The fault reduction factor (FRF) is a significant parameter for controlling the software reliability growth. It is the ratio of net fault correction to the number of failures encountered. In literature, many factors affect the behaviour of FRF, namely fault dependency, debugging time-lag, human learning behaviour and imperfect debugging. Besides this, several distributions, for example, inflection S-shaped, Weibull and Exponentiated-Weibull, are used as FRF. However, these standard distributions are not flexible to describe the observed behaviour of FRFs. This paper proposes three different software reliability growth models (SRGMs), which incorporate a three-parameter generalized inflection S-shaped (GISS) distribution as FRF. To model realistic SRGMs, time lags between fault detection and fault correction processes are also incorporated. This study proposed two models for the single release, whereas the third model is designed for multi-release software. Moreover, the first model is in perfect debugging, while the rest of the two are in an imperfect debugging environment. The extensive experiments are conducted for the proposed models with six single release and one multi-release data-sets. The choice of GISS distribution as an FRF improves the software reliability evaluation in comparison with the existing systems in the literature. Finally, the development cost and optimal release time are calculated in a perfect debugging environment.

故障减少因子（FRF）是控制软件可靠性增长的重要参数。它是净故障纠正与遇到的故障数量的比率。在文献中，许多因素影响 FRF 的行为，即故障依赖性、调试时滞、人类学习行为和不完善的调试。除此之外，还使用了几种分布，例如 S 形拐点、Weibull 和 Exponentiated-Weibull，用作 FRF。然而，这些标准分布不能灵活地描述 FRF 的观察行为。本文提出了三种不同的软件可靠性增长模型 (SRGM)，它们将三参数广义拐点 S 形 (GISS) 分布作为 FRF。为了模拟真实的 SRGM，还包含了故障检测和故障纠正过程之间的时间滞后。本研究为单一版本提出了两种模型，而第三种模型是为多版本软件设计的。而且，第一个模型处于完美调试状态，而其余两个模型处于不完美调试环境中。对具有六个单发布和一个多发布数据集的拟议模型进行了广泛的实验。与文献中的现有系统相比，选择 GISS 分布作为 FRF 提高了软件可靠性评估。最后，在完美的调试环境中计算开发成本和最佳发布时间。对具有六个单发布和一个多发布数据集的拟议模型进行了广泛的实验。与文献中的现有系统相比，选择 GISS 分布作为 FRF 提高了软件可靠性评估。最后，在完美的调试环境中计算开发成本和最佳发布时间。对具有六个单发布和一个多发布数据集的拟议模型进行了广泛的实验。与文献中的现有系统相比，选择 GISS 分布作为 FRF 提高了软件可靠性评估。最后，在完美的调试环境中计算开发成本和最佳发布时间。