Analyzing Software Defect Prediction Using AI Approaches
Keywords:
Software Defect Prediction (SDP), Software Testing (ST), Machine Learning (ML), Deep Learning (DL), Expert Approaches, Artificial Intelligence (AI).Abstract
Defect Prediction in software serves a unique function in verifying the higher-caliber development of software by identifying potential defects before they are revealed in production. As software systems become more sophisticated, traditional defect-predicting approaches sometimes fail to produce reliable results. The article analyzes the adoption of various Expert Approaches to forecast software imperfections to develop accurate and efficient applications. The paper reviews multiple Artificial Intelligence approaches used in software prediction. The study confirms that AI techniques give better results than traditional statistical techniques, achieving higher precision and recall. The various work done in the related field, expert approaches, adoption of SDP, economic benefits, and research gaps will be covered in the paper. The emphasis will be on how the expert approaches can improve the efficiency and precision of the SDP process.
DOI: https://doi.org/10.24321/3051.4304.202604
References
R. Malhotra and A. Chug, Software maintainability: Systematic literature review and current trends, International Journal of Software Engineering and Knowledge Engineer-ing, vol. 26, no. 08, pp. 1221–1253, (2016).
Q. Huang, E. Shihab, X. Xia, D. Lo, and S. Li, Identifying self-admitted technical debt in open-source projects using text mining,Empirical Software Engineering, vol. 23, pp. 418–451, (2018).
J. Pan, Software testing, Dependable Embedded Systems, vol. 5, no. 2006, pp. 1, (1999).
C. S. Spahiu, L. Stanescu, R. Marinescu, and M. Brezovan, Machine learning system for automated testing, in 2022 23rd International Carpathian Control Conference (ICCC). IEEE, pp. 142–146 (2022).
