关键词: 经验模态分解, 支持向量回归, 灰色系统模型, 软件可靠性预测

Abstract: A hybrid software reliability prediction model based on Empirical Mode Decomposition（EMD） is presented and applied to software reliability forecasting. The software failure samples are handled in order to obtain the Intrinsic Mode Functions（IMFs） and the residue of different frequency bands are obtained according to EMD. Then the corresponding failure data series in the IMFs and the residue are chosen as the training samples. By means of the flexible prediction capacity of Support Vector Regression（SVR） and Grey Model（GM）, the models of each IMF and the residue are forecasted. The ultimate forecasting result is obtained by reconstructing the forecasting results of each IMF and the residue. The method of EMD overcomes the shortcomings that it’s difficult to select proper wavelet function for wavelet transform, and the final result indicates that the IMFs can reflect the characteristic of software failure. After comparing with the results forecasted by means of combination of SVR and GM（1, 1）, it proves that the effect of the hybrid forecasting method of SVR&GM in software reliability forecasting is better.

Key words: empirical mode decomposition, support vector regression, grey model, software reliability prediction