Analysis and Classification of Motor Imagery Using Deep Neural Network

Authors

  • Isah Salim Ahmad State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China
  • Shuai Zhang State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China https://orcid.org/0000-0002-0403-6276 (unauthenticated)
  • Sani Saminu Hebei University of Technology, Biomedical Engineering Department, University of Ilorin-Nigeria. https://orcid.org/0000-0002-5182-7150 (unauthenticated)
  • Isselmou Abd El Kader State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China https://orcid.org/0000-0002-9959-8932 (unauthenticated)
  • Jamil maaruf musa Department of Computer Science and Technology, School of Artificial Intelligence. Hebei University of Technology, Tianjin 300401, China
  • Imran Javid State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China
  • Souha Kamhi State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China
  • Ummay Kulsum State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

DOI:

https://doi.org/10.31258/Jamt.2.2.85-93

Keywords:

BCI, EEG, Motor imagery (MI), CSP, Gradient Descent Method with Momentum and Adaptive Learning Rate (GDMLR), DNN

Abstract

Motor imagery based on brain-computer interface (BCI) has attracted important research attention despite its difficulty. It plays a vital role in human cognition and helps in making the decision. Many researchers use electroencephalogram (EEG) signals to study brain activity with left and right-hand movement. Deep learning (DL) has been employed for motor imagery (MI). In this article, a deep neural network (DNN) is proposed for classification of left and right movement of EEG signal using Common Spatial Pattern (CSP) as feature extraction with standard gradient descent (GD) with momentum and adaptive learning rate LR. (GDMLR), the performance is compared using a confusion matrix, the average classification accuracy is   87%, which is improved as compared with state-of-the-art methods that used different datasets.

Downloads

Download data is not yet available.

Author Biographies

  • Shuai Zhang, State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

    Professor,

    Vice Dean of the College of Electrical Engineering, Hebei University of Technology.Dr. Zhang received his Bachelor degree from the College of Electrical Engineering at Southwest Jiaotong University (China) at 2007. Afterwards, he started joint doctoral study and received PhD degrees from both the Department of Applied Physics in Ghent University (Belgium) at 2012, and the College of Electrical & Electronic Engineering in Huazhong University of Science & Technology (China) at 2013, in the field of plasma discharges.

    In 2013 he joined the Chongqing University (China) as a researcher supported by the Hundred Talents Program. He is also a research member in the State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University. From November 2013 to July 2014, he was a visiting scholar in the Cold Plasma Diagnostics and Application Lab. at the Department of Mechanical Engineering, University of Minnesota (Twin Cities Campus), USA. His research interests include atmospheric pressure plasma discharges, advanced optical diagnostics, plasma interactions with liquids and solids, and novel applications of plasma discharges in energy and material science. He has been co-authored more than 60 publications, and since 2015 the total citations of his work have achieved to 1596 with h-idex 22 and i10-idex 36 by Google Scholar

  • Sani Saminu, Hebei University of Technology, Biomedical Engineering Department, University of Ilorin-Nigeria.

    SANI SAMINU was born in Kano State, Nigeria. He received his B.Eng. degree in Electrical and Electronics Engineering from Kano University of Science and Technology Wudil, Kano, Nigeria. He obtained M.Sc. in Electrical and Electronics Engineering from Yasar University Izmir, Turkey.

    He has been working with Biomedical Engineering Department, University of Ilorin, Nigeria. He is currently a PhD candidate at School of Electrical Engineering, Hebei University of Technology Tianjin, China.

    His research interests are in signal processing, Wireless/Sensor communication and networks and instrumentation, in particular applied to biomedical applications.

  • Isselmou Abd El Kader, State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

       ISSELMOU ABD EL KADER received the B.S. degree from the School of Science, University Technology of Malaysia, Juhar, Malaysia, in 2013 and the M.S degree in biomedical engineering from Hebei University of Technology, Tianjin, China in 2017. He is currently Ph. D candidate with the State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China. He has published 13 papers indexing SCI and EI. His research interests include medical image processing, and machine learning.

     

  • Jamil maaruf musa, Department of Computer Science and Technology, School of Artificial Intelligence. Hebei University of Technology, Tianjin 300401, China

    jamilu maaaruf musa was born in Kano state, Nigeria. He received his Bsc. degree in Computer scienceAhmADU bELLO University, Zaria Nigeria. In 2015. He is currently Masters’ student at Deapartment of computer science Hebei University of Technology, Tianjin, China. His research interest includes a brain-computer interface (BCI) and Machine learning.

     

  • Imran Javid, State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

    IMRAN JAVID received his B.S from University of Peshawar, Pakistan (1st Division). Currently, He is master study (Biomedical engineering) with the State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China. He has 5 publications. His research interests include medical image processing, and machine learning

  • Souha Kamhi, State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

    SOUHA KAMHI received her bachelor degree from University Mohamed 6th of Health sciences, Casablanca, Morocco. Currently, she is master student with the State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China. Her current research interests include biomedical signal processing and brain–computer interfacing

  • Ummay Kulsum, State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology Tianjin 300130, China

    UMMAY KULSUM, Received her bachelor degree from Gono University, Dhaka, Bangladesh. Currently, she is master student with the State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China. Her current research interests include Electrical impedance tomography

Downloads

Published

2021-06-25

Issue

Vol. 2 No. 2 (2021): March 2021

Section

Articles

License

Copyright (c) 2021 Isah Salim Ahmad, Shuai Zhang, Sani Saminu, Isselmou Abd El Kader, Jamil maaruf musa; Imran Javid, Souha Kamhi, Ummay Kulsum

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Analysis and Classification of Motor Imagery Using Deep Neural Network. (2021). Journal of Applied Materials and Technology, 2(2), 85-93. https://doi.org/10.31258/Jamt.2.2.85-93