Skip to main content

Table 2 Comparison of all accuracies of all features using multiple learning algorithms derived through WEKA (ver 3.8) with additional 3 new features increasing accuracy of the model

From: A model to predict the function of hypothetical proteins through a nine-point classification scoring schema

Learning algorithms Accuracy with all 9 features Average accuracy Accuracy with all 6 features
trees_j48 97.00 95.85 67.57
trees_DecisionStump 86.33 45.95
trees_RandomForest 98.00 70.27
trees_REPTree 98.00 43.24
HoeffdingTree 96.67 Not reported
trees_LMT 98.33 70.27
trees_RandomTree 96.67 67.57
functions_smo_PolyK 98.33 96.33 78.38
functions_smo_RBFK 93.00 24.32
functions_smo_npolyk 96.67 59.46
functions_smo_Puk 97.33 Not reported
functions_RBFNetwork 96.67 97.11 48.65
functions_mlp 97.67 81.08
functions_VotedPerceptron 97.00 Not reported
bayes_nbay 96.67 94.83 54.05
bayes_NaiveBayesUpdateable 96.67 55.21
bayes_NaiveBayesMultinomial 93.00 Not reported
bayes_NaiveBayesMultinomialUpdateable 93.00 Not reported