+1 Recommend
1 collections
      • Record: found
      • Abstract: found
      • Article: found

      Boosting the Information Transfer Rate of an SSVEP-BCI System Using Maximal-Phase-Locking Value and Minimal-Distance Spatial Filter Banks

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          For Brain-Computer Interface (BCI) systems, improving the Information Transfer Rate (ITR) is a very critical issue. This study focuses on a Steady-State Visually Evoked Potential (SSVEP)-based BCI because of its advantage of high ITR. Unsupervised Canonical Correlation Analysis (CCA)-based method has been widely employed because of its high efficiency and easy implementation. In a recent study, an ensemble-CCA method based on individual training data was proposed and achieved an excellent performance with ITR of 267 bit/min. A 40-target SSVEP-BCI speller was investigated in this study, using an integration of Minimal-Distance (MD) and Maximal-Phase-locking value (MP) approaches. In the MD approach, a spatial filter is developed to minimize the distance between the training data and the reference sine signal, and in this study, two different types of distance were compared. In the MP approach, a spatial filter is developed to maximize the Phase-Locking Value (PLV) between the training calibration data and the reference sine signal. In addition to the fundamental frequency of stimulation, the harmonics were used to train MD and MP spatial filters, which formed spatial filter banks. The test data epoch was multiplied by the MP and MD spatial filter banks, and the distances and PLVs were extracted as features for recognition. Across 12 subjects with a 0.4 s-data length, the proposed method realized an average classification accuracy and ITR of 93% and 307 bit/min, respectively, which is significantly higher than the current state-of-the-art method. To the best of our knowledge, these results suggest that the proposed method has achieved the highest ITR in SSVEP-BCI studies.

          Related collections

          Author and article information

          Tsinghua Science and Technology
          Tsinghua University Press (Xueyan Building, Tsinghua University, Beijing 100084, China )
          05 June 2019
          : 24
          : 3
          : 262-270
          ∙ Ke Lin, Shangkai Gao, and Xiaorong Gao are with the Department of Biomedical Engineering, Tsinghua University, Beijing 100084, China. E-mail: lincoln1128@ 123456gmail.com ; gsk-dea@ 123456tsinghua.edu.cn .
          Author notes
          * To whom correspondence should be addressed. E-mail: gxr-dea@ 123456tsinghua.edu.cn ;

          Ke Lin received the BE degree from Nanjing University in 2012, and the PhD degree from Tsinghua University in 2017. His research interests focus on brain-computer interface, biomedical signal processing, and machine learning.

          Xiaorong Gao received the BS degree from Zhejiang University in 1986, MS degree from Peking Union Medical College in 1989, and PhD degree from Tsinghua University in 1992. He is currently a professor of the Department of Biomedical Engineering, Tsinghua University. His current research interests are biomedical signal processing and medical instrumentation, especially the study of brain-computer interface.

          Shangkai Gao graduated from Tsinghua University, Beijing, China, in 1970, and received the MEng degree in 1982 from Tsinghua University. She is now a professor of the Department of Biomedical Engineering in Tsinghua University. Her research interests include neural engineering and medical imaging, especially the study of brain-computer interface. She is now on the editorial board member of Journal of Neural Engineering and Physiological Measurement. She is a fellow of American Institute for Medical and Biological Engineering (AIMBE). She is now on the editorial board member of IEEE Transactions on Biomedical Engineering, as well as the senior editor of IEEE Transactions on Neural System and Rehabilitation Engineering.



          Comment on this article