Harnessing the Power of Functional Data and Machine Learning in Biomedical Research
Conference
Proposal Description
In today's data-driven world, functional data is a commonly generated data in biomedical research. While functional data analysis (FDA) techniques for a single variable are very popular, recent works in FDA have also focused on multivariate and correlated data, all requiring the use of sophisticated machine learning techniques to understand biomedical data better. One of the issues with current FDA research has been that the various groups producing and applying cutting-edge methodology need more exposure to each other’s ideas. This session aims to bring together a very diverse group of researchers who are conducting innovative research at the intersection of functional data and machine learning, and who are applying these to biomedical and public health data. The speakers and chair of this session are diverse not only in their intellectual outlook, but also in their career stage, gender, and race. By bringing these individuals together, we expect to foster collaboration, spark engaging conversations, and attract new people in this important field of research.
Submissions
- Bayesian Learning for Disparities in Rare Surgical Outcomes: An Integrated Data Approach
- Functional Regression through Distributed Learning: An Application to Brain Imaging Studies
- Shifting-Corrected Regularized Regression for Metabolomics Identification and Quantification
- Sparse Functional Canonical Correlation Analysis for Multiview Data Integration
- Time-to-Event Analysis with Unknown Time Origins via Longitudinal Biomarker Registration