Software Fault Prediction Using Canonical Discriminant Quadratic Regressive Milboost Ensemble classifier

Authors

  • T. Shathish Kumar, B. Booba

Keywords:

Software fault prediction, Jarque–Bera stochastic test-based metric dispersal class extractions, generalized canonical correlative normal discriminant analysis based software metrics selection, Iterative Dichotomize Linear Regressive Quadratic MilBoost.

Abstract

The aim of software fault prediction is to sense fault-prone software modules and enhances software quality as well as testing effectiveness through early recognition of faults. It aids to achieve desired software quality through lower cost. Earlier fault prediction classification algorithms to forecast fault-prone software modules. The prediction accuracy of conventional techniques was established to be significantly minimized with better misclassification. The selection of significant metrics from the source code is the fundamental step in the software prediction process. Therefore a novel technique called CAnonical Discriminant Quadratic Regressive Milboost Ensemble (CADME) technique is introduced for improving the software prediction accuracy as well as minimizing misclassification rate. Proposed CADME technique comprised metric selection , classification. Initially, number of JAVA packages given as input from the dataset. Then the metric dispersal class extractions are carried by using Jarque–Bera stochastic test. After the class extraction, the important software metrics are chosen for software prediction using generalized canonical correlative normal discriminant analysis. Following the metric selection, the software fault prediction is through by means of Iterative Dichotomize Linear Regressive Quadratic MilBoost. As a result of JAVA classes known with defects or not are predicted in an accurate manner by reducing the loss. This assists to develop the precision and F-score in fault prediction. Simulation results are performed on factors namely accuracy, precision, recall, F-score, and time complexity. The results as well as discussion of various metrics specified that proposed CADME technique improves the accuracy and minimum time complexity of software prediction than the conventional methods.

Downloads

Download data is not yet available.

References

Ayad Tareq Imam, Basma R. Al-Srour, Aysh Alhroob, “The automation of the detection of large class bad smell by using genetic algorithm and deep learning”, Journal of King Saud University –Computer and Information Sciences, Elsevier, Volume 34, Issue 6, 2022, Pages 2621-2636. https://doi.org/10.1016/j.jksuci.2022.03.028

Lucija Šikić, Adrian Satja Kurdija, Klemo Vladimir, Marin Šilić, “Graph Neural Network for Source Code Defect Prediction”, IEEE Access, Volume 10, 2022, Pages 10402 – 10415. DOI: 10.1109/ACCESS.2022.3144598

Sweta Mehta & K. Sridhar Patnaik, “Improved prediction of software defects using ensemble machine learning techniques”, Neural Computing and Applications, Springer, Volume 33, 2021, Pages 10551–10562. https://doi.org/10.1007/s00521-021-05811-3

Inderpreet Kaur And Arvinder Kaur, “A Novel Four-Way Approach Designed With Ensemble Feature Selection for Code Smell Detection”, IEEE Access, Volume 9, 2021, Pages 8695 – 8707. DOI: 10.1109/ACCESS.2021.3049823

Umamaheswara Sharma Bhutamapuram, Ravichandra Sadam, “With-in-project defect prediction using bootstrap aggregation based diverse ensemble learning technique”, Journal of King Saud University - Computer and Information Sciences, Elsevier, 2021, Pages 1-17. https://doi.org/10.1016/j.jksuci.2021.09.010

Fahad H. Alshammari, “Software Defect Prediction and Analysis Using Enhanced Random Forest (extRF) Technique: A Business Process Management and Improvement Concept in IOT-Based Application Processing Environment”, Mobile Information Systems, Hindawi, Volume 2022, September 2022, Pages 1-11. https://doi.org/10.1155/2022/2522202

Haonan Tong,Bin Liu,and Shihai Wang, “Kernel Spectral Embedding Transfer Ensemble for Heterogeneous Defect Prediction”, IEEE Transactions on Software Engineering , Volume 47, Issue 9, 2021, Pages 1886 – 1906. DOI: 10.1109/TSE.2019.2939303

Zhen Li , Tong Li , YuMei Wu , Liu Yang , Hong Miao , and DongSheng Wang, “Software Defect Prediction Based on Hybrid Swarm Intelligence and Deep Learning”, Computational Intelligence and Neuroscience, Hindawi, Volume 2021, December 2021, Pages 1-17. https://doi.org/10.1155/2021/4997459

ShivaniJain, AnjuSaha, “Improving performance with hybrid feature selection and ensemble machine learning techniques for code smell detection”, Science of Computer Programming, Elsevier, Volume 212, 2021, Pages 1-34. https://doi.org/10.1016/j.scico.2021.102713

Amal Alazba and, Hamoud Aljamaan, “Code smell detection using feature selection and stacking ensemble: An empirical investigation”, Information and Software Technology, Elsevier,

Volume 138, 2021, Pages 1-14. https://doi.org/10.1016/j.infsof.2021.106648

Tushar Sharma, Vasiliki Efstathiou, Panos Louridas, Diomidis Spinellis, “Code smell detection by deep direct-learning and transfer-learning”, Journal of Systems and Software, Elsevier, Volume 176, 2021, Pages 1-25. https://doi.org/10.1016/j.jss.2021.110936

Seema Dewangan, Rajwant Singh Rao, Alok Mishra and Manjari Gupta, “Code Smell Detection Using Ensemble Machine Learning Algorithms”, Applied Science, Volume 12, 2022, Pages 1-22. https://doi.org/10.3390/app122010321

Hafiz Shahbaz Munir, Shengbing RenID*, Mubashar Mustafa, Chaudry Naeem Siddique, Shazib Qayyum, “Attention based GRU-LSTM for software defect prediction”, PLoS ONE, Volume 16, Issue 3, 2021, Pages 1-19. https://doi.org/10.1371/journal.pone.0247444

Pasquale Ardimento, Lerina Aversano, Mario Luca Bernardi, Marta Cimitile, Martina Iammarino, “Temporal convolutional networks for just-in-time design smells prediction using fine-grained software metrics”, Neurocomputing, Elsevier, Volume 463, 2021, Pages 454-471. https://doi.org/10.1016/j.neucom.2021.08.010

Jiaxi Xu, Fei Wang, Jun Ai, “Defect Prediction With Semantics and Context Features of Codes Based on Graph Representation Learning”, IEEE Transactions on Reliability, Volume 70, Issue 2, 2021, Pages 613 – 625. DOI: 10.1109/TR.2020.3040191

Hao Wang, Weiyuan Zhuang, and Xiaofang Zhang, “Software Defect Prediction Based on Gated Hierarchical LSTMs”, IEEE Transactions on Reliability, Volume 70, Issue 2, 2021, Pages 711 – 727. DOI: 10.1109/TR.2020.3047396

Xiao Yu, Jin Liu , Jacky Wai Keung , Qing Li , Kwabena Ebo Bennin, Zhou Xu, Junping Wang , and Xiaohui Cui, “Improving Ranking-Oriented Defect Prediction Using a Cost-Sensitive Ranking SVM”, IEEE Transactions on Reliability , Volume 69, Issue 1, 2020, Pages 139 – 153. DOI: 10.1109/TR.2019.2931559

Aleksandar Kovaˇcevi´, Jelena Slivka, Dragan Vidakovi , Katarina-Glorija Gruji ,Nikola Luburi, Simona Proki, Goran Sladi, “Automatic detection of Long Method and God Class code smells through neural source code embeddings”, Expert Systems with Applications, Elsevier, Volume 204, 2022, Pages 1-18. https://doi.org/10.1016/j.eswa.2022.117607

Mouna Hadj-Kacem and Nadia Bouassida, “A multi-label classification approach for detecting test smells over java projects”, Journal of King Saud University - Computer and Information Sciences, Elsevier, 2021, Pages 1-10. https://doi.org/10.1016/j.jksuci.2021.10.008

Mohamed Maddeh, Sarra Ayouni , Sultan Alyahya, And Fahima Hajjej, “Decision tree-based Design Defects Detection”, IEEE Access , Volume 9, 2021, Pages 71606 – 71614, DOI: 10.1109/ACCESS.2021.3078724

Downloads

Published

26.03.2024

How to Cite

T. Shathish Kumar,. (2024). Software Fault Prediction Using Canonical Discriminant Quadratic Regressive Milboost Ensemble classifier. International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 3244–3258. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6014

Issue

Section

Research Article