Skip to main content

Table 2 Decoding performance of hand velocity using ICA-cleaned EEG

From: Decoding hand movement velocity from electroencephalogram signals during a drawing task

 

S1

S2

S3

S4

S5

Avg.

CCx

0.62 ± 0.05

0.29 ± 0.03

0.50 ± 0.03

0.29 ± 0.03

0.16 ± 0.01

0.37 ± 0.08

CCy

0.04 ± 0.02

0.17 ± 0.02

0.39 ± 0.03

0.28 ± 0.03

0.30 ± 0.02

0.24 ± 0.06

p x

0

0

0

0

1.84 × 10-9

-

p y

0.08

1.17 × 10-7

0

0

0

-

SNRx(dB)

2.14 ± 0.41

0.30 ± 0.12

1.19 ± 0.13

0.35 ± 0.08

0.09 ± 0.02

0.81 ± 0.38

SNRy(dB)

-0.06 ± 0.03

0.05 ± 0.08

0.66 ± 0.09

0.34 ± 0.06

0.36 ± 0.04

0.27 ± 0.13

  1. Pearson correlation coefficients (CCs), p-values and signal-to-noise ratios (SNRs) between measured and decoded hand velocities in x-dimension and y-dimension are listed. Top group: the mean ± stand error of the mean (SEM) of CCs is given for each subject and dimension across all 5 folds. The average of CCs across subjects is also given. Middle group: the mean of p-values is provided for each subject and dimension across all 5 folds. Button group: the SNRs are recorded for each subject and dimension across all 5 folds. The average of SNRs across subjects is also given. Before computing CC, p-value and SNR, the measured and decoded hand velocities were smoothed with a zero-phase, fourth-order, lowpass Butterworth filter with a cut-off frequency of 1 Hz.
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us