GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs

In this paper, a novel fully-automated state-based decoding method has been proposed for continuous decoding problems in brain-machine interface (BMI) systems, called Gaussian mixture of model (GMM)-assisted PLS (GMMPLS). In contrast to other state-based and hierarchical decoders, the proposed metho...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Reza Foodeh, Vahid Shalchyan, Mohammad Reza Daliri
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Brain–machine interfaces (BMIs) partial least square (PLS) state-based decoding continuous decoding Gaussian mixture of model (GMM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/f15419abfc554b26a732ae91211a69ae
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f15419abfc554b26a732ae91211a69ae
record_format	dspace
spelling	oai:doaj.org-article:f15419abfc554b26a732ae91211a69ae2021-11-18T00:08:01ZGMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs2169-353610.1109/ACCESS.2021.3123098https://doaj.org/article/f15419abfc554b26a732ae91211a69ae2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9585446/https://doaj.org/toc/2169-3536In this paper, a novel fully-automated state-based decoding method has been proposed for continuous decoding problems in brain-machine interface (BMI) systems, called Gaussian mixture of model (GMM)-assisted PLS (GMMPLS). In contrast to other state-based and hierarchical decoders, the proposed method does not demand any prior information about the desired output structure. Instead, GMMPLS uses the GMM algorithm to divide the desired output into a specific number of states (clusters). Next, a logistic regression model is trained to predict the probability membership of each time sample for each state. Finally, using the concept of the partial least square (PLS) algorithm, GMMPLS constructs a model for decoding the desired output using the input data and the achieved membership probabilities. The performance of the GMMPLS has been evaluated and compared to PLS, the nonlinear quadratic PLS (QPLS), and the bayesian PLS (BPLS) methods through a simulated dataset and two different real-world BMI datasets. The achieved results demonstrated that the GMMPLS significantly outperformed PLS, QPLS, and BPLS overall datasets.Reza FoodehVahid ShalchyanMohammad Reza DaliriIEEEarticleBrain–machine interfaces (BMIs)partial least square (PLS)state-based decodingcontinuous decodingGaussian mixture of model (GMM)Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148756-148770 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Brain–machine interfaces (BMIs) partial least square (PLS) state-based decoding continuous decoding Gaussian mixture of model (GMM) Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Brain–machine interfaces (BMIs) partial least square (PLS) state-based decoding continuous decoding Gaussian mixture of model (GMM) Electrical engineering. Electronics. Nuclear engineering TK1-9971 Reza Foodeh Vahid Shalchyan Mohammad Reza Daliri GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
description	In this paper, a novel fully-automated state-based decoding method has been proposed for continuous decoding problems in brain-machine interface (BMI) systems, called Gaussian mixture of model (GMM)-assisted PLS (GMMPLS). In contrast to other state-based and hierarchical decoders, the proposed method does not demand any prior information about the desired output structure. Instead, GMMPLS uses the GMM algorithm to divide the desired output into a specific number of states (clusters). Next, a logistic regression model is trained to predict the probability membership of each time sample for each state. Finally, using the concept of the partial least square (PLS) algorithm, GMMPLS constructs a model for decoding the desired output using the input data and the achieved membership probabilities. The performance of the GMMPLS has been evaluated and compared to PLS, the nonlinear quadratic PLS (QPLS), and the bayesian PLS (BPLS) methods through a simulated dataset and two different real-world BMI datasets. The achieved results demonstrated that the GMMPLS significantly outperformed PLS, QPLS, and BPLS overall datasets.
format	article
author	Reza Foodeh Vahid Shalchyan Mohammad Reza Daliri
author_facet	Reza Foodeh Vahid Shalchyan Mohammad Reza Daliri
author_sort	Reza Foodeh
title	GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
title_short	GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
title_full	GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
title_fullStr	GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
title_full_unstemmed	GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs
title_sort	gmmpls: a novel automatic state-based algorithm for continuous decoding in bmis
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/f15419abfc554b26a732ae91211a69ae
work_keys_str_mv	AT rezafoodeh gmmplsanovelautomaticstatebasedalgorithmforcontinuousdecodinginbmis AT vahidshalchyan gmmplsanovelautomaticstatebasedalgorithmforcontinuousdecodinginbmis AT mohammadrezadaliri gmmplsanovelautomaticstatebasedalgorithmforcontinuousdecodinginbmis
_version_	1718425260046417920

GMMPLS: A Novel Automatic State-Based Algorithm for Continuous Decoding in BMIs

Ejemplares similares