Graduate Seminar

Location:  Live Stream

Speaker: Pornpiya Vikitset

MSc Student supervised by Andrei Volodin

Title:  Similarity-based clustering of probability density functions

 Zoom Link:  https://uregina-ca.zoom.us/j/92805435386?pwd=42pEMT2QL4b8W8bqIOr5Y39hln8bSI.1

Abstract:

This seminar will present a new approach for clustering probability density functions (PDFs) using a robust similarity measure. The proposed approach addresses challenges such as unknown cluster counts, unbalanced cluster sizes, and noisy data. While numerical studies confirm its accuracy in grouping PDFs, the focus of this presentation will be on experiments using real-life data, demonstrating the performance and practical value of the proposed algorithm.