Table 2.
Numbers of incorrect assignment (Mean (SE) over 50 replications) in different breeds by different machine learning methods with reference population size of 30 individuals per breed and 2,000 most breed-informative SNPs revealed by DFI
| Breed | No anim | Machine learning | ||||
|---|---|---|---|---|---|---|
| ANN | KNN | NB | RF | SVM | ||
| NMD | 1 | 0.10 (0.10) | 0.00 | 0.00 | 0.00 | 0.00 |
| YKT | 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| GEL | 3 | 0.20 (0.05) | 0.00 | 0.00 | 0.00 | 0.00 |
| LIM | 9 | 0.30 (0.07) | 0.00 | 0.00 | 0.00 | 0.00 |
| MBL | 25 | 0.30 (0.13) | 0.00 | 0.00 | 0.00 | 0.00 |
| HF | 37 | 0.40 (0.17) | 0.00 | 0.00 | 0.00 | 0.00 |
| NWR | 48 | 1.40 (0.16) | 0.00 | 0.00 | 0.00 | 0.00 |
| CHA | 42 | 1.80 (0.23) | 0.00 | 0.00 | 0.04 (0.03) | 0.00 |
| SIM | 53 | 3.60 (0.44) | 1.00 (0.00) | 1.00 (0.00) | 0.06 (0.03) | 0.00 |
| BS | 90 | 6.20 (0.30) | 0.00 | 13.00 (0.00) | 4.00 (0.17) | 12.00 (0.00) |
| JER | 97 | 0.20 (0.06) | 0.00 | 0.00 | 0.00 | 0.00 |
| ANG | 129 | 0.80 (0.17) | 0.00 | 2.00 (0.00) | 1.02 (0.02) | 1.00 (0.00) |
| HOL | 170 | 3.10 (0.32) | 0.00 | 1.00 (0.00) | 0.24 (0.06) | 0.00 |
| Total | 705 | 18.40 (0.49) | 1.00 (0.00) | 17.00 (0.00) | 5.36 (0.18) | 13.00 (0.00) |
ANN Artificial Neural Network, KNN K-Nearest Neighbor, NB Naive Bayes, RF Random Forest, SVM Support Vector Machine