Curve Registration

I developed a method to register exponential family functional data, which was recently published in Biometrics. Our methods are implemented in the registr package, a GitHub hosted R package you can download here.

If each curve represents an observation for one subject, then curve registration refers to warping the domain (often time) of a set of curves so that the main features of each curve are aligned across subjects. An example with simulated data is below.


registration

Warping functions (center) are applied to the unregistered curves (left) to get registered curves (right). The exponential family part comes in because not all functional observations are Gaussian or continuous. Our approach to registration allows alignment of data that is discrete as well as continuous.

Below our method is applied to accelerometer data where each subject’s binary activity (active vs. not active) is collected at every minute over 24 hours. Periods of inactivity are colored in light blue and periods of activity are colored in dark blue. Applying our registration technique to the activity data pulls out patterns in physical activity.


binary registration

Interactive visualization of functional data analyses

I also have software for communicating the results of functional data analyses. I made a poster on this work for the 2017 Women in Statistics and Data Science (WSDS) conference, which you can access here.