Table S2. Results of the WS-CNN classifier for post-HI spike transient identification in experimental data (entire 6 hours – 9 layers)
Trained and validated on Sheep No. | No. of patterns in the Train and Validation Dataset | Tested on Sheep No. | No. of patterns in the Test-set | TP hits | TN hits | FP hits | FN hits | Sensitivity [%] | Selectivity [%] | Precision [%] | Accuracy [%] |
2,3,4,5,6,7 | 4567 | 1 | 443 | 154 | 268 | 2 | 19 | 89.0 | 99.3 | 98.7 | 95.3 |
1,3,4,5,6,7 | 4751 | 2 | 259 | 109 | 149 | 0 | 1 | 99.1 | 100 | 100 | 99.6 |
1,2,4,5,6,7 | 4731 | 3 | 279 | 81 | 195 | 1 | 2 | 97.6 | 99.5 | 98.8 | 98.9 |
1,2,3,5,6,7 | 3372 | 4 | 1638 | 820 | 783 | 31 | 4 | 99.5 | 96.2 | 96.4 | 97.9 |
1,2,3,4,6,7 | 4088 | 5 | 922 | 449 | 467 | 0 | 6 | 98.7 | 100 | 100 | 99.3 |
1,2,3,4,5,7 | 4466 | 6 | 544 | 231 | 308 | 5 | 0 | 100 | 98.4 | 97.9 | 99.1 |
1,2,3,4,5,6 | 4085 | 7 | 925 | 206 | 716 | 0 | 3 | 98.6 | 100 | 100 | 99.7 |
Overall performance of the 9 layers WS-CNN in the entire 6 hours | 98.54±1.43 |