人工神经网络在软件质量预测中的应用  

An Application of Artificial Neural Networks to Software Quality Prediction

作　　者：景疆[1] 杨俊[1] 

机构地区：[1]南京邮电大学计算机与科学学院

出　　处：《信息技术与标准化》2005年第11期41-43,共3页Information Technology & Standardization

摘　　要：软件质量预测建模技术是软件质量评价体系中的关键技术,它能够对用户所关心的软件质量特性进行评价。预测模型常常用来发现度量数据和质量要素两者之间的关系,但二者的关系常常复杂而非线性,传统的建模方法受到限制,而人工神经网络技术是一种对非线性关系的建模方法。Software quality prediction technology is the key technolagy of software quality evaluation system and can evaluate software quality characteristic concerned by customers. Models are often based on statistical relationships between measures of quality and measures of software metrics. However, relationships between static software metrics and quality factors are often complex anti nonlinear. limiting the accuracy of conventional approaches, Artificial neural networks are adept at modeling nonlinear functional relationships that are, difficult to model with other techniques. and thus. ate attractive for software quality modeling.

关 键 词：软件质量预测模型 软件度量 质量评测 人工神经网络 软件质量评价体系 人工神经网络技术 质量预测 非线性关系 应用 建模技术 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]