The MixFMM approach for Functional Clustering of Neuronal Signals

C. Rueda Sabater

The identification of unlabelled neuronal electric signals is one of the most challenging
open problems in neuroscience. Motivated to solve this problem, we propose MixFMM: a model-based approach for clustering oscillatory functional data. A mixture model is defined using Möbius waves as basic functions and gaussian errors.
We present a fair comparative analysis of the MixFMM with three competitors widely used in neuronal signal clustering. The datasets used for validation include benchmarking simulated and real cases. The internal and external validation indexes confirm a better performance of the MixFMM on real data sets against the competitors.

Keywords: Functional Data Analysis, FMM models, Oscillatory Signals, Model-based clustering

GT01.FDA2 Invited Session
November 8, 2023  4:00 PM
CC1: Audience

N. Acar Denizli, P. Delicado

D. P. Ovalle Muñoz, M. D. Ruiz Medina

H. A. Hernández Roig, M. C. Aguilera-Morillo, E. Arnone, R. E. Lillo Pascual, L. M. Sangalli