Podcasts and Videos
Attempting to use real medical data in a classroom setting is hard to do without limiting yourself to specific datasets. Through the research being presented we work to create an end-to-end workflow for generating synthetic health data and testing the synthetic data for privacy, resemblance, and utility. This includes creating a novel generation method called HealthGAN and defining metrics for measuring the privacy and resemblance of the generated data. The utility of the data is then measured in the context of the analysis task the dataset was designed to accomplish. The workflow is then tested by attempting to create synthetic versions of two real medical datasets from a secure environment.
User expectations of modern web applications continue to outpace the productivity of the software engineering process. The semantic web application stack of RDF, SPARQL, and related technologies, provides many benefits to users and developers, at the expense of additional complexity that impedes the engineering process. I will present a new software architecture that attempts to maximize the user-visible benefits of these technologies while minimizing their impact on developer productivity. I will also discuss an implementation of the architecture using off-the-shelf tools, such as TypeScript, GraphQL, and Scala, in conjunction with semantic web technologies. The result serves as a vehicle for delivering bespoke web applications for sponsored research projects, incorporating research into symbolic artificial intelligence, and helping students learn modern software engineering.
Recent years have seen a rising interest in combining the rich structured information contained in knowledge graphs with applications involving personalization. This talk will discuss insights into the emerging topic of "personal knowledge graphs", including key research challenges identified in literature and examples of proposed personal knowledge graph systems (especially in the domain of personalized health).
A health-care data expert (IDEA Associate Director Kristin Bennett) and a biomedical engineer discuss how data analysis can be used to tackle today’s biggest health challenges.
An artificial intelligence expert (IDEA Director Jim Hendler) and an accomplished musician consider how humans could and should responsibly deploy new technologies.