Jack Bodine

Read the blog post.

This project is a self-hosted short-form video client I built to replace corporate-owned apps like Instagram Reels. I wanted complete control over the algorithm and the content. The objective was to turn an addictive infinite feed into something that feels more healthy and productive. The backend is written in Python using FastAPI and SQLite, and uses ffmpeg to process scraped media into encrypted HLS streams. For the frontend, I developed a native iOS app using SwiftUI and a pool of AVPlayers. This project eventually turned into three blog posts, available on this site, which describe the implementation details of the project.

iOS Development, Swift, Python, Project Management

Read the write-up

For my master’s thesis, I created computational models for processing neuroscience data, specifically the massive amount of video data generated by two-photon calcium imaging (2PCI). Neuroscientists use 2PCI to record neuron activity, but manually mapping out individual neurons across terabytes of video makes scalable studies impossible. Existing automated tools either only segment the main body of the cell, or struggle to process lab-grown neural organoids.

To solve this, I built an end-to-end deep learning pipeline, focusing on U-Net segmentation models that I trained to map both the cell bodies and their processes. The biggest hurdle was an extreme lack of training data, as I only had 32 manually annotated images to work with. To get the model to perform, I implemented synthetic image generation (GANs and heuristics), data augmentation, and domain transferability to investigate if a model trained on one type of brain tissue could generalize to another.

I validated the pipeline on two very different datasets provided by the University of Copenhagen. The first involved neural organoids, comparing samples from healthy patients to those with schizophrenia, which allowed me to extract and analyze specific signal features like burst rates and synchronicity. The second dataset contained in vivo recordings of mice to observe how different medications affected their neuronal behavior. The results derived from my models are currently being worked into neuroscience publications.

Machine Learning, Research, Python, Project Management

Currently Unavailble

This NLP toolkit was made to implement various concepts from my NLP course. It includes n-gram models, logisitc regression classifiers, and sequence labeling models.

Natural Language Processing, Python, Machine Learning

Available Soon

At my university, Art of Code was registered as an art class rather than a computer science class. This course taught me to apply my programming skills in a creative medium. Using Processing in both Python and Java, I created several art projects that showcase the unique intersection of coding and art I explored during this course. These projects illustrate how programming can be used as a tool for artistic expression.

Art, Python, Java

Code Available on Github

“Computational Analysis of Big Data” focused on methods to handle and analyze large datasets to extract meaningful trends and insights. As part of a project, I worked with two other students to scrape movie data and analyze metrics such as the most successful director/actor combinations. This project utilized tools like Pandas, NumPy, and Streamlit, demonstrating our ability to work with big data and perform complex analyses.

Python, Data Analytics