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 1 443 145 266 4 28 83.8 98.5 97.3 92.8
1,3,4,5,6,7 4751 2 259 108 148 1 2 98.2 99.3 99.1 98.8
1,2,4,5,6,7 4731 3 279 82 195 1 1 98.8 99.5 98.8 99.3
1,2,3,5,6,7 3372 4 1638 817 793 21 7 99.2 97.4 97.5 98.3
1,2,3,4,6,7 4088 5 922 454 392 60 13 97.2 86.6 88.3 92.1
1,2,3,4,5,7 4466 6 544 231 299 14 0 100 95.5 94.3 97.4
1,2,3,4,5,6 4085 7 925 208 709 7 1 99.5 99.0 96.7 99.1
Overall performance of the 7 layers 1D-CNN in the entire 6 hours
96.83±2.83