Performance Evaluation of Some Selected Learning Algorithms for Software Defect Prediction Using Harmony Search Algorithm

Simple item page
dc.contributor.authorFolorunsho BAMISAYE
dc.date.accessioned2024-05-21T09:41:06Z
dc.date.available2024-05-21T09:41:06Z
dc.date.issued2022-12
dc.description.abstractSoftware defects (SD) is a significant area of software development that has called for the attention of both academics and professionals in the last few decades. The more software evolves, the more there is a need to produce testing measures by which the reliability, dependability, and efficiency of the software can be verified and ascertained. The quest to predict defects or better still produce error-free software is commendable, however, other factors such as an accurate prediction rate and time interval for prediction call for imperative attention. The prolonged processing of prediction can lead to misclassification, most especially when a large dataset is used for classification. In other words, misclassification and prolonged processing is inevitable when a large dataset is used for prediction. That is why this study has applied a meta-heuristic optimization algorithm for feature selection (FS) to reduce high dimensionality which may lead to prolonged classification time and misclassification. The HSA was employed for feature selection, and five learning algorithms- Support Vector Machine (SVM), Artificial Neural Network, K-Nearest Neigbour, Naïve Baye, and C4.5 were applied for classification. Also, Eclipse dataset was used for prediction. The operational output of the model was achieved using some evaluation metrics such as precision, accuracy, recall, classification time, and F1 score.The recorded results with HSA revealed that the ANN algorithm achieved the lowest classification time of 24.09s in the Eclipse Dataset which shows that the predictive rate of ANN outperformed other classifiers used for defect classification. The highest accuracy of 86.44% was obtained in SVM which shows that KNN outperformed other learning algorithms used for prediction in terms of correctness. Based on the output of KNN with harmony search in the SDP, it is therefore recommended for model development. Keywords: Software Defeat, Defect Prediction, Dimensionality Reduction, Feature Selection, Misclassification Word Count: 279
dc.identifier.citationKate Turabian
dc.identifier.otherM.Sc
dc.identifier.urihttps://repository.lcu.edu.ng/handle/123456789/179
dc.language.isoen
dc.publisherLead City University
dc.relation.ispartofseriesM.Sc
dc.titlePerformance Evaluation of Some Selected Learning Algorithms for Software Defect Prediction Using Harmony Search Algorithm
dc.typeThesis

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
Bamisaye Folorunsho Preliminary.pdf
Size:
1.03 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
Bamisaye FolorunshoThesis.pdf
Size:
10.26 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download

Collections

Department of Computer Science;