Motor Imagery Recognition of Upper Limb Single Joint Based on BCI Technology

In the study of brain-computer interface (BCI) technology, it is difficult to distinguish and recognize electroencephalogram (EEG) signals induced by motor imagery in different movements of the same joint. In order to improve the recognition rate of upper limb shoulder dichotomous motion imagination by BCI system, 50Hz notch filter and de-baseline drift processing are used to remove power frequency interference, and common average reference (CAR) method is used to preprocess the collected EEG data. Secondly, EEG data collected from four electrode channels, FC5, F3, F4 and FC6, are extracted by common spatial pattern (CSP). Finally, the twin support vector machine (TWSVM) is used to recognize the motion imagination state. The experimental results show that the recognition accuracy of upper limb shoulder motion imagination reaches 85.29%. Compared with other methods, the recognition rate is higher.

[1]  G. Pfurtscheller,et al.  Graz brain-computer interface II: towards communication between humans and computers based on online classification of three different EEG patterns , 1996, Medical and Biological Engineering and Computing.

[2]  Cuntai Guan,et al.  Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms , 2011, IEEE Transactions on Biomedical Engineering.

[3]  Shifei Ding,et al.  An overview on twin support vector machines , 2012, Artificial Intelligence Review.

[4]  Reshma Khemchandani,et al.  Twin Support Vector Machines for Pattern Classification , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[6]  Siamac Fazli,et al.  Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI , 2015, Pattern Recognit..

[7]  Chiew Tong Lau,et al.  A New Discriminative Common Spatial Pattern Method for Motor Imagery Brain–Computer Interfaces , 2009, IEEE Transactions on Biomedical Engineering.

[8]  J R Wolpaw,et al.  Spatial filter selection for EEG-based communication. , 1997, Electroencephalography and clinical neurophysiology.

[9]  J. Wolpaw,et al.  Multichannel EEG-based brain-computer communication. , 1994, Electroencephalography and clinical neurophysiology.

[10]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.