Data Set I: Motor imagery in ECoG recordings, Session-to-session transfer

         

Group information:

       Department of Biomedical Engieering,

       Tsinghua University

       Beijing, 100084, P.R.China

       Team director: Xiaorong GAO (gxr-dea@tsinghua.edu.cn)

       Team member: Qingguo Wei, Fei Meng, Yijun Wang

       Team supervisor: Shangkai GAO

 

Predicted labels: (listed also in TSINGHUA_dataset1_testlabels.mat)

test trials

predicted  labels

1~10

1

1

-1

-1

-1

-1

-1

-1

1

-1

11~20

1

1

1

-1

1

1

-1

-1

1

1

21~30

1

-1

-1

1

1

-1

1

1

-1

1

31~40

1

-1

1

-1

1

-1

1

1

1

1

41~50

1

-1

1

-1

1

-1

-1

1

1

-1

51~60

-1

1

1

-1

-1

-1

1

-1

-1

-1

61~70

1

-1

-1

-1

1

-1

1

-1

1

-1

71~80

1

-1

1

-1

-1

1

1

1

1

1

81~90

-1

1

-1

1

1

-1

-1

-1

-1

-1

91~100

-1

-1

1

-1

-1

-1

-1

1

1

1

 

 

 

 

 

 

 

 

 

 

 

 

 

Processing technique:

     Three features are combined to perform classification task. Two of them are extracted by common spatial subspace decomposition (CSSD) and Fisher discriminant analysis (FDA), and another feature is derived from waveform mean (WM) and FDA. The classifier is support vector machines (SVM).