2016
DOI: 10.18869/ijabbr.2016.117
|View full text |Cite
|
Sign up to set email alerts
|

A review on EEG based brain computer interface systems feature extraction methods

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
2
0
2

Year Published

2017
2017
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 17 publications
0
2
0
2
Order By: Relevance
“…Single-trial effective brain connectivity patterns enhance discriminability of mental imagery tasks Dheeraj Rathee 1 , Hubert Cecotti 1,2 and Girijesh Prasad 1 kinesthetic imagination of a particular motor action without its actual execution [9][10][11]. Although promising results and achievements have been reported in the literature [12], there remain many challenges and barriers to the use of this technology reliably and effectively for the intended beneficiaries [13]. One of the probable reasons for the limitations of MI-based BCI is the use of static channel derived features (e.g.…”
Section: Journal Of Neural Engineeringmentioning
confidence: 99%
“…Single-trial effective brain connectivity patterns enhance discriminability of mental imagery tasks Dheeraj Rathee 1 , Hubert Cecotti 1,2 and Girijesh Prasad 1 kinesthetic imagination of a particular motor action without its actual execution [9][10][11]. Although promising results and achievements have been reported in the literature [12], there remain many challenges and barriers to the use of this technology reliably and effectively for the intended beneficiaries [13]. One of the probable reasons for the limitations of MI-based BCI is the use of static channel derived features (e.g.…”
Section: Journal Of Neural Engineeringmentioning
confidence: 99%
“…By selecting the features to be extracted, you can extract the required information from the input data to simplify the task. Analysis using a large number of variables usually requires a lot of memory and time [11]. It has been found that each person has different characteristics of the brain controlling movement to obtain EEG signals, that is, there is a certain difference between individuals and individuals.…”
Section: Introductionmentioning
confidence: 99%
“…De acuerdo con el análisis de literatura realizado, se observó que la detección de la onda P300 se lleva a cabo mediante algoritmos con un enfoque de aprendizaje automático que tienen una etapa de extracción de características y una de clasificación. Para extraer características, se utilizan los métodos de single-trial (Thigpen & Keil, 2017), análisis de componentes principales (PCA) (Mirghasemi et al, 2006;Swarnkar et al, 2016) y transformada Wavelet (Ghassemzadeh & Haghipour, 2016;Uma & Kumar, 2014;Wang et al, 2014). Estos modelos se utilizan para reducir la cantidad de información cuando se obtiene el P300 con una gran cantidad de electrodos.…”
Section: Introductionunclassified
“…Estos modelos se utilizan para reducir la cantidad de información cuando se obtiene el P300 con una gran cantidad de electrodos. Para clasificación, es común el uso de los métodos de LDA por partes (Capati et al, 2016;Ghassemzadeh & Haghipour, 2016;Li et al, 2020), SVM (Bhatnagar et al, 2016;Momennezhad et al, 2014;Rakotomamonjy & Guigue, 2008) y redes neuronales convolucionales (CNN) (Carabez et al, 2017;Liu et al, 2018;Vařeka, 2020). LDA por partes es un clasificador popular en múltiples aplicaciones de P300, pero requiere de una cantidad significativa de electrodos (8,16 y 64) para tener resultados aceptables.…”
Section: Introductionunclassified