The Impact of Learning, Fatigue, and Dependent Faults on Software Reliability

Software reliability is a critical factor in ensuring the quality and dependability of software systems. Historically, software errors were primarily attributed to coding mistakes. However, recent insights have revealed that human error is a dynamic phenomenon influenced by factors such as learning processes and fatigue. This paper presents an approach that incorporates tester fatigue into the debugging process, thereby improving the development of more realistic software reliability growth models (SRGMs). The proposed approach utilizes S-shaped learning curves and an exponential fatigue function to account for the dynamic nature of human error. Additionally, interdependencies between faults are considered in the analysis. The quality, predictive capabilities, and accuracy of the proposed models are rigorously evaluated using three well-established fit criteria: mean squared error (MSE), mean absolute error (MAE), and the coefficient of determination ([Formula: see text]), applied to two failure datasets. By integrating the fatigue factor into the proposed models, a more comprehensive representation of software reliability dynamics is provided. This research contributes to the advancement of software reliability analysis and enhances the assessment of software system dependability.