Title: Consistent Data Clustering and its Application to Medical Data
Abstract: Data clustering is a fundamental task for discovering patterns in data and is central to machine learning. Often, a data set is assumed to be sampled according to a probability measure. Given this perspective, clusters can be defined as peaks in the sampled probability density, and a clustering algorithm would need to identify the peaks in the density to compute the clusters. Some of the challenges in this approach include the non-uniform sampling of the density and the bridges between peaks of the density. To solve these problems, I showcase a clustering algorithm that divides the clustering problem into three steps: picking a good threshold on the sample density to separate the peaks, clustering the superlevel set at the chosen threshold, and classifying the remaining points. I will present the applications of my work in two different medical data projects: survey data of pediatric obstructive sleep apnea and image segmentation of brain tumors.
Dr. Vazquez will conclude her talk with a brief description of the personal journey that led her to the field of mathematical biology, highlighting the challenges she has faced along the way and how she has overcome them. This talk will be geared at the level of a general scientific audience.
Zoom information: To join the seminar by zoom, please use the following link:
https://osu.zoom.us/j/93066786961?pwd=aGxpQitJUmNLNlRqSi9naXBmWWx4dz09
Video: https://osu.box.com/s/5dhudi35im3csjzr94flxf8m3dr3othi