Epilepsy affects 50 million people worldwide, and most seizures happen without warning, leaving patients at risk of serious injury. While researchers have tried to predict seizures using brain wave patterns, existing methods struggle to work across different patients. I developed a machine learning system that analyzes EEG signals and achieved 87.5% accuracy in detecting pre-seizure…

My project investigates how tumor cells switch between dormant and actively dividing states (quiescence) using single-cell RNA sequencing data from breast cancer tumors. I analyze the data using computational tools in R to classify cells by their cell-cycle phase and measure how many quiescent-like cells are re-entering the cell cycle, particularly the S-phase where DNA…

It has been found that by implanting a diode into the body and applying a high frequency AC field in the area of the diode, precise, batteryless, and leadless peripheral nerve stimulation is possible. There has been minimal work on discovering the ideal configuration that can maximize stimulation while still being safe for patients. Using…

This project presents a low-cost system designed to measure task time and motor behavior using an interactive, sensor-based task. The system captures precise timing data during user interactions to assess motor–cognitive performance in a controlled yet accessible format. While not diagnostic, it demonstrates the potential for scalable behavioral tools to contribute to early screening of…

Our applied project focuses on the development of an affordable, portable wearable device that delivers targeted brain cooling as a neuroprotective therapy for conditions such as cardiac arrest and stroke, while minimizing the complications associated with whole-body hypothermia. We integrated COMSOL simulations with physical prototyping to model heat transfer using Peltier elements positioned at key…

This project develops a smart corrective insole for children with idiopathic toe walking, a gait pattern in which the forefoot contacts the ground instead of a consistent heel strike. The device combines plantar force sensors, an adjustable heel air bladder, and a Bluetooth-connected smartphone application to monitor gait in real time, encourage a heel-down walking…

This project develops a smart insole system that uses an array of pressure sensors to capture plantar pressure during walking. A machine learning model is trained to estimate ground reaction forces and center of pressure from this wearable data, reducing the need for traditional lab-based equipment. The system aims to enable portable, real-world biomechanical analysis…

Hydrocephalus diodes have a difficult time maintaining current while the human body attacks it. Our lab is testing several different encapsulation materials to ensure the longevity of the diode connection and maintenance of the current throughout. The end result is that the silicone double diode setup has that maintenance and longevity as previously mentioned and…

This project is a safety simulation based assessment using electromagnetic modeling to investigate how MRI radiofrequency fields interact with conductive deep brain stimulation (DBS) implants. A patient inspired phantom was simulated in a 1.5 T MRI environment to gain insights on incident electric fields and localized specific absorption rate (SAR) hotspots. The aim of the…

This project focuses on the validation and characterization of human induced pluripotent stem cell (hiPSC) lines generated via prime editing to knockout the BIN1 gene, a major genetic risk factor for Alzheimer’s Disease. Through genomic sequencing, protein analysis, and pluripotency assays, it was confirmed that these edited isogenic lines maintain cellular health and differentiation potential….