Manual Fine Needle Aspiration (FNA) biopsy is often used to diagnose breast cancer in Sub-Saharan Africa (SSA). While performed with ultrasound guidance in the United States, most SSA healthcare centers lack imaging resources, rendering clinicians unable to consistently sample breast lesions with adequate cellularity, leading to high false-negative rates, repeat patient visits, increased financial burden, and delayed treatment initiation. Our solution, an automated handheld device, has shown promise in improving sample cellularity as compared to manual FNA.

This project implements an integrated hardware-software architecture to enable robust acoustic sensing. The deployed setup pairs the microphone with a Blues Cygnet microcontroller board, which digitizes and streams audio data to a PC via USB. The wireless Blues Notecard operates by connecting to local Wi-Fi, enabling real-time environmental sound capture and automatic cloud uploads for centralized processing. Acoustic features, such as Mel-Frequency Energy (MFE) coefficients, are extracted from the raw signals to train machine learning models that are capable of distinguishing gunshots from ambient noise.

This project analyzes the Cleveland Browns’ practice field goal data to examine how variables like ball speed, launch angle, and apex influence kick success. Using linear regression, Random Forest models, and XGBoost, we predicted make probabilities across various conditions and distances. These probabilities were scaled using in-game Expected Points Added (EPA) values from nflfastR to estimate the potential impact of each practice kick. A bin-by-bin EPA analysis revealed areas where kickers underperform in games compared to practice, helping identify opportunities for targeted coaching. We also applied league-average scaling curves to evaluate how Browns kickers’ practice-to-game transition compares with the rest of the NFL. Results indicate that mechanical adjustments—such as increasing ball speed on longer kicks—can substantially enhance projected game EPA, supporting data-driven performance optimization.

DnATA is a DNA-based data storage platform designed to address the growing need for sustainable and durable data archiving. Our system uses a computational pipeline to convert digital files into DNA sequences, which are then stored and replicated inside bacterial cells. Leveraging natural bacterial replication reduces reliance on energy-intensive, short-lived conventional storage devices. By combining principles from synthetic biology, DnATA explores a novel biological approach to long-term archival data storage. While still in early stages, our work demonstrates the feasibility of encoding, storing, and retrieving digital information from cells, thereby opening new possibilities for secure, low-maintenance archival solutions.