Trained and validated on Sheep No. No. of patterns in the train 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 1 443 173 266 4 2 100 98.5 98.7 99.1
1,3,4,5,6,7 4751 2 259 110 146 3 0 100 98.0 97.3 98.8
1,2,4,5,6,7 4731 3 279 83 194 2 0 100 99.0 97.6 99.3
1,2,3,5,6,7 3372 4 1638 823 803 11 1 99.9 98.6 98.7 99.3
1,2,3,4,6,7 4088 5 922 454 454 1 13 97.2 99.8 99.8 98.5
1,2,3,4,5,7 4466 6 544 231 313 0 0 100 100 100 100
1,2,3,4,5,6 4085 7 925 208 716 0 1 99.5 100 100 99.9
Overall performance of the 11-layers 1D-CNN in the entire 6 hours 99.27±0.51
Table S9. Results of the 1D-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 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 1 443 139 270 0 34 80.3 100 100 92.3
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 73 196 0 10 88.0 100 100 96.4
1,2,3,5,6,7 3372 4 1638 822 813 1 2 99.8 99.9 99.9 99.8
1,2,3,4,6,7 4088 5 922 455 454 1 12 97.4 99.8 99.8 98.6
1,2,3,4,5,7 4466 6 544 231 313 0 0 100 100 100 100
1,2,3,4,5,6 4085 7 925 209 714 2 0 100 99.7 99.1 99.8
Overall performance of the 9 layers 1D-CNN in the entire 6 hours
98.07±2.63