The purpose of the registry/repository is to provide a mechanism to store data and images to help facilitate the development of a deep learning framework for automatic, objective, fast, and accurate image quality assessment (IQA) of structural MRI data. IQA is typically performed via visual inspection by MRI technologists and can be time-consuming, subjective, and error prone. Our method will complete IQA in milliseconds with high sensitivity and specificity.
With generative artificial intelligence (genAI), there are many unknowns about the best ways to use it for teaching and learning. This study's purpose is to identify best practices for creating learning experiences using genAI.
The research study seeks to improve the effectiveness of warnings for little cigars and cigarillos (LCCs) among youth who currently use, have ever used, or are susceptible to using LCCs
The purpose of this research study is to better understand executive function and decision making in adults. We are interested in how color and emotional interference impact reaction time and attention.
The purpose of this research study is to investigate the level of community engagement in wind energy developments in the European Arctic, with a focus on the involvement of Indigenous communities, such as the Sámi people. The study aims to understand the factors driving community engagement and the extent to which justice considerations are integrated within the energy transition process.
This study is examining Medicaid "unwinding", which refers to the process occurring nationwide of states resuming eligibility redeterminations for Medicaid enrollees after three years of continuous pandemic-related coverage protections. Over 15 million people are estimated to lose Medicaid coverage through this process, with nearly half still remaining eligible but facing administrative barriers to renew their coverage. This study focuses specifically on North Carolina's experiences with unwinding, utilizing a case study approach.The study aims to explore the factors shaping North Carolina's response, challenges encountered, and outcomes thus far. It also examines potential solutions to strengthen Medicaid policy for future redeterminations.
This project helps UNC Health support the health and happiness of people in North Carolina by growing local businesses and sharing wealth. We plan to do this by 1) learning how UNC Health's 14 places feel about buying things, especially from diverse and green businesses; and 2) getting all UNC Health places to agree on supporting small, local, and diverse businesses.
Interviews are being conducted to establish a set of criteria for gauging the success or failure of corporate rebranding campaigns.
Predictive modeling has recently attracted a lot of attention from organizations trying to leverage AI and big data to improve their work processes such as decision-making. However, real-world problems are rarely well-formulated machine learning problems. Practitioners have to supply a well-defined predictive target to operationalize a predictive model. In such cases, they often resort to using observed variables to approximate the actual construct of interest. For example, people have used high sales numbers as a proxy for a good employee. Proxy label selection is a recurring challenge when predictive ML is applied to real-world problems. The purpose of this interview study is to understand how ML practitioners select proxy labels, evaluate proxy labels, and iterate through the different tasks involved.
This study will test the effect and effectiveness of labels on political ads that disclose the use of generative AI. Governments and some internet platforms have begun requiring that political advertisers include these disclaimers, however we lack experimental study of the effect and effectiveness of these disclaimers.