Research Article
Classification of Electroencephalogram Signal for Developing Brain-Computer Interface Using Bioinspired Machine Learning Approach
Table 2
Performances of subjects of the age group 29–40 using the AR Yule-Walker features with FFNNCSA.
| Subjects | Average training time for ten trials (sec) | Average testing time for ten trials (sec) | Average classification performance (%) | Sd | Max | Min | Mean |
| S11 | 19.65 | 0.79 | 1.73 | 94.16 | 88.58 | 93.90 | S12 | 19.74 | 0.78 | 1.70 | 93.51 | 87.65 | 93.16 | S13 | 19.58 | 0.76 | 1.75 | 94.89 | 89.82 | 93.32 | S14 | 19.42 | 0.77 | 1.77 | 94.69 | 88.94 | 93.62 | S15 | 19.68 | 0.72 | 1.66 | 94.22 | 89.24 | 93.21 | S16 | 19.36 | 0.73 | 1.69 | 94.30 | 88.74 | 93.48 | S17 | 19.47 | 0.75 | 1.68 | 95.10 | 88.56 | 93.77 | S18 | 19.74 | 0.81 | 1.73 | 94.68 | 88.80 | 93.60 | S19 | 19.78 | 0.80 | 1.72 | 94.56 | 89.25 | 93.95 | S20 | 19.12 | 0.74 | 1.62 | 95.78 | 90.18 | 95.00 |
|
|