基于LM-BP神经网络的软件质量综合评价

The comprehensive evaluation of software quality based on LM-BP neural network

由于传统软件质量评价存在主观性等缺陷.针对这种情况,提出基于LM-BP神经网络的软件质量综合评价方法.算法以ISO/IEC 9126为软件质量度量标准,解决了标准BP算法存在的问题,建立了LM-BP神经网络软件质量综合评价模型,为软件质量综合评价提供了一种新的方法.实验结果表明,LM-BP神经网络的软件质量综合评价能客观、定量、快速且准确得到软件质量综合评价结果,该评价模型具有客观性和实用性.

Because traditional software quality evaluation has some defects such as subjectivity , we proposed a method based on levenberg marquardt-back propagation(LM-BP) neural network software quality comprehensive evaluation .Based on ISO/IEC 9126 software quality model ,the algorithm solves the problems existing in the standard BP algorithm ,establishes the LM-BP neu‐ral network software quality comprehensive evaluation model ,and offers a new method for com‐prehensive evaluation of software quality .Experimental results show that the LM-BP neural net‐work software quality comprehensive evaluation is objective ,quantitative ,fast and accurate .The evaluation model is objective and practical .