Research Article
Determination of Fetal State from Cardiotocogram Using LS-SVM with Particle Swarm Optimization and Binary Decision Tree
Table 4
Comparison of LS-SVM-PSO-BDT with the existing methods in similar works.
| Method | Maximum classification accuracy | Number of classes | Number of data points |
| LS-SVM-PSO-BDT | 91.62% | 3 | 2162 |
| SVM Krupa et al., 2011 [8] | 81.50% | 2 | 129 |
| SVM Georgoulas et al., 2006 [4] | 81.25% | 2 | 80 |
| Hidden Markov models Georgoulas et al., 2004 [6] | 83.00% | 2 | 36 |
| ANBLIR system Czabanski et al., 2010 [7] | 97.50% | 2 | 685 |
| ANFIS Ocak and Ertunc, 2012 [9] | 97.15% | 2 | 1831 |
| SVM and GA Ocak, 2013 [10] | 99.30% (specificity) 100% (sensitivity) | 2 | 1831 |
|
|