Low-correlation multilinear dimensionality reduction applied to volcano-seismic classification

Peixoto A.A.T.; Fernandes C.A.R.; Lara P.E.; Inza A. · Pattern Recognition (2025) · DOI: 10.1016/j.patcog.2024.110946

Resumen

In the present work, a technique for reducing the dimensionality of tensor data, called Low-Correlation Multilinear Dimensionality Reduction (LC-MDR), is proposed. The method optimizes a cost function that takes into account the data correlation, generating variables with low correlation. The LC-MDR fits the input data correlation into a new tensor decomposition denoted by Even-Order Nested PARAFAC Decomposition (EONPD), a proposed extension of the Nested PARAFAC Decomposition (NPD) for higher-order tensors. In addition, a generalization of the EONPD, denoted by Higher-Order Nested PARAFAC Decomposition (HONPD), is also presented. Contrarily to existing approaches that use orthogonal transformation matrices, the LC-MDR does not impose this constraint on the transformation matrices in order to minimize the output correlation. The proposed technique was evaluated in a classification system of volcano-seismic events using data obtained from the Ubinas volcano in 2009 using a full tensorial classification framework. The results showed significant gains for the LC-MDR when compared with concurrent techniques in terms of accuracy, data correlation and processing time.