Ref. Methods used Evaluation performance metrics Accuracy Specificity Sensitivity/recall F1 AUC Precision TPR FPR [16 ] SVM 98.11 0.9574 0.8888 NB 96.22 0.93610 0.9696 CNN 99.53 1.0 0.9757 LR 96.69 0.9575 0.9696 KNN 95.75 0.9148 0.9696 ANN 97.64 0.9787 0.9757 [59 ] Decision tree 91.1 0.71 0.91 [48 ] SVM 100% NB 97.017% Decision table 100% [19 ] Decision tree AD Tree CDT J48 LAD Tree [62 ] DENN 0.99 0.99 0.99 NN 0.94 0.94 0.94 RF 0.92 0.91 0.91 SVM 0.73 0.73 0.73 Gradient boosting 0.85 0.85 0.85 [4 ] SVM 0.83 0.88 0.88 0.88 0.89 NB 0.89 0.84 0.91 0.91 1.0 RF 0.93 1.0 0.96 0.96 0.92 KNN 0.98 0.97 0.99 0.99 1.0 [1 ] J48 98.44 0.984 0.984 0.984 LMT 98.44 0.984 0.984 0.984 DS 97.82 0.978 0.977 0.979 REP Tree 97.66 0.977 0.976 0.977 NP Tree 97.98 0.980 0.979 0.980 [53 ] DT Overall % Overall % NB Overall % Overall % KNN Overall % Overall % RT Overall % Overall % Deep learning Overall % Overall % [61 ] LDA 0.9080 0.8667 0.9524 0.9091 0.8696 KNN 0.8851 0.8000 0.9762 0.8913 0.8200 [63 ] RF 0.9571 0.9821 0.8571 [47 ] DNN 86.96 OVR-SVM 56.52 CART 60.87 [46 ] LR 0.97 0.97 0.97 [57 ] DT RF RF (hyperparameter) LR SVM ANN [64 ] DNN SVM N/A N/A [15 ] ANN RNN DT ELM GB KNN LR MLP NB RF SVM XGB [54 ] KNN 67.5564 LR 72.0238 SVM 70.5952 LDA 72.2024 NB 70.7769 Classification and regression tree 69.1667 [60 ] WOEM 99 98 98 SLFN(ELM) 96 96 96 SVM 94 96.5 96.5 ANN 90 95 95 KNN 95 97 97 [55 ] DT LDA LR SVM KNN [44 ] RF LR NB MCR with average of probabilities MCR with majority voting [5 ] J48 RF Bayes Adaboost PART ANN SVM AttSelclasss [42 ] FARF (combined Firefly-Random Forest) 94.32 35.10 RF 90.78 34.09 [45 ] ANN 83 83.5 84 85 83 SVM 91 86.5 86 86 86 IANFIS 98 90 91 92 89 [56 ] SVM-NP 95.547 0.940 0.956 0.973 SVM-PK 100 1.00 1.00 1.00 SVM-PUK 100 1.00 1.00 1.00 SVM-RBF 99.315 0.993 0.993 0.993 [58 ] SVM Active pruning rules (APR) RKFNN [65 ] BFNNRELU ANFAND SVM MLP NB C4.5 RNT [40 ] MCFM 0.842 0.843 SVM 0.833 0.833 RF 0.851 0.852 NB 0.865 0.865
