Theses and Dissertations
Filtering by
- Creators: Harrington Bioengineering Program
Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage their carbohydrate counting. This early model has a 68.3% accuracy of identifying 101 different food classes. A more refined model in future work could be deployed into a mobile application to identify food the user is about to consume and log it for easier carbohydrate counting.
Chronic wounds affect many people worldwide and significantly impact their quality of life. Hydrogel wound dressings are a promising option for chronic wounds due to their properties, including mild fabrication conditions, high water content, biodegradability, and bioactive molecule delivery capabilities. This thesis will explore the mechanisms that contribute to the wound healing properties of a bovine type I collagen-based hydrogel that incorporates platelet-rich plasma and describe how this hydrogel will be capable of effectively healing chronic wounds.