Classification using least squares support vector machine for reliability analysis

• 作 者: Zhi-wei GUO Guang-chen BAI
• 机 构: School of Jet Propulsion
• 出 处: 应用数学和力学（英文版）
• 发表日期: 2004年期
• 关键词: least squares support vector machine classification reliability performance func
• 基金项目: 国家高技术研究发展计划(863计划)

In order to improve the efficiency of the support vector machine (SVM) for classification to deal with a large amount of samples,the least squares support vector machine (LSSVM) for classification methods is introduced into the reliability analysis.To reduce the computational cost,the solution of the SVM is transformed from a quadratic programming to a group of linear equations.The numerical results indicate that the reliability method based on the LSSVM for classification has higher accuracy and requires less computational cost than the SVM method.