| 基于神经网络的软件关键模块的识别方法 |
| |
| 引用本文： | 王毅刚,朱小冬,甘茂治.基于神经网络的软件关键模块的识别方法[J].计算机应用,2005,25(6):1336-1338. |
| |
| 作者姓名： | 王毅刚 朱小冬 甘茂治 |
| |
| 作者单位： | 军械工程学院,维修工程研究所,河北,石家庄,050003;军械工程学院,装备模拟训练中心,河北,石家庄,050003 |
| |
| 摘 要： | 研究了如何利用神经网络解决软件关键模块的识别问题。首先利用交叉确认改进了级联相关算法，设计了多层前馈神经网络作为模式分类器，以软件模块的复杂性度量作为特征向量识别软件中的关键模块。最后以自行开发的维修性分配与预计(MAP)软件为例说明了采用改进的级联相关算法确定软件关键模块的优势。
|
| 关 键 词： | 级联相关 关键模块 交叉确认 软件复杂性度量 模式识别 |
| 文章编号： | 1001-9081(2005)06-1336-03 |
Pattern recognition method for critical modules of software based on neural networks |
| |
| WANG Yi-gang,ZHU Xiao-dong,GAN Mao-zhi.Pattern recognition method for critical modules of software based on neural networks[J].journal of Computer Applications,2005,25(6):1336-1338. |
| |
| Authors: | WANG Yi-gang ZHU Xiao-dong GAN Mao-zhi |
| |
| Affiliation: | WANG Yi-gang 1,ZHU Xiao-dong 2,GAN Mao-zhi 11.Maintenance Engineering Institute,Ordnance Engineering College,Shijiazhuang Hebei 050003,China, 2.Equiment Simulation Training Center,Ordnance Engineering College,Shijiazhuang Hebei 050003,China) |
| |
| Abstract: | How neural network could deal with the pattern recognition of software critical modules was studied. First, the cascaded-correlation algorithm was modified using cross validation, and then based on the complexity metrics of software modules, the multilayer neural network classifier was designed to identify critical modules of software. Finally, by analyzing the application in the project MAP, the experiment result shows the advantage of the modified cascaded-correlation algorithm. |
| |
| Keywords: | cascade-correlation critical module cross-validation software complexity metric pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
