Convolutional denoising autoencoder based SSVEP signal enhancement to SSVEP-based BCIs

Chia Chun Chuang; Chien Ching Lee; Chia Hong Yeng; Edmund Cheung So; Bor-Shyh Lin; Yeou Jiunn Chen

doi:10.1007/s00542-019-04654-2

Convolutional denoising autoencoder based SSVEP signal enhancement to SSVEP-based BCIs

Chia Chun Chuang, Chien Ching Lee, Chia Hong Yeng, Edmund Cheung So, Bor-Shyh Lin, Yeou Jiunn Chen^*

^*Corresponding author for this work

Institute of Imaging and Biomedical Photonics

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

For steady state visually evoked potential (SSVEP) based brain computer interfaces (BCIs), the elicited SSVEP signals always contain noises and then the performance of SSVEP-based BCIs would be greatly degraded in practical applications. Therefore, to develop an SSVEP signal enhancement would be able to increase the accuracy of SSVEP-based BCIs. In this study, a convolutional denoising autoencoder based SSVEP signal enhancement is proposed to suppress the noise components. The convolutional denoising autoencoder is applied to estimate and suppress the noise components. To effectively estimate the noise components, a sinusoid wave is designed as an ideal SSVEP signal. To ignore the effects of phase, cross correlation is adopted to estimate the phase in the training stage. The experimental results evaluated by using signal-to-noise ratio and canonical correspondence analysis showed that the proposed approaches can effectively suppress the noises components. Therefore, the proposed approach can be applied to develop robust SSVEP-based BCIs.

Original language	English
Pages (from-to)	1-8
Number of pages	8
Journal	Microsystem Technologies
DOIs	https://doi.org/10.1007/s00542-019-04654-2
State	Published - 14 Oct 2019

Access to Document

10.1007/s00542-019-04654-2

Cite this

@article{e09f4becbc7043c9a51fddbf6e9065ff,

title = "Convolutional denoising autoencoder based SSVEP signal enhancement to SSVEP-based BCIs",

abstract = "For steady state visually evoked potential (SSVEP) based brain computer interfaces (BCIs), the elicited SSVEP signals always contain noises and then the performance of SSVEP-based BCIs would be greatly degraded in practical applications. Therefore, to develop an SSVEP signal enhancement would be able to increase the accuracy of SSVEP-based BCIs. In this study, a convolutional denoising autoencoder based SSVEP signal enhancement is proposed to suppress the noise components. The convolutional denoising autoencoder is applied to estimate and suppress the noise components. To effectively estimate the noise components, a sinusoid wave is designed as an ideal SSVEP signal. To ignore the effects of phase, cross correlation is adopted to estimate the phase in the training stage. The experimental results evaluated by using signal-to-noise ratio and canonical correspondence analysis showed that the proposed approaches can effectively suppress the noises components. Therefore, the proposed approach can be applied to develop robust SSVEP-based BCIs.",

author = "Chuang, {Chia Chun} and Lee, {Chien Ching} and Yeng, {Chia Hong} and So, {Edmund Cheung} and Bor-Shyh Lin and Chen, {Yeou Jiunn}",

year = "2019",

month = oct,

day = "14",

doi = "10.1007/s00542-019-04654-2",

language = "English",

pages = "1--8",

journal = "Microsystem Technologies",

issn = "0946-7076",

publisher = "Springer Verlag",

}

TY - JOUR

T1 - Convolutional denoising autoencoder based SSVEP signal enhancement to SSVEP-based BCIs

AU - Chuang, Chia Chun

AU - Lee, Chien Ching

AU - Yeng, Chia Hong

AU - So, Edmund Cheung

AU - Lin, Bor-Shyh

AU - Chen, Yeou Jiunn

PY - 2019/10/14

Y1 - 2019/10/14

N2 - For steady state visually evoked potential (SSVEP) based brain computer interfaces (BCIs), the elicited SSVEP signals always contain noises and then the performance of SSVEP-based BCIs would be greatly degraded in practical applications. Therefore, to develop an SSVEP signal enhancement would be able to increase the accuracy of SSVEP-based BCIs. In this study, a convolutional denoising autoencoder based SSVEP signal enhancement is proposed to suppress the noise components. The convolutional denoising autoencoder is applied to estimate and suppress the noise components. To effectively estimate the noise components, a sinusoid wave is designed as an ideal SSVEP signal. To ignore the effects of phase, cross correlation is adopted to estimate the phase in the training stage. The experimental results evaluated by using signal-to-noise ratio and canonical correspondence analysis showed that the proposed approaches can effectively suppress the noises components. Therefore, the proposed approach can be applied to develop robust SSVEP-based BCIs.

AB - For steady state visually evoked potential (SSVEP) based brain computer interfaces (BCIs), the elicited SSVEP signals always contain noises and then the performance of SSVEP-based BCIs would be greatly degraded in practical applications. Therefore, to develop an SSVEP signal enhancement would be able to increase the accuracy of SSVEP-based BCIs. In this study, a convolutional denoising autoencoder based SSVEP signal enhancement is proposed to suppress the noise components. The convolutional denoising autoencoder is applied to estimate and suppress the noise components. To effectively estimate the noise components, a sinusoid wave is designed as an ideal SSVEP signal. To ignore the effects of phase, cross correlation is adopted to estimate the phase in the training stage. The experimental results evaluated by using signal-to-noise ratio and canonical correspondence analysis showed that the proposed approaches can effectively suppress the noises components. Therefore, the proposed approach can be applied to develop robust SSVEP-based BCIs.

UR - http://www.scopus.com/inward/record.url?scp=85076498643&partnerID=8YFLogxK

U2 - 10.1007/s00542-019-04654-2

DO - 10.1007/s00542-019-04654-2

M3 - Article

AN - SCOPUS:85076498643

SN - 0946-7076

SP - 1

EP - 8

JO - Microsystem Technologies

JF - Microsystem Technologies

ER -

Convolutional denoising autoencoder based SSVEP signal enhancement to SSVEP-based BCIs

Abstract

Access to Document

Other files and links

Fingerprint

Cite this