A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks

Keun Tae Kim; Cuntai Guan; Seong Whan Lee

doi:10.1109/TNSRE.2019.2946625

A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks

Keun Tae Kim, Cuntai Guan, Seong Whan Lee

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

105 Citations (Scopus)

Abstract

In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.

Original language	English
Article number	8865669
Pages (from-to)	94-103
Number of pages	10
Journal	IEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume	28
Issue number	1
DOIs	https://doi.org/10.1109/TNSRE.2019.2946625
Publication status	Published - 2020 Jan

Bibliographical note

Funding Information:
Manuscript received November 7, 2018; revised April 12, 2019, August 22, 2019, and October 1, 2019; accepted October 4, 2019. Date of publication October 11, 2019; date of current version January 8, 2020. This work was supported in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User’s Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning) under Grant 2017-0-00451. (Corresponding author: Seong-Whan Lee.) K.-T. Kim and S.-W. Lee are with the Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]).

Funding Information:
This work was supported in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User's Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User's Intentions using Deep Learning) under Grant 2017-0-00451.

Publisher Copyright:
© 2001-2011 IEEE.

Keywords

Subject-transfer framework
convolutional neural networks
electromyography
myoelectric interfaces

ASJC Scopus subject areas

Internal Medicine
General Neuroscience
Biomedical Engineering

Access to Document

10.1109/TNSRE.2019.2946625

Cite this

@article{5272aa91f5b742458b7c7a8e9f4cdf6e,

title = "A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks",

abstract = "In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.",

keywords = "Subject-transfer framework, convolutional neural networks, electromyography, myoelectric interfaces",

author = "Kim, {Keun Tae} and Cuntai Guan and Lee, {Seong Whan}",

note = "Funding Information: Manuscript received November 7, 2018; revised April 12, 2019, August 22, 2019, and October 1, 2019; accepted October 4, 2019. Date of publication October 11, 2019; date of current version January 8, 2020. This work was supported in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User{\textquoteright}s Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User{\textquoteright}s Intentions using Deep Learning) under Grant 2017-0-00451. (Corresponding author: Seong-Whan Lee.) K.-T. Kim and S.-W. Lee are with the Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]). Funding Information: This work was supported in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User's Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User's Intentions using Deep Learning) under Grant 2017-0-00451. Publisher Copyright: {\textcopyright} 2001-2011 IEEE.",

year = "2020",

month = jan,

doi = "10.1109/TNSRE.2019.2946625",

language = "English",

volume = "28",

pages = "94--103",

journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",

issn = "1534-4320",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks

AU - Kim, Keun Tae

AU - Guan, Cuntai

AU - Lee, Seong Whan

N1 - Funding Information: Manuscript received November 7, 2018; revised April 12, 2019, August 22, 2019, and October 1, 2019; accepted October 4, 2019. Date of publication October 11, 2019; date of current version January 8, 2020. This work was supported in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User’s Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning) under Grant 2017-0-00451. (Corresponding author: Seong-Whan Lee.) K.-T. Kim and S.-W. Lee are with the Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, South Korea (e-mail: [email protected]; [email protected]). Funding Information: This work was supported in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of Non-Invasive Integrated BCI SW Platform to Control Home Appliances and External Devices by User's Thought via AR/VR Interface) under Grant 2017-0-00432 and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (Development of BCI based Brain and Cognitive Computing Technology for Recognizing User's Intentions using Deep Learning) under Grant 2017-0-00451. Publisher Copyright: © 2001-2011 IEEE.

PY - 2020/1

Y1 - 2020/1

N2 - In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.

AB - In recent years, electromyography (EMG)-based practical myoelectric interfaces have been developed to improve the quality of daily life for people with physical disabilities. With these interfaces, it is very important to decode a user's movement intention, to properly control the external devices. However, improving the performance of these interfaces is difficult due to the high variations in the EMG signal patterns caused by intra-user variability. Therefore, this paper proposes a novel subject-transfer framework for decoding hand movements, which is robust in terms of intra-user variability. In the proposed framework, supportive convolutional neural network (CNN) classifiers, which are pre-trained using the EMG data of several subjects, are selected and fine-tuned for the target subject via single-trial analysis. Then, the target subject's hand movements are classified by voting the outputs of the supportive CNN classifiers. The feasibility of the proposed framework is validated with NinaPro databases 2 and 3, which comprise 49 hand movements of 40 healthy and 11 amputee subjects, respectively. The experimental results indicate that, when compared to the self-decoding framework, which uses only the target subject's data, the proposed framework can successfully decode hand movements with improved performance in both healthy and amputee subjects. From the experimental results, the proposed subject-transfer framework can be seen to represent a useful tool for EMG-based practical myoelectric interfaces controlling external devices.

KW - Subject-transfer framework

KW - convolutional neural networks

KW - electromyography

KW - myoelectric interfaces

UR - http://www.scopus.com/inward/record.url?scp=85078358351&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2019.2946625

DO - 10.1109/TNSRE.2019.2946625

M3 - Article

C2 - 31613773

AN - SCOPUS:85078358351

SN - 1534-4320

VL - 28

SP - 94

EP - 103

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

IS - 1

M1 - 8865669

ER -

A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this