| 基于支持向量机的面向对象软件可维护性预测 |
| |
| 引用本文： | 王李进,胡欣欣.基于支持向量机的面向对象软件可维护性预测[J].吉林林学院学报,2010(3):282-285. |
| |
| 作者姓名： | 王李进 胡欣欣 |
| |
| 作者单位： | 福建农林大学计算机与信息学院,福建福州350002 |
| |
| 基金项目： | 福建省自然科学基金（2009J05043）; 福建省教育厅资助项目（JA08063） |
| |
| 摘 要： | 以面向对象软件的度量准则作为预测因子,以维护期间所修改的代码函数作为可维护性,运用支持向量机回归原理,构造了面向对象软件可维护性预测模型.为了评价模型的性能,同时构造人工神经网络模型.在R软件环境下仿真,通过误差的可视分析和RMSE分析知,SVM模型预测面向对象软件可维护性具有较好的性能,效果明显优于ANN模型.
|
| 关 键 词： | 支持向量机 人工神经网络 可维护性 面向对象 |
Predicting on Object-Oriented Software Maintainability Based on Support Vector Machine |
| |
| Authors: | WANG Li-jin HU Xin-xin |
| |
| Institution: | (College of Computer and Information Science,Fujian Agriculture and Forestry University,Fuzhou 350002,China) |
| |
| Abstract: | A maintainability prediction model was built by using the principle of support vector regression.The predictors were defined as object-oriented software metrics,and the maintainability was measured as the number of changes made to code during a maintenance period.To evaluate the performance of model,the artificial neural networks model was also built.Simulated SVM model under the environment of R software had a better performance of predicting the maintainability,and was superior to ANN model by visual analysis of error and RMSE. |
| |
| Keywords: | support vector machine artificial neural networks maintainability object-oriented |
| 本文献已被 维普 等数据库收录！ |
|
