International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Software Defect Prediction using Lightweight Convolutional Neural Networks (LCNN) and Explainable AI (XAI) |
|---|---|
| ABSTRACT | Software defects continue to pose a critical challenge in mission-critical systems, with the global cost of software bugs exceeding USD 1.1 trillion annually. Traditional machine learning approaches for Software Defect Prediction (SDP) treat code metrics as flat feature vectors, failing to capture the spatial correlations between different metric groups. This paper presents LCNN, a Lightweight Convolutional Neural Network system that introduces 2D Spatial Feature Extraction — transforming 20 NASA CM1 software metrics into a 4×5 spatial grid (“Metric Image”) — enabling a 2D-Residual CNN to learn hidden cross-metric dependencies invisible to tabular models. The NASA CM1 dataset (498 original samples) is expanded to 7,000 balanced samples using combined SMOTE and bootstrapped oversampling. The proposed LCNN 2D-CNN achieves a Test Accuracy of 94.50%, ROC-AUC of 0.976, and Defect Recall of 99.1% — outperforming all classical ML baselines. Explainable AI is integrated via LIME for per-prediction explanations and SHAP for global feature importance validation. The complete system is deployed as a Flask web dashboard with real-time inference, dynamic confidence bars, and embedded LIME visualizations. |
| AUTHOR | DR. T.V.S SRIRAM, P. PRASAD, B.CHANDINI Sr. Asst. Professor, Dept. of MCA, NSRIT, Visakhapatnam, AP, India Asst. Professor, Dept. Of MCA, NSRIT, Visakhapatnam, AP, India Dept. of MCA, NSRIT, Visakhapatnam, AP, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406090 |
| pdf/90_Software Defect Prediction using Lightweight Convolutional Neural Networks (LCNN) and Explainable AI (XAI).pdf | |
| KEYWORDS | |
| References | [1] T. Menzies, J. Greenwald, and A. Frank, “Data mining static code attributes to learn defect predictors,” IEEE Transactions on Software Engineering, vol. 33, no. 1, pp. 2–13, Jan. 2007. [2] S. Lessmann, B. Baesens, C. Mues, and S. Pietsch, “Benchmarking classification models for software defect prediction,” IEEE Transactions on Software Engineering, vol. 34, no. 4, pp. 485–496, 2008. [3] S. Wang, T. Liu, and L. Tan, “Automatically learning semantic features for defect prediction,” in Proc. 38th ICSE, Austin, TX, 2016, pp. 297–308. [4] J. Li, P. He, J. Zhu, and M. R. Lyu, “Software defect prediction via convolutional neural network,” in Proc. IEEE QRS, Prague, 2017, pp. 318–328. [5] M. T. Ribeiro, S. Singh, and C. Guestrin, ‘“Why should I trust you?”: Explaining the predictions of any classifier,’ in Proc. 22nd ACM SIGKDD, San Francisco, CA, 2016, pp. 1135–1144. [6] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in NeurIPS, vol. 30, Long Beach, CA, 2017, pp. 4765–4774. [7] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002. [8] A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE CVPR, Las Vegas, NV, 2016, pp. 770–778. [10] M. H. Halstead, Elements of Software Science. New York: Elsevier, 1977. [11] T. J. McCabe, “A complexity measure,” IEEE Transactions on Software Engineering, vol. SE-2, no. 4, pp. 308–320, Dec. 1976. [12] NASA PROMISE Software Engineering Repository. Available: http://promise.site.uottawa.ca/SERepository/datasets/cm1.arff [Accessed: 2024]. [13] TensorFlow Documentation. Available: https://www.tensorflow.org [14] LIME Library. Available: https://github.com/marcotcr/lime [15] SHAP Library. Available: https://github.com/slundberg/shap [16] Flask Documentation. Available: https://flask.palletsprojects.com [17] scikit-learn Documentation. Available: https://scikit-learn.org [18] imbalanced-learn Documentation. Available: https://imbalanced-learn.org [19] M. Hall et al., “A systematic literature review on fault prediction performance in software engineering,” IEEE Transactions on Software Engineering, vol. 38, no. 6, pp. 1276–1304, 2012. [20] Google Scholar — Software Defect Prediction Research. Available: https://scholar.google.com [21] IEEE Xplore — CNN for Software Defect Detection. Available: https://ieeexplore.ieee.org [22] Python Documentation. Machine Learning Libraries. Available: https://docs.python.org [23] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. [24] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. [25] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [26] C. Cortes and V. Vapnik, “Support Vector Networks,” Machine Learning, vol. 20, pp. 273–297, 1995. [27] T. Cover and P. Hart, “Nearest Neighbor Pattern Classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967. [28] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [29] W. McKinney, Python for Data Analysis, 3rd ed., O’Reilly Media, 2022. [30] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed., O’Reilly Media, 2022. [31] C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. [32] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, Springer, 2017. [33] F. Chollet, Deep Learning with Python, 2nd ed., Manning Publications, 2021. [34] S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson, 2009. [35] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed., Morgan Kaufmann, 2012. [36] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in Proc. ICLR, San Diego, CA, 2015. [37] S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” in Proc. ICML, Lille, France, 2015, pp. 448–456. [38] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014. [39] Keras Documentation. Available: https://keras.io [40] M. Abadi et al., “TensorFlow: A System for Large-Scale Machine Learning,” in Proc. 12th USENIX OSDI, Savannah, GA, 2016, pp. 265–283. |
