arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09463cs.SEcs.LG
收藏

基于机器学习与数据挖掘方法的有效软件风险预测管理数据分析

An Effective Software Risk Prediction Management Analysis of Data Using Machine Learning and Data Mining Method

Southern Methodist University(南卫理公会大学);New York University(纽约大学);Columbia University(哥伦比亚大学)

Jinxin Xu, Yue Wang, Ruisi Li, Ziyue Wang, Qian Zhao

AI总结:

本文提出结合增强型乌鸦搜索算法与ANFIS的软件风险预测方法,并在NASA 93数据集上验证其相比现有方法具有更高的风险评估准确性与有效性。

摘要:

为了确保更高质量的软件开发过程,风险管理至关重要。此外,风险是指那些可能对组织运营或项目进展产生负面影响的潜在因素。对软件项目风险进行合理优先级排序,是确定软件项目性能特征并最终取得成功的关键因素。这些风险因素能够与相同的训练样本协调使用,并具有良好的互补性和兼容性。我们在四个基准数据集上进行了深入实验,以验证所提出的CIA方法在封闭世界和开放世界场景下、有防御和无防御条件下的有效性。我们还提出了一种顺序增强参数优化技术,该技术能够捕捉最新深度学习最先进的网站指纹攻击模型之间的相互依赖关系。为了实现精确的软件风险评估,采用增强型乌鸦搜索算法(ECSA)来调整ANFIS的设置。利用ECSA提取那些仅对局部最优解产生极小改变并停留在其中的解。在使用ANFIS技术时对ANFIS变量进行调整。使用NASA 93数据集和93个软件项目数值进行了实验验证。该方法的结果清晰地展示了对于实现项目性能至关重要的软件风险要素。实验结果表明,与其他现有方法相比,我们的综合模糊技术在软件项目风险评估中能够实现更高的准确性和有效性。

英文摘要:

For one to guarantee higher-quality software development processes, risk management is essential. Furthermore, risks are those that could negatively impact an organization's operations or a project's progress. The appropriate prioritisation of software project risks is a crucial factor in ascertaining the software project's performance features and eventual success. They can be used harmoniously with the same training samples and have good complement and compatibility. We carried out in-depth tests on four benchmark datasets to confirm the efficacy of our CIA approach in closed-world and open-world scenarios, with and without defence. We also present a sequential augmentation parameter optimisation technique that captures the interdependencies of the latest deep learning state-of-the-art WF attack models. To achieve precise software risk assessment, the enhanced crow search algorithm (ECSA) is used to modify the ANFIS settings. Solutions that very slightly alter the local optimum and stay inside it are extracted using the ECSA. ANFIS variable when utilising the ANFIS technique. An experimental validation with NASA 93 dataset and 93 software project values was performed. This method's output presents a clear image of the software risk elements that are essential to achieving project performance. The results of our experiments show that, when compared to other current methods, our integrative fuzzy techniques may perform more accurately and effectively in the evaluation of software project risks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑