Table 2: LOOCV success rates by covariant discriminant, neural network, SVM, bagging, and improved 3D kernel approach.

AlgorithmRate of correct prediction for each class Overall rate of correct prediction
Type AType BType CType DType E

Covariant discriminant74.0%52.0%83.7%49%45.4%76.4%
Neural network75.63%30.92%88.86%50.98%30.91%77.76%
SVMs77.7%28.3%92.5%52.9%35.5%80.9%
Bagging79.80%48.68%93.21%49.02%60.91%84.18%
3D kernel78.11%31.02%94.36%52.63%45.46%84.50%