一种新的正交参数选优法及其在非线性回归分析中的应用  

A NEW ORTHOGONAL OPTIMIZING PARAMETERS METHOD AND THE APPLICATION IN NONLINEAR REGRESSION ANALYSIS

作　　者：孙丰荣[1] 宋好好[1] 张明强[1] 刘利[1] 王长宇[1] 

机构地区：[1]山东大学信息科学与工程学院,济南250100

出　　处：《中国生物医学工程学报》2004年第3期215-221,214,共8页Chinese Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目 ( 60 0 72 0 2 2 )

摘　　要：非线性回归分析是工程中经常采用的一种用来估计数学模型参数的方法 ,该方法能否顺利运用与参数初始值的选择有极大关系。本研究提出一种新的正交参数选优法阻尼正交表法 ,它不仅可以保证非线性回归分析算法的顺利收敛 ,而且能够显著提高后者的收敛速度 ,进而极大改善非线性回归分析算法的应用性能。本研究的数值试验及心肌造影超声心动图定量分析应用实例表明 ,作为对传统正交参数选优法的一种改进 。Nonlinear regression analysis is usually used to estimate the parameters of a mathematical model in engineering. Selecting proper initial values for the parameters is a very key step which determines wether the consequent analysis successful or not. In this paper we present a new orthogonal optimizing parameters method, damp orthogonal array method, which not only makes the algorithm of nonlinear regression analysis convergent, but also accelerates the convergence of the algorithm notably, and consequently, improves the applied property of the algorithm of nonlinear regression analysis greatly. The numerical experiment and the example of applied quantitative analysis to myocardial contrast echocardiography (MCE) indicate that damp orthogonal array method has wide perspective of applications in science and engineering calculation and signal and information processing.

关 键 词：正交表 非线性回归分析 阻尼因子 心肌造影超声心动图 

分 类 号：R44[医药卫生—诊断学] TP399[医药卫生—临床医学]