Search for: All records

Food insecurity hinders individuals from the healthy and sustainable life they truly deserve. Unfortunately, food insecurity and chronic health diseases affect millions of people across the United States. Food banks are constantly fighting the uphill battle against food insecurity to supply adequate, relevant, healthy meals to those who need them. Oftentimes hunger relief organizations lack data and software tools that could aid strategic decision-making. A local food bank faces this exact problem and is struggling to find clients that face chronic health diseases in their service area. This study uses data from the local food bank to develop visualizations that investigate the health considerations of the population they serve. The results easily found a specific county with the largest number of health considerations and a zip code with the highest number of individuals facing hypertension. Dominant chronic health considerations highlight the importance for food banks to diversify their food selections. It is important for the local food bank to know what foods are essential within each county and zip code area to provide services that will be valuable to those who need them. This study benefits food banks so they can yield better service to the community. 

Food insecurity is a serious problem in America and the pandemic makes the problem even worse. Feeding America has more than 200 food banks. that These food banks and their partner agencies are the key players in the battle against food insecurity. Partner agencies may vary in size and location depending on the service area and the variety of the partner agencies and the complexities of their operations make equitable food distribution very challenging. There is a need for a meaningful to group those partner agencies to assist food bank operations managers to make informed decisions. This study uses data from a local food bank and its partner agencies. Each agency is unique in terms of its behavior. Therefore, k-means clustering was used to categorize agencies into groups based on the number of persons served and the amount of food received. The results of the study will provide evidence-based information to assist the food bank in making informed decisions. 

Maintaining an appropriate staffing level is essential to providing a healthy workplace environment at nursing homes and ensuring quality care among residents. With the widespread Covid-19 pandemic, staff absenteeism frequently occurs due to mandatory quarantine and providing care to their inflicted family members. Even though some of the staff show up for work, they may have to perform additional pandemic-related protection duties. In combination, these changes lead to an uncertain reduction in the quantity of care each staff member able to provide in a future shift. To alleviate the staff shortage concern and maintain the necessary care quantity, we study the optimal shift scheduling problem for a skilled nursing facility under probabilistic staff shortage in the presence of pandemic-related service provision disruptions. We apply a two-stage stochastic programming approach to our study. Our objective is to assign staff (i.e., certified nursing aids) to shifts to minimize the total staffing cost associated with contract staff workload, the adjusted workload for the changing resident demand, and extra workload due to required sanitization. Thus, the uncertainties considered arise from probabilistic staff shortage in addition to resident service need fluctuation. We model the former source of uncertainty with a geometric random variable for each staffer. In a proof-of-the-concept study, we consider realistic COVID-19 pandemic response measures recommended by the Indiana state government. We extract payment parameter estimates from the COVID-19 Nursing Home Dataset publicly available by the Centers for Medicare and Medicaid Services (CMS). We conclude with our numerical experiments that when a skilled nursing facility is at low risk of the pandemic, the absenteeism rate and staff workload increase slightly, thus maintaining the current staffing level can still handle the service disruptions. On the other hand, under high-risk circumstances, with the sharp increase of the absence rate and workload, a care facility likely needs to hire additional full-time staff as soon as possible. Our research offers insights into staff shift scheduling in the face of uncertain staff shortages and service disruption due to pandemics and prolonged disasters. 

In this paper, we present a co-design study with teachers to contribute towards the development of a technology-enhanced Artificial Intelligence (AI) curriculum, focusing on modeling unstructured data. We created an initial design of a learning activity prototype and explored ways to incorporate the design into high school classes. Specifically, teachers explored text classification models with the prototype and reflected on the exploration as a user, learner, and teacher. They provided insights about learning opportunities in the activity and feedback for integrating it into their teaching. Findings from qualitative analysis demonstrate that exploring text classification models provided an accessible and comprehensive approach for integrated learning of mathematics, language arts, and computing with the potential of supporting the understanding of core AI concepts including identifying structure within unstructured data and reasoning about the roles of human insight in developing AI technologies. 

In this paper, we present a co-design study with teachers to contribute towards development of a technology-enhanced Artificial Intelligence (AI) curriculum, focusing on modeling unstructured data. We created an initial design of a learning activity prototype and explored ways to incorporate the design into high school classes. Specifically, teachers explored text classification models with the prototype and reflected on the exploration as a user, learner, and teacher. They provided insights about learning opportunities in the activity and feedback for integrating it into their teaching. Findings from qualitative analysis demonstrate that exploring text classification models provided an accessible and comprehensive approach for integrated learning of mathematics, language arts, and computing with the potential of supporting the understanding of core AI concepts including identifying structure within unstructured data and reasoning about the roles of human insight in developing AI technologies.