Machine Learning with Biometrics Data for Personal Health Diagnosis
“Big Data” can be used to predict health but are very large datasets that are difficult to interpret in meaningful ways with basic statistical methods. Personal health sensors and administrative medical records create Big Data that can be organized and categorized by machine learning techniques to enhance patient and clinician understanding and detection of early stage disease. Students on this project will use health data (such as EKGs, pulse, tissue parameterization, and brain waves) to develop machine learning based algorithms to translate this data into meaningful health improvement.
This team will use machine learning techniques to analyze MGI Big Data. In the future, we aim to collect and analyze data from wearable sensors, cell phone health apps, and other sources for collecting real time biometric data. Applications include fitness and sports sensors, precision medicine, and health promotion.
Meeting Time and Location
Our team typically meets Fridays 4pm-6pm at EECS. A best time will be finalized once students are identified. Each subteam arranges a convenient time to meet and work together.
Each subteam has a team leader that reports to and meets with the faculty PI. The teams are flexibly structured to enhance creativity and opportunity for student growth.