Investigating Tree Family Machine Learning Techniques for a Predictive System to Unveil Software Defects

Table 1

Summary of the literature survey.

Author	Technique/model	Datasets	Evaluation measures
Czibula et al. [11]	RAD	PC1, PC2, PC3, PC4, KC1, KC3, MC2, JM1, MW1, and CM1	Accuracy, specificity, precision, PD, and ROC
Li et al. [20]	DP-CNN	Camel, jEdit, Lucene, xalam, Xerces, synapse, and poi	FM
Jacob and Raju [21]	HFS, NB, NN, RF, RT, J48	PC1, PC2, PC3, PC4, CM1, MW1, KC3, and JM1	Specificity, sensitivity, MCC, and accuracy
Bashir et al. [22]	NB, RF, KNN, MLP, SVM, J48, and decision stump	CM1, JM1, KC2, MC1, PC1, and PC5	ROC
Miholca et al. [7]	HyGRAR	JEdit 4.2, JEdit 4.0, Anr 1.7, JEdit 4.3, Tomcat 6.0, AR1, AR3, AR4, AR5, and AR6	Accuracy, sensitivity, specificity, and precision
Alsaeedi and Khan [8]	Bagging, SVM, DT, and RF	PC1, PC3, PC4, PC5, JM1, KC2, KC3, MC1, MC2, and CM1	GM, specificity, F-score, recall, precision, and accuracy
Iqbal et al. [9]	OneR, NB, K^∗, MLP, RBF, SVM, KNN, DT, PART, and RF	PC1, PC2, PC3, PC4, PC5, KC1, KC3, CM1, JM1, MW1, MC1, and MC2	MCC, ROC area, FM, recall, precision, and accuracy
Malhotra and Kamal [6]	J48, RF, NB, AdaBoost, bagging, and SPIDER3	NASA datasets	Accuracy, sensitivity, specificity, and precision
Manjula and Florence [23]	GA, DNN, NB, RF, DT, ABC, SVM, and KNN	KC1, KC2, CM1, PC1, and JM1	Precision, sensitivity, specificity, recall, F-score, and accuracy