A New Framework for Automatic Detection of Motor and Mental Imagery EEG Signals for Robust BCI Systems

Xiaojun Yu, Muhammad Zulkifal Aziz, Muhammad Tariq Sadiq, Zeming Fan, Gaoxi Xiao

Research output: Contribution to journalArticlepeer-review


Nonstationary signal decomposition (SD) is a primary procedure to extract monotonic components or modes from electroencephalogram (EEG) signals for the development of robust brain-computer interface (BCI) systems. This study proposes a novel automated computerized framework for proficient identification of motor and mental imagery (MeI) EEG tasks by employing empirical Fourier decomposition (EFD) and improved EFD (IEFD) methods. Specifically, the multiscale principal component analysis (MSPCA) is rendered to denoise EEG data first, and then, EFD is utilized to decompose nonstationary EEG into subsequent modes, while the IEFD criterion is proposed for a single conspicuous mode selection. Finally, the time- and frequency-domain features are extracted and classified with a feedforward neural network (FFNN) classifier. Extensive experiments are conducted on four multichannel motor and MeI data sets from BCI competitions II and III using a tenfold cross-validation strategy. Results compared with the other existing methods demonstrated that the highest classification accuracies of 99.82% (data set IV-a), 93.33% (data set IV-b), 91.96% (data set III), and 88.08% (data set V) in subject-specific scenarios, while 82.70% (data set IV-a) in the subject-independent framework are achieved for IEFD with FFNN classifiers collectively. The overall exploratory results authenticate that the proposed IEFD-based automated computerized framework not only outperforms the conventional SD methods but is also robust and computationally efficient for the development of subject-dependent and subject-independent BCI systems.
Original languageEnglish
Article number1006612
Number of pages12
JournalIEEE Transactions on Instrumentation and Measurement
Publication statusPublished - 26 Mar 2021

Bibliographical note

Funding Information:
Manuscript received January 22, 2021; revised March 17, 2021; accepted March 18, 2021. Date of publication March 26, 2021; date of current version April 6, 2021. This work was supported in part by the National Key Research and Development Program of Shaanxi (2021SF-342), Fundamental Research Funds for the Central Universities (G2018KY0308), China Postdoctoral Science Foundation under Grant (2018M641013), Postdoctoral Science Foundation of Shaanxi Province (2018BSHYDZZ05). The Associate Editor coordinating the review process was Adam G. Polak. (Corresponding authors: Xiaojun Yu; Muhammad Tariq Sadiq.) Xiaojun Yu, Muhammad Zulkifal Aziz, Muhammad Tariq Sadiq, and Zeming Fan are with the School of Automation, Northwestern Polytechnical University, Xi’an 710072, China (e-mail: xjyu@nwpu.edu.cn; zulkifalaziz@ mail.nwpu.edu.cn; tariq.sadiq@mail.nwpu.edu.cn; fanzeming@nwpu.edu.cn).

Publisher Copyright:
© 1963-2012 IEEE.


  • Biomedical signal processing
  • brain-computer interface (BCI)
  • computer-Aided diagnosis (CAD)
  • electroencephalography
  • empirical Fourier decomposition (EFD)
  • mental imagery (MeI)
  • motor imagery (MI)


Dive into the research topics of 'A New Framework for Automatic Detection of Motor and Mental Imagery EEG Signals for Robust BCI Systems'. Together they form a unique fingerprint.

Cite this