Table 1.
An overview of the literature review.
Fig 1.
Visualization of the research framework’s implementation view.
Table 2.
Presents an overview of the Antarex dataset structure.
Table 3.
A summary of the key parameters responsible for generating the data.
Table 4.
A brief synopsis of the main dataset.
Table 5.
Configuring the ML classifier parameters.
Fig 2.
Shows the block diagram of the modified decision tree (J48) classifier.
Fig 3.
Shows the accuracy of CPU-mem mono on ML classifiers for each class (true/false).
Fig 4.
Shows CPU-mem mono class (true/false) ML classifiers’ accuracy regarding data validation outcomes.
Fig 5.
AdaBoostM1 classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem mono.
Fig 6.
Bagging classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem mono.
Fig 7.
J48 classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem mono.
Fig 8.
Dl4jMLP classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem mono.
Fig 9.
NBTree classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem mono.
Fig 10.
Classifier errors of AdaBoostM1 based on CPU-mem mono in accuracy & fault prediction.
Fig 11.
Classifier errors of Bagging based on CPU-mem mono in accuracy & fault prediction.
Fig 12.
Classifier errors of J48 based on CPU-mem mono in accuracy & fault prediction.
Fig 13.
Classifier errors of Dl4jMLP based on CPU-mem mono in accuracy & fault prediction.
Fig 14.
Classifier errors of NBTree based on CPU-mem mono in accuracy & fault prediction.
Fig 15.
Shows the accuracy of CPU-mem multi on ML classifiers for each class (true/false).
Fig 16.
Shows CPU-mem multi-class (true/false) ML classifiers’ accuracy regarding data validation outcomes.
Fig 17.
AdaBoostM1 classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem multi.
Fig 18.
Bagging classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem multi.
Fig 19.
J48 classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem multi.
Fig 20.
Dl4jMLP classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem multi.
Fig 21.
NBTree classifier’s confusion matrix for accuracy & fault prediction based on CPU-mem multi.
Fig 22.
Classifier errors of AdaBoostM1 based on CPU-mem multi in accuracy & fault prediction.
Fig 23.
Classifier errors of Bagging based on CPU-mem multi in accuracy & fault prediction.
Fig 24.
Classifier errors of J48 based on CPU-mem multi in accuracy & fault prediction.
Fig 25.
Classifier errors of Dl4jMLP based on CPU-mem multi in accuracy & fault prediction.
Fig 26.
Classifier errors of NBTree based on CPU-mem multi in accuracy & fault prediction.
Fig 27.
Shows the accuracy of HDD Mono on ML classifiers for each class (true/false).
Fig 28.
Shows HDD Mono class (true/false) ML classifiers’ accuracy regarding data validation outcomes.
Fig 29.
AdaBoostM1 classifier’s confusion matrix for accuracy & fault prediction based on HDD mono.
Fig 30.
Bagging classifier’s confusion matrix for accuracy & fault prediction based on HDD mono.
Fig 31.
J48 classifier’s confusion matrix for accuracy & fault prediction based on HDD mono.
Fig 32.
Dl4jMLP classifier’s confusion matrix for accuracy & fault prediction based on HDD mono.
Fig 33.
NBTree classifier’s confusion matrix for accuracy & fault prediction based on HDD mono.
Fig 34.
Classifier errors of AdaBoostM1 based on HDD mono in accuracy & fault prediction.
Fig 35.
Classifier errors of Bagging based on HDD mono in accuracy & fault prediction.
Fig 36.
Classifier errors of J48 based on HDD mono in accuracy & fault prediction.
Fig 37.
Classifier errors of Dl4jMLP based on HDD mono in accuracy & fault prediction.
Fig 38.
Classifier errors of NBTree based on HDD mono in accuracy & fault prediction.
Fig 39.
Shows the accuracy of HDD multi on ML classifiers for each class (true/false).
Fig 40.
Shows HDD multiclass (true/false) ML classifiers’ accuracy regarding data validation outcomes.
Fig 41.
AdaBoostM1 classifier’s confusion matrix for accuracy & fault prediction based on HDD multi.
Fig 42.
Bagging classifier’s confusion matrix for accuracy & fault prediction based on HDD multi.
Fig 43.
J48 classifier’s confusion matrix for accuracy & fault prediction based on HDD multi.
Fig 44.
Dl4jMLP classifier’s confusion matrix for accuracy & fault prediction based on HDD multi.
Fig 45.
NBTree classifier’s confusion matrix for accuracy & fault prediction based on HDD multi.
Fig 46.
Classifier errors of AdaBoostM1 based on HDD multi-in accuracy & fault prediction.
Fig 47.
Classifier errors of Bagging based on HDD multi-in accuracy & fault prediction.
Fig 48.
Classifier errors of J48 based on HDD multi-in accuracy & fault prediction.
Fig 49.
Classifier errors of Dl4jMLP based on HDD multi-in accuracy & fault prediction.
Fig 50.
Classifier errors of NBTree based on HDD multi-in accuracy & fault prediction.
Fig 51.
Accuracy of the primary dataset on ML classifiers by class (failure/repair).
Fig 52.
Shows the accuracy by class (failure/repair) of the primary dataset on ML classifiers associated with DV outcomes.
Fig 53.
AdaBoostM1 classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 54.
Bagging classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 55.
J48 classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 56.
Dl4jMLP classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 57.
NBTree classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 58.
Classifier errors of AdaBoostM1 based on primary data in accuracy & fault prediction.
Fig 59.
Classifier errors of Bagging based on primary data in accuracy & fault prediction.
Fig 60.
Classifier errors of J48 based on primary data in accuracy & fault prediction.
Fig 61.
Classifier errors of Dl4jMLP based on primary data in accuracy & fault prediction.
Fig 62.
Classifier errors of NBTree based on primary data in accuracy & fault prediction.
Fig 63.
Shows a comparison of ML classifiers with modified decision tree (J48) accuracy based on the primary dataset’s class, (failure/repair).
Fig 64.
Comparing ML classifiers with modified decision tree (J48) accuracy by primary dataset class about DV findings.
Fig 65.
Modified decision tree (J48) classifier’s confusion matrix for accuracy & fault prediction based on primary dataset.
Fig 66.
Classifier errors of modified decision tree (J48) based on primary data in accuracy & fault prediction.
Table 6.
Achievement of research aims.