Dimension Reduction Techniques in a Brain–Computer Interface Application

Federico Cozza; Paola Galdi; Angela Serra; Gabriele Pasqua; Luigi Pavone; Roberto Tagliaferri

doi:10.1007/978-981-13-8950-4_11

Dimension Reduction Techniques in a Brain–Computer Interface Application

Federico Cozza, Paola Galdi, Angela Serra, Gabriele Pasqua, Luigi Pavone, Roberto Tagliaferri^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

Abstract

Electroencephalography (EEG)-based Brain–computer interface (BCI) technology allows a user to control an external device without muscle intervention through recorded neural activity. Ongoing research on BCI systems includes applications in the medical field to assist subjects with impaired motor functionality (e.g., for the control of prosthetic devices). In this context, the accuracy and efficiency of a BCI system are of paramount importance. Comparing four different dimension reduction techniques in combination with linear and nonlinear classifiers, we show that integrating these methods in a BCI system results in a reduced model complexity without affecting overall accuracy.

Original language	English
Title of host publication	Neural Approaches to Dynamics of Signal Exchanges
Editors	Anna Esposito, Marcos Faundez-Zanuy, Francesco Carlo Morabito, Eros Pasero
Publisher	Springer
Pages	107-118
Number of pages	12
Volume	151
Edition	1
ISBN (Electronic)	978-981-13-8950-4
ISBN (Print)	978-981-13-8949-8
DOIs	https://doi.org/10.1007/978-981-13-8950-4_11
Publication status	Published - 2020

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	151
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Keywords / Materials (for Non-textual outputs)

Brain–computer interface
Dimension reduction
EEG
Machine learning
p300

Access to Document

10.1007/978-981-13-8950-4_11Licence: All Rights Reserved

https://link.springer.com/chapter/10.1007/978-981-13-8950-4_11#Abs1Licence: All Rights Reserved

Cite this

Cozza, F., Galdi, P., Serra, A., Pasqua, G., Pavone, L., & Tagliaferri, R. (2020). Dimension Reduction Techniques in a Brain–Computer Interface Application. In A. Esposito, M. Faundez-Zanuy, F. Carlo Morabito, & E. Pasero (Eds.), Neural Approaches to Dynamics of Signal Exchanges (1 ed., Vol. 151, pp. 107-118). (Smart Innovation, Systems and Technologies; Vol. 151). Springer. https://doi.org/10.1007/978-981-13-8950-4_11

@inbook{e3fa8244b96f4b3aa5ce11590e3a8819,

title = "Dimension Reduction Techniques in a Brain–Computer Interface Application",

abstract = "Electroencephalography (EEG)-based Brain–computer interface (BCI) technology allows a user to control an external device without muscle intervention through recorded neural activity. Ongoing research on BCI systems includes applications in the medical field to assist subjects with impaired motor functionality (e.g., for the control of prosthetic devices). In this context, the accuracy and efficiency of a BCI system are of paramount importance. Comparing four different dimension reduction techniques in combination with linear and nonlinear classifiers, we show that integrating these methods in a BCI system results in a reduced model complexity without affecting overall accuracy.",

keywords = "Brain–computer interface, Dimension reduction, EEG, Machine learning, p300",

author = "Federico Cozza and Paola Galdi and Angela Serra and Gabriele Pasqua and Luigi Pavone and Roberto Tagliaferri",

year = "2020",

doi = "10.1007/978-981-13-8950-4_11",

language = "English",

isbn = "978-981-13-8949-8",

volume = "151",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer",

pages = "107--118",

editor = "Anna Esposito and Marcos Faundez-Zanuy and {Carlo Morabito}, Francesco and Eros Pasero",

booktitle = "Neural Approaches to Dynamics of Signal Exchanges",

address = "United Kingdom",

edition = "1",

}

Cozza, F, Galdi, P, Serra, A, Pasqua, G, Pavone, L & Tagliaferri, R 2020, Dimension Reduction Techniques in a Brain–Computer Interface Application. in A Esposito, M Faundez-Zanuy, F Carlo Morabito & E Pasero (eds), Neural Approaches to Dynamics of Signal Exchanges. 1 edn, vol. 151, Smart Innovation, Systems and Technologies, vol. 151, Springer, pp. 107-118. https://doi.org/10.1007/978-981-13-8950-4_11

Dimension Reduction Techniques in a Brain–Computer Interface Application. / Cozza, Federico; Galdi, Paola; Serra, Angela et al.
Neural Approaches to Dynamics of Signal Exchanges. ed. / Anna Esposito; Marcos Faundez-Zanuy; Francesco Carlo Morabito; Eros Pasero. Vol. 151 1. ed. Springer, 2020. p. 107-118 (Smart Innovation, Systems and Technologies; Vol. 151).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - Dimension Reduction Techniques in a Brain–Computer Interface Application

AU - Cozza, Federico

AU - Galdi, Paola

AU - Serra, Angela

AU - Pasqua, Gabriele

AU - Pavone, Luigi

AU - Tagliaferri, Roberto

PY - 2020

Y1 - 2020

N2 - Electroencephalography (EEG)-based Brain–computer interface (BCI) technology allows a user to control an external device without muscle intervention through recorded neural activity. Ongoing research on BCI systems includes applications in the medical field to assist subjects with impaired motor functionality (e.g., for the control of prosthetic devices). In this context, the accuracy and efficiency of a BCI system are of paramount importance. Comparing four different dimension reduction techniques in combination with linear and nonlinear classifiers, we show that integrating these methods in a BCI system results in a reduced model complexity without affecting overall accuracy.

AB - Electroencephalography (EEG)-based Brain–computer interface (BCI) technology allows a user to control an external device without muscle intervention through recorded neural activity. Ongoing research on BCI systems includes applications in the medical field to assist subjects with impaired motor functionality (e.g., for the control of prosthetic devices). In this context, the accuracy and efficiency of a BCI system are of paramount importance. Comparing four different dimension reduction techniques in combination with linear and nonlinear classifiers, we show that integrating these methods in a BCI system results in a reduced model complexity without affecting overall accuracy.

KW - Brain–computer interface

KW - Dimension reduction

KW - EEG

KW - Machine learning

KW - p300

UR - http://www.scopus.com/inward/record.url?scp=85073164455&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-8950-4_11

DO - 10.1007/978-981-13-8950-4_11

M3 - Chapter (peer-reviewed)

AN - SCOPUS:85073164455

SN - 978-981-13-8949-8

VL - 151

T3 - Smart Innovation, Systems and Technologies

SP - 107

EP - 118

BT - Neural Approaches to Dynamics of Signal Exchanges

A2 - Esposito, Anna

A2 - Faundez-Zanuy, Marcos

A2 - Carlo Morabito, Francesco

A2 - Pasero, Eros

PB - Springer

ER -

Cozza F, Galdi P, Serra A, Pasqua G, Pavone L, Tagliaferri R. Dimension Reduction Techniques in a Brain–Computer Interface Application. In Esposito A, Faundez-Zanuy M, Carlo Morabito F, Pasero E, editors, Neural Approaches to Dynamics of Signal Exchanges. 1 ed. Vol. 151. Springer. 2020. p. 107-118. (Smart Innovation, Systems and Technologies). Epub 2019 Sept 19. doi: 10.1007/978-981-13-8950-4_11

Dimension Reduction Techniques in a Brain–Computer Interface Application

Abstract

Publication series

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this