Our Algorithms for Threat Detection project aims to develop new results and a toolkit of algorithms, applicable to a wide variety of spatiotemporal datasets, in topological data analysis for anomaly detection. These new results and algorithms focus on combining topological data analysis for the representation of spatial components of datasets and time-frequency analysis for the representation of the temporal components. The new algorithms will focus on anomaly detection in volumetric traffic data and US census data, but will be generalizable to other spatiotemporal datasets. The proposed research will also address algorithmic unfairness and biased datasets, developing strategies to mitigate disparate impacts that may occur as a result of our novel algorithms. The project will model human mobility across political boundaries across multiple scales, in order to identify and predict residential instability. The project will also address societal concerns regarding the deployment of automated decision making technologies--such as artificial intelligence--in the context of human dynamics.
We have a diverse group of researchers that are collaborating on the project.
- My Co-PI is Shannon Harper from the Sociology Department
- RA Sarah McCarty
- RA Mitch Haeuser
- Postdoctoral Associate Enrique Alvarado
- Mike Catanzaro from Geometric Data Analytics