A critical component of pandemic response is the ability to collect, process, and analyze large sets of complex data ranging from GIS surveillance information to viral genomic information.
Collection, processing and storage of complex data is only one component of this hub. The ability to utilize that data for predictive modeling is of further critical importance including pandemic spread models, hot-spot identification, behavioral connections to spread, etc. The ability to utilize pandemic information to inform scientific, community and governmental stakeholders represents an additional component of the ICCT hub that is essential to pandemic mitigation.
Coordinators: Sandy Justice, USF Sarasota-Manatee; Matthew Mullarkey, Muma College of Business; Sudeep Sakar, College of Engineering; Shivendu Shivendu, Muma College of Business
Research Cluster Areas:
- Data infrastructure to support the network, which will involve creating data lakes on the cloud in partnership with USF IT that is secure and stores all the relevant clinical, public health, mobility, and any other relevant datasets that are necessary to model present and future pandemic outbreaks
- Cloud-based analysis infrastructure, which will involve developing models and methods to generate insights, early warning signals, identifying hotspots, and visualizations using big data technologies
- Communications and Policy infrastructure, which will involve creating forward-looking simulations and analytical modeling tools with a goal of informing various stakeholders, including policymakers
- Data Security and Privacy involving vulnerabilities exposed by the virus and the changing nature of work as well as the deployment and use of surveillance mechanisms (including mobile and platform applications and personally identifiable data)
- Pandemic mapping & GIS coordination, which will involve coordinating big data sets with patient and citizen population behaviors to graph hotspots, trends, peaks, outbreaks and other social and behavioral patterns in the spread of communicable disease
- Deep learning, which will include efforts to support teams of natural science researchers seeking to gain insights from massive data to develop detailed understanding of the underlying nature of the disease, its spread, its containment, and its behavior in various human populations.
- Artificial intelligence and Machine Learning, which will include the development of algorithms and programs that learn from and automate approaches to make better, more rapid decisions in every sector, including treatment centers, public policy, disease management, experimental analysis, drug discovery, and patient communications