| Prediction method |
Reference |
tp |
fn |
fp |
tn |
MCC |
ACC(%) |
| Expectation Maximization and Support Vector Machine(EMSVM) |
This paper |
52 |
1 |
0 |
53 |
0.98 |
99.05 |
| Knowledge Based Neural Network(KBANN) |
Geoffrey G. Towel1 et al.
(1990)
|
- |
- |
- |
- |
- |
96.22 |
| Multilayer Perceptron |
- |
- |
- |
- |
- |
92.45 |
| OťNeill’s Method |
- |
- |
- |
- |
- |
88.68 |
| K-Nearest Neighbors(k-NN) |
- |
- |
- |
- |
- |
87.74 |
| Decision Tree (ID3) |
- |
- |
- |
- |
- |
82.08 |
| Hidden Markov Model(HMM) |
Leonardo G. Tavares et al
.(2008)
|
50 |
3 |
5 |
48 |
0.850 |
92.45 |
| Complement Class Naive Bayes(CNB) |
49 |
4 |
3 |
50 |
0.868 |
93.40 |
| Multilayer Perceptron Neural Network(MLP) |
49 |
4 |
3 |
50 |
0.968 |
93.40 |
| Support Vector Machine(SVM) |
49 |
4 |
4 |
49 |
0.849 |
92.45 |
| LogitBoost |
47 |
6 |
5 |
48 |
0.793 |
89.62 |
| NBTree |
47 |
6 |
5 |
48 |
0.793 |
89.62 |
| Lazy Bayesian Rules Classifier(LBR) |
48 |
5 |
3 |
50 |
0.850 |
92.45 |
| PART |
44 |
9 |
11 |
42 |
0.623 |
81.13 |
| ANN trained with backpropagation |
Raúl Ramos-Pollán et al.
(2012)
|
- |
- |
- |
- |
- |
89.09 |
| ANN trained with resilient propagation |
- |
- |
- |
- |
- |
94.36 |
| ANN trained with simulated annealing |
- |
- |
- |
- |
- |
88.50 |
| ANN trained with genetic algorithms |
- |
- |
- |
- |
- |
73.37 |
