Application of Software Aging Prediction Based on Wavelet Analysis and Support Vector Machines
Zhu Xiao-chuan · Jisuanji fangzhen · 2012
Software aging data contain a lot of noises,and the traditional forecasting method can not effectively eliminate the noises.In order to improve the prediction accuracy of software aging,the paper presented a software aging prediction method based on wavelet support vector machine.The collection of software aging prediction data was reduced,then wavelet analysis was performed on the data decomposition which is of multiple letter scales.Then,software aging data of various scales coefficients were predicted by using wavelet analysis.Last,the obtained coefficient forecasting results were used for reconstruction to get the software aging prediction result.The simulation results show that,compared with the traditional forecasting methods,wavelet support vector machine can improve the software aging prediction accuracy and predict the trend of decline of software.