MUET logo

Use of deep learning in early software bug detection

Authors

  • Syed Mibran Hassan Zaidi

    Master’s Researcher of Computer Science & Information Technology Department, NED University of Engineering & Technology, Karachi 75270, Pakistan
    Author

  • Maria Khan

    Master’s Researcher of Computer Science & Information Technology Department, NED University of Engineering & Technology, Karachi 75270, Pakistan
    Author

  • Mustafa Latif

    Associate Professor in the Department of Software Engineering, NED University of Engineering & Technology, Karachi 75270, Pakistan
    Author

  • Ali Akhtar

    Lecturer in the Department of Computer Science & Information Technology, NED University of Engineering & Technology, Karachi 75270, Pakistan
    Author

  • Sallar Khan

    Doctoral Researcher School of Informatics and Cybersecurity, Technological University Dublin, Dublin D15 YV78, Ireland
    Author

DOI:

https://doi.org/10.22581/muet1982.0331

Keywords:

Deep Learning , CNN , Random Forest , Software Bug Detection , Ensemble Approach , Voting Ensemble

Abstract

In the software maintenance and development process, software bug identification is a significant challenge because this is connected with the successful software in its whole state. To increase software efficiency, dependability, and quality early software problem identification is important. Therefore, an efficient software bug detection model is a critically significant challenging operation, and that has been developed in this work by designing the efficient model while using the promises dataset as input for bug identification. An ensemble technique approach is proposed to increase the performance of detecting software bugs for moderate to large datasets. This was achieved by using an ensemble parallel technique for training the Convolutional Neural Network and Random Forest algorithm in a parallel way. Then, the predictions from both models are aggregated using an ensemble voting technique. The performance of the implied technique is evaluated using various kinds of metrics, including accuracy, F-measure, recall, and precision. Experimental findings show significant improvements in prediction accuracy and F1 scores compared to the standalone CNN model, including increases of 33.06% for Camel, 13.43% for Jedit, 50.85% for Xerces, and 18.35% for Synapse. These findings highlight the potential of ensemble learning techniques for enhancing software bug detection.

Downloads

References

O. E. Olorunshola, M. E. Irhebhude, A. E. Evwiekpaefe, and F. N. Ogwueleka, “Evaluation of machine learning classification techniques in predicting software defects,” Trans. Mach. Learn. Artif. Intell., vol. 8, pp. 1–15, 2020.

B. A. Sanusi, S. O. Olabiyisi, A. O. Olowoye, and B. L. Olatunji, “Software defect prediction system using machine learning-based algorithms,” J. Adv. Comput. Intell. Theory, vol. 1, no. 3, pp. 1–9, 2019.

J. Li, P. He, J. Zhu, and M. R. Lyu, “Software defect prediction via convolutional neural network,” in Proc. IEEE Int. Conf. Softw. Qual., Rel. Security (QRS), Prague, Czech Republic, Jul. 2017, pp. 318–328.

W. Alkaberi and F. Assiri, “Predicting the number of software faults using deep learning,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 2, pp. 13222–13231, 2024, doi: 10.48084/etasr.6798.

W. Long et al., “Unified spatial-temporal neighbour attention network for dynamic traffic prediction,” IEEE Trans. Veh. Technol., vol. 72, no. 2, pp. 1515–1529, 2023.

D. Li, K. D. Ortegas, and M. White, “Exploring the computational effects of advanced deep neural networks on logical and activity learning for enhanced thinking skills,” Systems, vol. 11, no. 7, p. 319, 2023.

M. Sh. Daoud et al., “Machine learning empowered software defect prediction system,” Intell. Autom. Soft Comput., vol. 31, no. 2, pp. 1287–1300, 2022.

A. Jude and J. Uddin, “Explainable software defects classification using SMOTE and machine learning,” Ann. Emerg. Technol. Comput., vol. 8, no. 1, 2024.

M. Ali et al., “Software defect prediction using an intelligent ensemble-based model,” 2024.

Fei, “PROMISEbackup,” GitHub, 2024. [Online]. Available: https://github.com/feiwww/PROMISEbackup

S. Mehta and K. S. Patnaik, “Improved prediction of software defects using ensemble machine learning techniques,” Neural Comput. Appl., vol. 33, no. 16, pp. 10551–10562, 2021.

X. Wu and J. Wang, “Application of bagging, boosting and stacking ensemble and easy ensemble methods for landslide susceptibility mapping in the Three Gorges Reservoir area of China,” Int. J. Environ. Res. Public Health, vol. 20, no. 6, p. 4977, 2023.

M. A. Javed, “A framework for software defect prediction using nested-ensemble learning and feature selection techniques,” M.S. thesis, Virtual Univ. Pakistan, 2021.

F. Matloob, “Software defect prediction model using multi-layer feed-forward neural networks,” Ph.D. dissertation, Virtual Univ. Pakistan, 2020.

S. K. Pandey, R. B. Mishra, and A. K. Tripathi, “Machine learning-based methods for software fault prediction: A survey,” Expert Syst. Appl., vol. 172, no. 2, p. 114595, 2021.

A. B. Farid, E. M. Fathy, A. S. Eldin, and L. A. Abd-Elmegid, “Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM),” PeerJ Comput. Sci., vol. 7, no. 5, p. e739, 2021.

Z. M. Zain, S. Sakri, N. H. A. Ismail, and R. M. Parizi, “Software defect prediction harnessing on multi 1-dimensional convolutional neural network structure,” Comput. Mater. Continua, vol. 71, no. 1, p. 1521, 2022.

L. Qiao, X. Li, Q. Umer, and P. Guo, “Deep learning-based software defect prediction,” Neurocomputing, vol. 385, no. 2, pp. 100–110, 2020.

G. Mahajan and N. Chaudhary, “Design and development of a novel hybrid optimization-based convolutional neural network for software bug localization,” Soft Comput., vol. 26, no. 24, pp. 13651–13672, 2022.

G. Rani, U. Pandey, A. A. Wagde, and V. S. Dhaka, “A deep reinforcement learning technique for bug detection in video games,” Int. J. Inf. Technol., vol. 15, no. 1, pp. 355–367, 2023.

Z. Wang et al., “BugPre: An intelligent software version-to-version bug prediction system using graph convolutional neural networks,” Complex Intell. Syst., vol. 9, no. 4, pp. 3835–3855, 2023.

M. Choetkiertikul et al., “Automatically recommending components for issue reports using deep learning,” Empir. Softw. Eng., vol. 26, no. 2, pp. 1–39, 2021.

S. T. Cynthia, B. Roy, and D. Mondal, “Feature transformation for improved software bug detection models,” in 15th Innovations in Software Engineering Conf., 2022, pp. 1–10.

G. Giray et al., “On the use of deep learning in software defect prediction,” J. Syst. Softw., vol. 195, p. 111537, 2023.

Ö. F. Arar and K. Ayan, “Software defect prediction using cost-sensitive neural network,” Appl. Soft Comput., vol. 33, pp. 263–277, 2015.

X. Chen et al., “Software defect number prediction: Unsupervised vs supervised methods,” Inf. Softw. Technol., vol. 106, pp. 161–181, 2019.

M. Nevendra and P. Singh, “Multistage preprocessing approach for software defect data prediction,” in Commun. Comput. Inf. Sci., 2018, pp. 505–515.

A. Abo-eleneen et al., “The role of reinforcement learning in software testing,” Inf. Softw. Technol., 2023.

M. Rahimi et al., “Fog-based smart homes: A systematic review,” J. Netw. Comput. Appl., 2020.

M. Songhorabadi et al., “Fog computing approaches in IoT-enabled smart cities,” J. Netw. Comput. Appl., 2023.

M. Etemadi, “A systematic review of healthcare recommender systems: Open issues, challenges, and techniques,” Expert Syst. Appl., 2023.

D. Karimi, H. Dou, S. K. Warfield, and A. Gholipour, “Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis,” Med. Image Anal., vol. 67, p. 101819, Jul. 2020. [Online]. Available: https://doi.org/10.1016/j.media.2020.101819

Published

2025-07-01

Issue

Vol. 44 No. 3 (2025): July Issue

Section

Articles

License

Copyright (c) 2025 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

Use of deep learning in early software bug detection. (2025). Mehran University Research Journal of Engineering and Technology, 44(3), 141-151. https://doi.org/10.22581/muet1982.0331