Presentation 1: Radiation Therapy Treatment Planning under Uncertainties Speaker: Saba Ebrahimi Abstract: Cancer is one of the leading causes of death in the United States. Radiation Therapy (RT) is an effective treatment option for cancer patients. In radiation therapy, a patient undergoes a series of treatment sessions over several weeks. The clinical goal of radiation therapy is to maximize the tumor damage while minimizing toxic effects on surrounding healthy tissues during the course of treatment. Every step of radiation therapy is subject to some types of uncertainties, which may compromise the quality of treatment. Therefore, it is desired to develop an optimization approach to meet prescription requirements and tackle the uncertainties in radiation therapy. This talk will discuss some existing challenges in radiation therapy treatment planning and robust optimization role in addressing uncertainties in this problem. Presentation 2: Forecasting the Demand of Mobile Clinic Services at Target Communities via Integrating Multi-Source Data Speaker: Bilal Majeed Abstract: Demand forecasting plays an important role in the deployment of mobile clinic services to target communities as it can help the service provider to maximize its coverage under limited resource. The challenge in the development of the forecasting model lies in the fact that the delinquency is only observed in schools for which very limited information is available, while rich demographic and economic information is available for census tracts but no observations of delinquency has been made at the census tract level. To address such a challenge, we first develop a hierarchical approach to forecast the demand of vaccinations in schools and census tracts. In the first stage of the hierarchical approach, we solve a linear optimization model to compute an association matrix that can align some common features in both the census tracts and school zones. Then we use the estimated association to develop a forecasting model to predict the vaccination delinquency in both schools and census tracts. A non-convex optimization model is also proposed to find the association matrix and the forecasting model simultaneously. A case study from Houston Independent School District (HISD) and its associated communities is reported to demonstrate the efficacy of the new model and technique.
Saba Ebrahimi is a fourth-year Ph.D. student in Industrial Engineering at University of Houston. Her doctoral research is about radiation therapy treatment planning under uncertainties. In her dissertation, she focuses on combining optimization methods and machine learning techniques to find the optimal radiation therapy treatment plan for cancer patients that can improve patient’s survival. She also works as a research and teaching assistant at Department of Industrial Engineering, University of Houston. Bilal Majeed is a third-year Ph.D. student in Industrial Engineering at University of Houston. His doctoral research is on vaccination demand forecasting via integrating multisource data. In his dissertation, he focuses on combining optimization methods and machine learning techniques to predict the accurate demand for vaccinations in target communities and develop an optimal deployment plan that can increase coverage. He also works as a research and teaching assistant at Department of Industrial Engineering, University of Houston.