Research Article
Software Defect Prediction via Attention-Based Recurrent Neural Network
Table 5
F1-measure comparison of different models.
| Project | DP-ARNN | RF | RBM + RF | DBN + RF | CNN | RNN |
| Camel | 0.515 | 0.396 | 0.310 | 0.330 | 0.473 | 0.506 | Lucene | 0.721 | 0.604 | 0.600 | 0.623 | 0.711 | 0.672 | Poi | 0.764 | 0.669 | 0.639 | 0.652 | 0.734 | 0.722 | Xerces | 0.270 | 0.185 | 0.128 | 0.167 | 0.243 | 0.262 | Jedit | 0.560 | 0.550 | 0.468 | 0.500 | 0.596 | 0.595 | Xalan | 0.644 | 0.638 | 0.628 | 0.623 | 0.639 | 0.606 | Synapse | 0.477 | 0.414 | 0.303 | 0.360 | 0.424 | 0.487 | W/T/L | | 7/0/0 | 7/0/0 | 7/0/0 | 6/0/1 | 5/0/2 | Average | 0.564 | 0.494 | 0.439 | 0.465 | 0.546 | 0.550 |
|
|