Gut Predictions: Building a Predictive Model of the Gut Biome
Matthew Biggs (Biomedical Engineering) and Steven Steinway (Biomedical Science)
This project explores which intestinal bacteria promote stability in the healthy microbiome and which are responsible for disrupting the microbiome in disease. Given the complexity of the microbiome, the tools of network science allowed them to systematically design and propose treatment strategies for numerous human diseases. Learn more.
Data-Driven, Complex Systems Model of Public Opinion
Osama Eshera (Systems & Information Engineering) and Chelsea Goforth (Politics)
This project used a complex systems framework to develop a more multifaceted conceptualization of public opinion, which yielded more fruitful results for questions about public opinion posed by political, non-profit and community organizations. Learn more.
Data Meets Mind-Body Therapy: Data-Driven Musculoskeletal Models that Guide the Use of Yoga for Treatment of Chronic Diseases
Tamara Fischer-White (School of Nursing) and Kelley Virgilio (Biomedical Engineering)
This project developed advanced computational models to provide a scientific understanding of muscle contributions to yoga and to form a novel framework for revealing the most effective yoga therapy poses and sequences for those with chronic disease. Learn more.
Uncovering Mechanisms of Social Movements within the Arab Spring: A Data-Mining Approach
Robert Kubinec (Politics) and Peter Wu (Systems and Information Engineering)
This project used a massive database of tweets collected from Arab Twitter users during the first six months of the Arab Spring, covering hundreds of protest events. They employed a statistical computer model to examine popular grievances expressed on Twitter and their connection to later outbreaks of protest activity.
Maintained Individual Data Distributed Likelihood Estimation (MIDDLE)
Joshua Pritikin (Psychology) and Yang Wang (Systems and Information Engineering)
This project developed software, the Maintained Individual Data: Distributed Likelihood Estimation, or MIDDLE, to provide a way for social, behavioral, and health researchers to collect and analyze the data they need, while ensuring that subjects’ personal data remains on their own smartphones and is never shared with researchers. Using the software application, researchers send candidate models to subjects’ smartphones, which will evaluate how well the model fits their own data. Only the model fit metric will be communicated back to researchers. In this way, statistical analysis can be conducted without revealing any personal data.