ATD: Quantifying Human Mobility using Topological and Time-Frequency Analysis

Iowa State University, Ames IA

Investigators

Abstract

The immense amount of data at hand in modern applications creates challenges in storing, processing, and mining the data. These challenges are particularly difficult when the data concerns human behavior and involves both spatial and temporal components. This project aims to address challenges posed by such datasets in an effort to better understand human dynamics and mobility. This project has the potential to benefit society in several ways. First, by developing more accurate and efficient mathematical algorithms for processing spatiotemporal data, the project results can lead to improved anomaly and threat detection. Second, the project will contribute to STEM workforce development through training of graduate students and postdoctoral associates, curriculum development, and outreach activities. Third, results of the project will provide avenues for incorporation of new algorithms for analyzing datasets that describe human behavior. Fourth, the project will address the ethical, legal, and societal impacts of the research, especially societal concerns regarding the collection and analysis of data as well as disparate impacts resulting from the processing of that data. This 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. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.