IMPLEMENTATION OF SOFTWARE TESTING USING MACHINE LEARNING: A SYSTEMATIC MAPPING STUDY

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Software testing is an essential part of the life cycle of software development, verifying the quality. Dependability of software products. The introduction of machine learning (ML) technologies has led to Increasing a desire to use machine learning techniques to be improve and mechanize different areas of software testing. This systematic mapping project intends to offer a detailed an outline of the existing at the moment of research and application in the domain of software testing with machine intelligence. In the study thoroughly evaluates a wide range of literature, including academic publications and conferences. Proceedings and industry reports will be used to identify and categorize existing techniques. Machine learning-based approaches and technologies for software testing. A mapping study classifies the ML techniques used, such as classification, clustering, and anomaly detection. Analyses their application in several testing activities, such as test case creation, test Execution and fault forecasting. Furthermore, the mapping study examines the problems, advantages and trends connected to the execution of machine learning in the software testing. It identifies significant research gaps Identifies areas for further investigation. By combining and arranging existing knowledge, the systematic mapping study is a useful resource for researchers, practitioners, and business. Professionals looking for insights into the changing landscape of software testing through Integration of machine learning technologies. This study's findings add to a deeper understanding of the current status of the industry and lay the groundwork for future breakthroughs in the junction of software testing and machine learning.

References

1. J.  C.  Westland, "The cost of errors in software development: Evidence from industry," Journal of Systems and Software, no. 62, no. 1, pp. 1-9, 2002. 
2. Wang, J., & Zhang, C.: Software reliability prediction using a deep learning model based on RNN encoder/decoder. Reliab. Eng. Syst. Saf. 170, 73-82 (2018)
3. P. Ammann & J. Offutt, Introduction to Software Testing, 2nd Edition. Cambridge University Press. 2016. 
4. Reena, P. and Rajan, B.: A new feature subset selection approach for software fault prediction. Int. J. Computing. Appl. 100(17), 39-43 (2014)
5. D. Zhang & J. J. Tsai, "Machine Learning and Software Engineering," Software Quality Journal, Vol. 11, no. 2, pp. 87-119, 2003.
6. Mandal, P., Ami, A.S.: Choosing the optimal features for software fault prediction.  In the IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), pp. 110-113. IEEE (2015)
7. Bishnu, P.S., Bhattacherjee, V.: Software defect prediction with quad tree-based k-means clustering algorithm. IEEE Transactions. Knowl. Data Engineering. 24(6), 1146-1150 (2012)
8. Xia, Y. et al.: A novel metric selection method for software fault prediction.  In: International Conference on Progress in Informatics and Computing (PIC), pp. 433–436.  IEEE (2014)
9. B. Lantz, Machine Learning with R, 2nd Edition. Packt Publishing. 2015.
10. Dejaeger, K., Verbraken, T., & Baesens, B.: Toward intelligible software fault prediction models with Bayesian network classifiers. IEEE Transactions. Software engineering. 39(2), 237-257 (2013)
11. Catal, C.: Software fault prediction: literature survey and current trends. Expert System. Appl. 38(4), 4626-4636 (2011)
12. K.  Petersen, S.  Vakkalanka & L.  Kuzniarz's "Guidelines for Conducting Systematic Mapping Studies in Software Engineering: An Update," Information and Software Technology, volume. 64, pp. 1-18, 2015.

13. Okutan, A., Y?ld?z, O.T.: Using Bayesian networks to predict software defects. Empir.  Software engineering. 19 (1), 154-181 (2014)

14. B. A. Kitchenham, D. Budgen and O. P. Brereton, "Using Mapping Studies as the Basis for Further Research--A Participant-Observer Case Study," Information and Software Technology, Vol. 53, no. 6, pp. 638-651, 2011. 
15. Xing, F., Guo, P., and Lyu, M.R.: A Novel Method for Early Software Quality Prediction Based on Support vector machine.  In: 16th IEEE International Symposium on Software Reliability Engineering (ISSRE 2005). p. 10. IEEE (2005)
16. Kumar, L., et al.: Effective fault prediction model created utilizing the least squares support vector. Machine (LSSVM). J. Syst. Software 137, 686–712 (2018)
17. R Malhotra and J Jain (2021): Predicting errors in object-oriented software using cost- IOP Conference: Sensitive classification. Series: Materials Science and Engineering 1022 (2021). 012112 IOP Publishing doi: 10.1088/1757-899X/1022/1/012112 https://en.wikipedia.org/wiki/Machine_learning
18. Altay Ataman 2023: Machine Learning for Test Automationhttps://research.aimultiple.com/machine-learning-test-automation/
19. Liu, Mingxia Miao, Linsong Zhang, and Daoqiang 2014/06/01 676 686 Two-Stage Cost-sensitive Learning for Software Defect Prediction, IEEE Transactions on Reliability 63, DO I- 10.1109/TR.2014.2316951.

Keywords