SMAN2: Soft-Max Multilayer Adversarial Neural Network-Based Cross-Project Software Defect Prediction

• Published in: SN computer science Vol. 4; no. 6; p. 780
• Main Authors: Ruckmani, V., Prakasam, S.
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 12.10.2023; Springer Nature B.V
• Subjects: Advances in Computational Approaches for Image Processing; Algorithms; Classification; Cloud Applications and Network Security; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Data Structures and Information Theory; Datasets; Defects; Feature selection; Information Systems and Communication Service; Literature reviews; Methods; Multilayers; Neural networks; Optimization; Original Research; Pattern Recognition and Graphics; Prediction models; Raw materials; Semantics; Software; Software Engineering/Programming and Operating Systems; Software reliability; Software testing; Standard scores; Testing time; Vision; Wireless Networks; score filter; Normalized data; Another neat tool (ANT) software dataset; Spider optimization mutual feature selection (SOMFS); ); Soft-max multilayer adversarial neural network (SMAN; Cross-project software defect prediction (CPSDP)
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-023-02224-y

Cross-project software defect prediction (CPSDP) is an excessive way to enhance test performance and ensure software reliability. The CPSDP allows developers to allocate limited resources to identify errors and prioritize testing efforts. Predicting earlier defects is a convenient operation that decreases software testing time and costs. CPSDP is difficult because predictors built into raw materials rarely generalize to the target projects. However, there are more perfect events in a real software program than defective ones, which results in severe class distribution bias and poor assortment performance. The existing method does not consider the relational features in the software required to create accurate prediction models. This paper presents soft-max multilayer adversarial neural network (SMAN 2 ) and spider optimization mutual feature selection (SOMFS) algorithm to address this problem. First, a Z -score normalization filter is used to prepare a dataset, like checking missing values and changing them into normalized data. Then, we use the SOMFS technique to choose the finest attributes from the normalized software dataset to reduce the dimensionality. Later, dimensionality reduced dataset trained into the proposed SMAN 2 algorithm analyses software defects. Concerning parameters, precision, recall, classification performance, and F1-score performance indicators find that the proposed SMAN 2 algorithm performs better than the previous methods.