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 1 443 166 255 15 7 96.0 94.4 91.7 95.0
1,3,4,5,6,7 4751 2 259 110 149 0 0 100 100 100 100
1,2,4,5,6,7 4731 3 279 81 188 8 2 97.6 95.6 91.0 96.4
1,2,3,5,6,7 3372 4 1638 823 734 80 1 99.9 90.2 91.1 95.1
1,2,3,4,6,7 4088 5 922 452 463 4 3 99.3 99.1 99.1 99.2
1,2,3,4,5,7 4466 6 544 230 306 7 1 99.6 97.8 97.0 98.5
1,2,3,4,5,6 4085 7 925 207 715 1 2 99.0 99.9 99.5 99.7
Overall performance of the 5 layers WS-CNN in the entire 6 hours 97.70±1.99