M. P. Bohorquez Castañeda, C. Avellaneda, L. Vargas
We present several methodologies for supervised classification of spatially-correlated functional data. We use several dimension reduction techniques, summary statistics, spatial dependence among functions, functional geostatistics and convolutional neural networks. The group-covariance models are allowed to be unequal. Proposals are illustrated using data of brain signals collected by electrodes that are transformed in functional data through power spectral density (PSD) and empirical mode decomposition (EMD).
Keywords: Functional geostatistics, classification, spatial dependence
Scheduled
Invited Session Colombian Society of Statistics. Spatial Statistics for functional data
June 7, 2022 6:40 PM
Conference hall