Abstract
Existing software defect prediction techniques do not pay enough attention to the different cost impacts caused by misclassification and cannot prioritize modules with high defect risk. To address these problems, a defect heterogeneity risk assessment method with misclassification cost (DHRA) is proposed. Firstly, noise samples, discrete samples, and high-dimensional features are processed. Secondly, the imbalance ratio and the ratio of misclassification of different categories are calculated to obtain the overall misclassification cost (MC). The heterogeneous classifiers are selected based on the evaluation metric and MC. Then, the defective assessment value is calculated by multiplying the voting weight matrix based on misclassification cost and the base probability matrix. Finally, the defect risk grade of the module is assessed based on the defect risk table. The experimental results show that DHRA outperforms other methods in terms of accuracy, F-score, and Matthews correlation coefficient. The defect risk grade obtained by this method can accurately reflect the potential defects of the samples.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, J.F., Pan, L.S., Han, Q.L.T.: Deep learning based attack detection for cyber-physical system cybersecurity: a survey. IEEE/CAA J. Autom. Sin. 9(3), 377–391 (2022)
Chen, X.F., Gu, Q.S., Liu, W.S.T.: Survey of static software defect prediction. J. Softw. 27(1), 1–25 (2016)
Lin, G.F., Wen, S.S., Han, Q.L.T.: Software vulnerability detection using deep neural networks: a survey. Proc. IEEE 108(10), 1825–1848 (2020)
Qiu, J.Y.F., Zhang, J.S., Luo, W.T.: A survey of android malware detection with deep neural models. ACM Comput. Surv. 53(6), 1–36 (2020)
Gong, L.N.F., Jiang, S.J.S., Jiang, L.T.: Research progress of software defect prediction. J. Softw. 30(10), 3090–3114 (2019)
Yu, X.F., Jacky, K.S., Xiao, Y.T.: Predicting the precise number of software defects are we there yet. Inf. Softw. Technol. 146(1), 106847–106863 (2022)
Wang, S.F., Liu, T.Y.S., Tan, L.T.: Automatically learning semantic features for defect prediction. In: Dillon, L.F., Visser, W.S. (eds.) IEEE/ACM 38th International Conference on Software Engineering 2016, ICSE, vol. 38, pp. 297–308. Association for Computing Machinery, New York (2016)
Zhou, Z.H.F., Feng, J.S.: Deep forest: towards an alternative to deep neural networks.In: Sierra, C.F. (ed.) Twenty-Sixth International Joint Conference on Artificial Intelligence 2017, IJCAI, vol. 26, pp. 3553–3559. Morgan Kaufmann, San Francisco (2017)
Issam, H.L.F., Mohammad, A.S., Lahouari, G.T.: Software defect prediction using ensemble learning on selected features. Inf. Softw. Technol. 58(1), 388–402 (2015)
Chen, H.W.F., Jing, X.Y.S., Li, Z.Q.T.: An empirical study on heterogeneous defect prediction approaches. IEEE Trans. Softw. Eng. 47(12), 2803–2822 (2020)
Amal, A.F., Hamoud, A.S.: Code smell detection using feature selection and stacking ensemble: an empirical investigation. Inf. Softw. Technol. 138(1), 106648–106661 (2021)
Yang, H.Y.F., Zhang, Z.X.S., Xie, L.X.T.: Network security situation assessment with network attack behavior classification. Int. J. Intell. Syst. 37(3), 1–19 (2022)
GB/T 20984, Information security technology-risk assessment specification for information security. National Standard of the People’s Republic of China (2007)
Shepperd, M.F., Song, Q.S., Sun, Z.T.: Data quality: some comments on the NASA software defect datasets. IEEE Trans. Softw. Eng. 39(9), 1208–1215 (2013)
Jurecako, M.F., Mmadeyski, L.S.: Towards identifying software project clusters with regard to defect prediction. In: Proceedings of the 6th International Conference on Predictive Models in Software Engineering 2010, ICSE, pp. 1–10. Association for Computing Machinery, New York (2010)
D’Ameros, M.F., Lanza, M.S., Robbes, R.T.: Evaluating defect prediction approaches: a benchmark and an extensive comparison. Empirical Softw. Eng. 17(4), 531–577 (2012). https://doi.org/10.1007/s10664-011-9173-9
Wu, R.F., Zhang, H.S., Kim, S.T.: Relink: recovering links between bugs and changes. In: Proceedings of the 19th ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering 2011, ICSE, pp. 15–25. Association for Computing Machinery, New York (2011)
Acknowledgment
This work was supported by the National Natural Science Foundation of China (No. U1833107).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xie, L., Liu, S., Yang, H., Zhang, L. (2022). A Defect Heterogeneous Risk Assessment Method with Misclassification Cost. In: Chen, X., Huang, X., Kutyłowski, M. (eds) Security and Privacy in Social Networks and Big Data. SocialSec 2022. Communications in Computer and Information Science, vol 1663. Springer, Singapore. https://doi.org/10.1007/978-981-19-7242-3_18
Download citation
DOI: https://doi.org/10.1007/978-981-19-7242-3_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7241-6
Online ISBN: 978-981-19-7242-3
eBook Packages: Computer ScienceComputer Science (R0)