Research Article
Hepatitis Disease Diagnosis Using Hybrid Case Based Reasoning and Particle Swarm Optimization
Table 1
Classification accuracies for hepatitis disease classification problem.
| Authors | Method | Classification accuracy (%) | Reference |
| | Weighted 9 NN | 92.9 | |
Duch and Grudzinski | 18 NN, stand, manhattan | 90.2 | [19] | | 15 NN, stand, Euclidean | 89.0 | |
| | FSM with rotational | 89.7 | |
Duch et al. | FSM without rotational | 88.5 | [20] | | RBF(tooldiag) | 79 | | | MLPBP(tooldiag) | 77.4 | |
| | LDA | 86.4 | | | Naïve Bayes and semi NB | 86.3 | | | QAD | 85.8 | | | 1-NN | 85.3 | | | ASR | 85 | |
Ster and Dobnikar | Fisher discriminant analysis | 84.5 | [21] | | LVQ | 83.2 | | | CART(decision tree) | 82.7 | | | MLP with BP | 82.1 | | | ASI | 82.0 | | | LFC | 81.9 | |
|
Jankowski | IncNET | 86.0 | [22] |
| | MLP | 74.37 | |
Ozyilmaz and Yildirim | RBF | 83.75 | [23] | | GRNN | 80.0 | |
|
Bascil and Temurtas | MLNN with Levenberg Marquardt | 91.87 | [24] |
|
|