Recursive Exponentially Weighted N-way Partial Least Squares Regression with Recursive-Validation of Hyper-Parameters in Brain-Computer Interface Applications

A tensor-input/tensor-output Recursive Exponentially Weighted N-Way Partial Least Squares (REW-NPLS) regression algorithm is proposed for high dimension multi-way (tensor) data treatment and adaptive modeling of complex processes in real-time. The method unites fast and efficient calculation schemes...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 7; no. 1; pp. 16281 - 15
Main Authors: Eliseyev, Andrey, Auboiroux, Vincent, Costecalde, Thomas, Langar, Lilia, Charvet, Guillaume, Mestais, Corinne, Aksenova, Tetiana, Benabid, Alim-Louis
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 24.11.2017
Nature Publishing Group
Subjects:
631/378/116/2394
639/705/1042
Algorithms
Brain
Brain-Computer Interfaces
Computational neuroscience
Electrocorticography
Electroencephalography
Engineering Sciences
Humanities and Social Sciences
Implants
Least-Squares Analysis
Magnetoencephalography
multidisciplinary
Nervous system
Neurosciences - methods
Recursive algorithms
Science
Science (multidisciplinary)
Software
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A tensor-input/tensor-output Recursive Exponentially Weighted N-Way Partial Least Squares (REW-NPLS) regression algorithm is proposed for high dimension multi-way (tensor) data treatment and adaptive modeling of complex processes in real-time. The method unites fast and efficient calculation schemes of the Recursive Exponentially Weighted PLS with the robustness of tensor-based approaches. Moreover, contrary to other multi-way recursive algorithms, no loss of information occurs in the REW-NPLS. In addition, the Recursive-Validation method for recursive estimation of the hyper-parameters is proposed instead of conventional cross-validation procedure. The approach was then compared to state-of-the-art methods. The efficiency of the methods was tested in electrocorticography (ECoG) and magnetoencephalography (MEG) datasets. The algorithms are implemented in software suitable for real-time operation. Although the Brain-Computer Interface applications are used to demonstrate the methods, the proposed approaches could be efficiently used in a wide range of tasks beyond neuroscience uniting complex multi-modal data structures, adaptive modeling, and real-time computational requirements.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
PMCID: PMC5701264
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-017-16579-9