【摘要】 用原子吸收光谱法测定青海土族、藏族和回族青年人体头发中的钙、铁、锌、铜、镁、锰和镉等7种元素的含量,用支持向量分类法比较研究。表明,在3个民族的头发之间,7种元素含量的综合水平存在着较显著的差别,其判别函数可以用于判别和预测这三个民族。并用留一法检验其预报能力。计算表明:支持向量机算法结果优于Fisher法。更多还原

【Abstract】 The concentration of Ca,Fe,Zn,Cu,Mg,Mn and Cd in the hair of young people from Tu,Zang and Hui Nationalities of QingHai were determined by atomic absorption spectrophotometry(AAS).A data matrix of concentration of elements existing in the hair from those three nationalities is evaluated comprehensively by using support vector classification(SVC).The results showed that there are considerable differences among these nationalities.The function of judgment model was used to classify and predict samples of Zang,Tu and Hui Nationalities.The cross validation by leaving-one method has been used to compare the prediction ability of support vector machine method with Fisher method.It has been found that the prediction result by support vector machine is better than that of Fisher method.更多还原