The classification of EEG-based wink signals: A CWT-Transfer Learning pipeline

Jothi Letchumy Mahendra Kumar; Mamunur Rashid; Rabiu Muazu Musa; Mohd Azraai Mohd Razman; Norizam Sulaiman; Rozita Jailani; Anwar P.P. Abdul Majeed

doi:10.1016/j.icte.2021.01.004

The classification of EEG-based wink signals: A CWT-Transfer Learning pipeline

Jothi Letchumy Mahendra Kumar
, Mamunur Rashid
, Rabiu Muazu Musa
, Mohd Azraai Mohd Razman
, Norizam Sulaiman
, Rozita Jailani
, Anwar P.P. Abdul Majeed^*

^*Corresponding author for this work

Universiti Malaysia Pahang Al-Sultan Abdullah
Universiti Malaysia Terengganu
Universiti Teknologi MARA
Innovative Manufacturing
Centre for Software Development & Integrated Computing

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

37 Citations (Scopus)

Abstract

Brain–Computer Interface technology plays a vital role in facilitating post-stroke patients’ ability to carry out their daily activities of living. The extraction of features and the classification of electroencephalogram (EEG) signals are pertinent parts in enabling such a system. This research investigates the efficacy of Transfer Learning models namely ResNet50 V2, ResNet101 V2, and ResNet152 V2 in extracting features from CWT converted wink-based EEG signals, prior to its classification via a fine-tuned Support Vector Machine (SVM) classifier. It was shown that ResNet152 V2-SVM pipeline could achieve an excellent accuracy on all train, test and validation datasets.

Original language	English
Pages (from-to)	421-425
Number of pages	5
Journal	ICT Express
Volume	7
Issue number	4
DOIs	https://doi.org/10.1016/j.icte.2021.01.004
Publication status	Published - Dec 2021
Externally published	Yes

Keywords

BCI
CWT
EEG
SVM
Transfer Learning

Access to Document

10.1016/j.icte.2021.01.004

Cite this

@article{7aa17accfd684beca9f43dba524e5cfd,

title = "The classification of EEG-based wink signals: A CWT-Transfer Learning pipeline",

abstract = "Brain–Computer Interface technology plays a vital role in facilitating post-stroke patients{\textquoteright} ability to carry out their daily activities of living. The extraction of features and the classification of electroencephalogram (EEG) signals are pertinent parts in enabling such a system. This research investigates the efficacy of Transfer Learning models namely ResNet50 V2, ResNet101 V2, and ResNet152 V2 in extracting features from CWT converted wink-based EEG signals, prior to its classification via a fine-tuned Support Vector Machine (SVM) classifier. It was shown that ResNet152 V2-SVM pipeline could achieve an excellent accuracy on all train, test and validation datasets.",

keywords = "BCI, CWT, EEG, SVM, Transfer Learning",

author = "\{Mahendra Kumar\}, \{Jothi Letchumy\} and Mamunur Rashid and Musa, \{Rabiu Muazu\} and \{Mohd Razman\}, \{Mohd Azraai\} and Norizam Sulaiman and Rozita Jailani and \{P.P. Abdul Majeed\}, Anwar",

note = "Funding Information: This study is funded by Universiti Malaysia Pahang via RDU180321. Publisher Copyright: {\textcopyright} 2021 The Korean Institute of Communications and Information Sciences (KICS)",

year = "2021",

month = dec,

doi = "10.1016/j.icte.2021.01.004",

language = "English",

volume = "7",

pages = "421--425",

journal = "ICT Express",

issn = "2405-9595",

number = "4",

}

TY - JOUR

T1 - The classification of EEG-based wink signals

T2 - A CWT-Transfer Learning pipeline

AU - Mahendra Kumar, Jothi Letchumy

AU - Rashid, Mamunur

AU - Musa, Rabiu Muazu

AU - Mohd Razman, Mohd Azraai

AU - Sulaiman, Norizam

AU - Jailani, Rozita

AU - P.P. Abdul Majeed, Anwar

PY - 2021/12

Y1 - 2021/12

N2 - Brain–Computer Interface technology plays a vital role in facilitating post-stroke patients’ ability to carry out their daily activities of living. The extraction of features and the classification of electroencephalogram (EEG) signals are pertinent parts in enabling such a system. This research investigates the efficacy of Transfer Learning models namely ResNet50 V2, ResNet101 V2, and ResNet152 V2 in extracting features from CWT converted wink-based EEG signals, prior to its classification via a fine-tuned Support Vector Machine (SVM) classifier. It was shown that ResNet152 V2-SVM pipeline could achieve an excellent accuracy on all train, test and validation datasets.

AB - Brain–Computer Interface technology plays a vital role in facilitating post-stroke patients’ ability to carry out their daily activities of living. The extraction of features and the classification of electroencephalogram (EEG) signals are pertinent parts in enabling such a system. This research investigates the efficacy of Transfer Learning models namely ResNet50 V2, ResNet101 V2, and ResNet152 V2 in extracting features from CWT converted wink-based EEG signals, prior to its classification via a fine-tuned Support Vector Machine (SVM) classifier. It was shown that ResNet152 V2-SVM pipeline could achieve an excellent accuracy on all train, test and validation datasets.

KW - BCI

KW - CWT

KW - EEG

KW - SVM

KW - Transfer Learning

UR - https://www.scopus.com/pages/publications/85100054065

U2 - 10.1016/j.icte.2021.01.004

DO - 10.1016/j.icte.2021.01.004

M3 - Article

AN - SCOPUS:85100054065

SN - 2405-9595

VL - 7

SP - 421

EP - 425

JO - ICT Express

JF - ICT Express

IS - 4

ER -

The classification of EEG-based wink signals: A CWT-Transfer Learning pipeline

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this