A New Functional Data Clustering Technique Based on Spectral Clustering and Downsampling

Al Alawi, M., Ray, S. and Gupta, M. (2022) A New Functional Data Clustering Technique Based on Spectral Clustering and Downsampling. 17th Conference of the International Federation of Classification Societies (IFCS 2022), Porto, Portugal, 19-23 July 2022. ISBN 9789899895591

Full text not currently available from Enlighten.

Publisher's URL: https://ifcs2022.fep.up.pt/wp-content/uploads/2022/07/IFCS2022_Book_Abstracts_v1.pdf


We present a new framework for clustering functional data along with a new paradigm for performing model selection based on downsampling. Our clustering framework is a generalisatiion of the spectral clustering approach and is flexible enough to exploit higher order features of curves, including derivatives. Extensive comparative studies with existing methods show a clear advantage of our approach over existing functional data analysis clustering approaches. Additionally, we present a new paradigm for model selection, by introducing the technique of downsampling, which allows us to create lower resolution replicates of the observed curves. These replicates can then be used to provide insight into the tuning parameters for the specific clustering techniques. The usefulness of the proposed methods is illustrated through simulations and applications to real-life datasets.

Item Type:Conference or Workshop Item
Glasgow Author(s) Enlighten ID:Gupta, Dr Mayetri and Ray, Professor Surajit and Al Alawi, Maryam Ali Said
Authors: Al Alawi, M., Ray, S., and Gupta, M.
College/School:College of Science and Engineering
College of Science and Engineering > School of Mathematics and Statistics > Statistics

University Staff: Request a correction | Enlighten Editors: Update this record