Fig 1.
Software defects types.
Table 1.
Comparative analysis with PCA vs feature optimization approaches.
Table 2.
MLP vs classification algorithms.
Table 3.
SPAM-XAI compared with previous models.
Table 4.
PROMISE defects prediction attribute aspects.
Fig 2.
(a). Dataset: CM1. (b). Dataset: PC1. (c). Dataset: PC2.
Table 5.
Dataset detail division.
Fig 3.
SMOTE representation.
Fig 4.
Internal architecture of the SPAM-XAI model.
Fig 5.
Illustration of MLP.
Fig 6.
Overview of SPAM-XAI model complete architecture.
Table 6.
Demonstration confusion matrix.
Table 7.
SPAM-XAI confusion matrix.
Fig 7.
Analysis of CM1 ROC curve.
Table 8.
SPAM-XAI confusion matrix using PC1 dataset.
Fig 8.
Analysis PC1 AU-ROC curve.
Table 9.
SPAM-XAI confusion matrix using PC2 dataset.
Fig 9.
Analysis PC2 AU-ROC curve.
Table 10.
Statistical model evaluation for CM1, PC1 & PC2 datasets using SPAM-XAI model.
Table 11.
Experimental evaluation of various baseline models with the SPAM-XAI model.
Fig 10.
(a). Baseline model Comparative Analysis with CM1 dataset. (b). Baseline model Comparative Analysis with PC1 dataset.
Table 12.
Analysis of previously developed models with SPAM-XAI model.
Fig 11.
(a). Precision CM1 and PC1 dataset. (b). Recall CM1 and PC1 dataset. (c). F-Measure CM1 and PC1 dataset. (d). Accuracy CM1and PC1 dataset. (e). AU-ROC-area CM1 and PC1 dataset.
Table 13.
Comparison of total training duration (in seconds) of previously developed models with SPAM-XAI.
Fig 12.
SPAM-XAI using the CM1 dataset.
Fig 13.
SPAM-XAI using the PC1 dataset.