To aid early illness detection research, we developed machine learning models to augment realistic physiological data using MIT Lincoln Laboratory’s Super Computer. We applied validation metrics to the generated data to compare its accuracy against the real data. We found that all five models we developed were capable of generating realistic heath data. The models’ ability to augment realistic “healthy” data can improve the ongoing efforts of early illness detection.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Talley, Caleb
• Patel, Jai
• Ussrey, Natasha

Subject

• Project-Based Learning
• Health
• Computing

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-102523-150308
• 114239

Mot-clé

• High Performance Computing
• Data Science
• Generative AI
• Deep Learning
• Big Data
• Machine Learning

Advisor

• Liu, Xiaozhong
• Heineman, George T.

Year

• 2023

Center

• MIT Lincoln Laboratory-Lexington, Massachusetts Project Center - MQP

Sponsor

• MIT Lincoln Laboratory

Date created

• 2023-10-25

Resource type

• Major Qualifying Project

Major

• Computer Science

Source

• E-project-102523-150308

Rights statement

• In Copyright

Dernière modification

• 2023-12-04