Table 2 Results of the proposed algorithm with 720 hidden neurons and 14 components
From: Robust algorithm for arrhythmia classification in ECG using extreme learning machine
Results from Proposed Algorithm | Actual heart beat type | ||||||
|---|---|---|---|---|---|---|---|
| Â | Nor | LBBB | RBBB | PVC | APB | PB | Total |
Normal | 53885 | 90 | 35 | 276 | 188 | 1 | 54475 |
LBBB | 83 | 5922 | 2 | 64 | 5 | 0 | 6076 |
RBBB | 65 | 1 | 5356 | 29 | 5 | 0 | 5456 |
PVC | 104 | 16 | 1 | 4783 | 6 | 0 | 4910 |
APB | 379 | 7 | 16 | 141 | 1692 | 1 | 2236 |
PB | 0 | 0 | 0 | 0 | 0 | 2700 | 2700 |
Total | 54516 | 6036 | 5410 | 5293 | 1896 | 2702 | 75853 |
Accuracy, Sensitivity, Specificity (%) | |||||||
Beat types | Nor | LBBB | RBBB | PVC | APB | PB | Avg. |
sensitivity | 98.84 | 98.11 | 99.00 | 90.36 | 89.24 | 99.93 | 98.00 |
specificity | 97.23 | 99.78 | 99.86 | 99.82 | 99.26 | 100.00 | 97.95 |
accuracy | 98.39 | 99.65 | 99.80 | 99.16 | 99.01 | 100.00 | 98.72 |