Table 3 Confusion matrices and average recognition rates of spectrogram feature based on STL TSB-HMMs and MTL TSB-HMMs with 2 training samples and 128 training samples per target-aspect frame
From: Multi-task hidden Markov modeling of spectrogram feature from radar high-resolution range profiles
| Â | STL TSB-HMMs | MTL TSB-HMMs | ||||
|---|---|---|---|---|---|---|
| Â | An-26 | Cessna Citation S/II | Yark-42 | An-26 | Cessna Citation S/II | Yark-42 |
2 × 135 training samples | ||||||
An-26 | 81.0 | 87.0 | 14.1 | 86.3 | 1.3 | 4.9 |
Cessna citation S/II | 8.0 | 3.5 | 12.2 | 12.2 | 88.0 | 5.4 |
Yark-42 | 11.0 | 9.5 | 73.7 | 1.5 | 10.7 | 89.7 |
Average recognition rates (%) | 52.7 | 88.0 | ||||
128*135 training samples | ||||||
An-26 | 93.8 | 0.7 | 2.5 | 95.8 | 0.4 | 1.9 |
Cessna citation S/II | 4.4 | 88.3 | 1.1 | 3.5 | 92.3 | 0.8 |
Yark-42 | 1.8 | 11.0 | 96.4 | 0.7 | 7.3 | 97.3 |
Average recognition rates (%) | 92.8 | 95.1 | ||||