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 1 443 118 270 0 55 68.2 100 100 87.6
1,3,4,5,6,7 4751 2 259 106 149 0 4 96.4 100 100 98.5
1,2,4,5,6,7 4731 3 279 79 191 5 4 95.2 97.4 94.0 96.8
1,2,3,5,6,7 3372 4 1638 728 814 0 96 88.3 100 100 94.1
1,2,3,4,6,7 4088 5 922 431 455 0 36 92.3 100 100 96.1
1,2,3,4,5,7 4466 6 544 228 311 2 3 98.7 99.4 99.1 99.1
1,2,3,4,5,6 4085 7 925 203 711 5 6 97.1 99.3 97.6 98.8
Overall performance of the 5 layers 1D-CNN in the entire 6 hours 95.86±3.74