欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对基于神经网络的计算机软件故障预测方法中存在的过学习和泛化能力差的问题,提出一种基于支持向量机（SVM）的软件故障预测方法.该方法应用具有强大非线性逼近能力与优秀泛化能力的支持向量机对软件故障因子与软件隐藏故障数之间的非线性关系进行拟合.采用经典粒子群优化算法（CPSO）,在测试样本集均方根误差（RMSE）与平均绝对百分比误差（MAPE）同时最小时,选择和优化支持向量机的参数向量.计算机测控软件故障预测实验验证了该方法的可行性和可靠性.
英文摘要：
The traditional forecasting method for computer soft fault based on neural networks has the problems of over-fitting and poor generalization ability.In order to solve the drawbacks,we proposes a new forecasting method Based SVM（support vector machine）.The proposed method uses SVM,which has strong nonlinear approximation ability and good generalization ability,to fit the relationship between factors of software fault and hidden number of software fault.We apply CPSO（canonical particle swarm optimization）,using the principle of RMSE（root mean square error） and MAPE（mean absolute percentage error） minimization of test sample sets to tune and optimize the parameter vector of SVM.The experimental results of a computer measurement and control software show that the method is feasible and effective.
同期刊论文项目
同项目期刊论文
期刊信息
位置：