Table 6 Classification confusion matrix for results with LOSO CV on the IMBALANCED data set using top 15 DTCWT features and three clinical features. The overall per-subject classification accuracy achieved is 63.48%
From: Classification of lung pathologies in neonates using dual-tree complex wavelet transform
| Â | Â | Predicted class | |||||
|---|---|---|---|---|---|---|---|
| Â | Â | Normal (%) | CLD (%) | CON (%) | PTX (%) | RDS (%) | TTN (%) |
True Class | Normal | 4.86 | 0 | 0 | 11.89 | 0 | 83.24 |
CLD | 0 | 100 | 0 | 0 | 0 | 0 | |
CON | 0 | 0 | 96.39 | 0 | 3.61 | 0 | |
PTX | 23.81 | 0 | 15.24 | 3.81 | 22.86 | 34.29 | |
RDS | 5.71 | 0 | 17.96 | 6.12 | 39.59 | 30.61 | |
TTN | 13.96 | 0 | 0 | 5.09 | 5.47 | 75.47 | |