组合导航系统软件可靠性的神经网络静态预测  

Neural network based static prediction of software reliability in integrated navigation system

作　　者：张家海[1] 胡恒章[1] 

机构地区：[1]哈尔滨工业大学控制科学与工程系,黑龙江哈尔滨150001

出　　处：《哈尔滨工业大学学报》2002年第5期697-699,共3页Journal of Harbin Institute of Technology

摘　　要：在组合导航系统大规模软件开发中 ,为了控制软件的质量 ,必须对软件模块的缺陷数进行预测 .根据软件模块测试报告及软件复杂度 ,用神经网络方法预测了软件模块的缺陷数 .结果表明Accurate prediction of the number of faults in program modules is a major problem for quality control of a large scale integrated navigation software system. According to the software test record and software complexity, a neural network was used as a tool for the prediction of the number of faults in a program on a trial basis. It is indicated that the neural network does produce the models with a better quality of fit and prediction than the traditional linearity regression method.

关 键 词：神经网络 组合导航系统 软件可靠性 静态预测 软件开发 

分 类 号：TN967.2[电子电信—信号与信息处理] TP311.5[电子电信—信息与通信工程]