
• Attended Sloan Equity and Inclusion in STEM Introductory Courses (SEISMIC) Conference

I was hired by Worcester Polytechnic Institute as a Summer Instructor introducing eighth-grade students to Python. I worked alongside Dr. Eileen Perez and a classmate of mine. The program consisted of two seperate one-week sessions. I taught sessions about basic programming structures such as loops, arrays, conditionals, and more. I also wrote and provided sample code to the students and designed a fill-in-the-blank style template of a text-based Tic Tac Toe for them to practice with.

Helping Hands is an app prototype that my partner Sebastian Serafin and I built from scratch to presentation in 36 hours. The goal of the project was to connect those in need in the Worcester, MA area to volunteers who can help them. Look here for a four-minute presentation of our work. While we were not able to complete the app during the hackathon due to time constraints, we were able to work effectively as a team to quickly design and develop a prototype.