Improving Strategies For Hunger Relief and Food Security Through Computational Data Science
Research Traineeship Program
Information-driven Decision Making
Information inequality is the multifaceted disparity among social units in accessing and utilizing information resources for their benefit. Food security is hindered by information inequality among inter- and intra- food donors, distributors and beneficiaries We aim for an equitable, effective, efficient, and sustainable food security network by investigating information inequality in food security using social network analysis (SNA) and other big-data techniques. We recognize two topics under this theme: (1) SNA and other big-data techniques and (2) information equity as a moral imperative
Information Visualization (Informed Seeing) is the use of interactive, visual representation of abstract data to amplify cognition. Data may be very messy, inconsistent, and contain errors, making it very difficult to use for decision making. Consequently, these data need to be preprocessed, analyzed, and properly presented to the users. This research theme contains two topics: (i) the measurement and design of appropriate visualization tools and (ii) development of interactive visual aids to support decision making in hunger relief.
Information-driven decision modeling (Intelligent solving) aims to use big data to optimize the allocation of resources to ensure that equity, effectiveness, and efficiency is achieved with respect to food distribution. A number of structural and operational constraints affect the ability to achieve these objectives. We seek to use data to develop computational models that allow us to understand the implications of welfare effects in the presence of food insecurity in local humanitarian food supply chains.
North Carolina Agricultural
And Technical State University