Novel artificial intelligence-based ensemble learning for optimized software quality

Abstrak

Artificial intelligence (AI) contributes towards improving software engineering quality; however, existing AI models are witnessed to deploy learning-based approaches without addressing various complexities associated with datasets. A literature review showcases an unequilbrium between addressing the accuracy and computational burden. Therefore, the proposed manuscript presents a novel AI-based ensemble learning model that is capable of performing an effective prediction of software quality. The presented scheme adopts correlation-based and multicollinearity-based attributes to select essential feature selection. At the same time, the scheme also introduces a hybrid learning approach integrated with a bio-inspired algorithm for constructing the ensemble learning scheme. The quantified outcome of the proposed study showcases 65% minimized defect density, 94% minimized mean time to failure, 62% minimized processing time of the algorithm, and 43% enhanced predictive accuracy.