Feature Version | No. Calls | TP0 | FN | TP | FP | Precision | Recall |
---|
Features15 | 1468 | 168 | 70 | 478 | 990 | 32.56% | 70.59% |
Features8 | 1386 | 170 | 68 | 479 | 907 | 34.56% | 71.43% |
InvBFM | 1379 | 170 | 68 | 479 | 900 | 34.73% | 71.43% |
- Features15 means the first 15 features are extracted, Features8 means selecting 8 numeral features by the chi-square test from Features15, InvBFM means the union of Features8 and 2 features that lead to better results in practice. No.Calls: detected inversion count. TP true positive, TP0 remove repeats of TP, FP false positive, FN false negative. The kernel of SVM is linear, with the penalty factor of 0.1 and the gamma of 20