Table 4 The selected features and the obtained classification accuracies by the use of the GA-based method
Training algorithm | Selected features | Classification accuracy (%) |
|---|---|---|
‘trainrp’ | The first, fifth, and eight coefficients of MFCCs | 89.9 |
Energy at the seventh, ninth, 36th, 40th, 42nd, 48th, 49th, 51st, 61st, and 62nd nodes of WP tree | ||
Entropy at the first, seventh, eight, 16th, 27th, 28th, 29th, 37th, 45th, 46th, 53rd, and 61st nodes of WP tree | ||
(Feature vector length = 25) | ||
‘trainscg’ | The first and fifth coefficients of MFCCs | 95.3 |
Energy at the 11th, 17th, 22nd, 25th, 29th, 35th, 40th, 41st, 45th, 46th, 49th, 55th, 61st, and 63rd nodes of WP tree | ||
Entropy at the first, 13th, 15th, 19th, 26th, 35th, 36th, 42nd, 43rd, 44th, 46th, 52nd, 53rd, and 55th nodes of WP tree | ||
(Feature vector length = 30) | ||
‘traingdx’ | The first, third, and fifth coefficients of MFCCs | 93.8 |
Energy at the eight, 20th, 21st, 43rd, 60th, and 62nd node of WP tree | ||
Entropy at the 11th, 13th, 35th, 52nd, 54th, 58th, 59th, and 62nd nodes of WP tree | ||
(Feature vector length = 17) |