Research talk: Image and network analysis: From foundations to applications in art museums and child mental health

Speaker: Mariano Tepper, Duke University

I will start this talk by describing a recurring problem in unsupervised data exploration. Clustering is the task of grouping a set of objects in such a way that objects in the same group or cluster are more similar to each other (in some sense) than to those in other clusters. Different techniques lead to different solutions: which one is the right one? We formulate a consensus clustering solution that integrates these different solutions, distilling all their good qualities. I will present this novel framework, based on nonnegative matrix factorization (NMF), and show how to handle large scale problems. This led to new computational algorithms in big data NMF, one of the most critical tools in data science. These algorithms were released as a very efficient software package for large data analysis challenges.

After presenting the fundamentals of this new approach to a critical problem in image and network sciences, I will describe two novel and unique projects that emerged from my research in image and video processing.

The first one is a collaboration between Engineering and Art History to use emerging technologies for developing a new model of the “engaged museum” that reaches out to involve the public of all ages in “reconnecting” works of art to their original context through interactive and gaming displays. The first of these prototypes is now part of the Nasher Museum’s permanent collection at Duke University.

The second project’s goal is to help in the automatic early detection of child developmental disorders, in particular for autism spectrum disorder. Nowadays, detection methods are extremely time-intensive and require a high level of observer training; thus, they are impractical for large population clinical and research purposes. Our work aims at empowering clinicians, teachers, care givers, and parents in this early detection challenge. A key part of this initiative is our just-released mobile application for collecting and analyzing child behavioral data at an unprecedented scale and scope.