【摘要】 纸基纳米金检测六价铬(Cr⁶⁺)具有快速、精确、特异性高等优点,纸基颜色变化程度可表征Cr⁶⁺浓度。针对基于纸基纳米金的Cr⁶⁺浓度识别问题,提出以支持向量回归（SVR）模型作为识别算法,合理选择出最优参数训练模型,基于训练的模型对浓度进行识别。实验表明:基于SVR的识别精度明显优于多项式非线性回归识别和BP神经网络识别,采用SVR可实现基于纸基纳米金的Cr⁶⁺浓度精确识别。更多还原

【Abstract】 Nanogold-based membranes is rapid,precise and selective colorimetric sensors for assay of Cr⁶⁺,the variation intensity of color of the membrane can character the concentration of Cr⁶⁺. To identify the concentration,an identification algorithm based on support vector regression（ SVR） model is proposed,the optimal parameters training model is selected,then use the training model to identify the concentration. Experiments demonstrate that the identification precision of the proposed method is higher than polynomial nonlinear regression and BP neural network,the method can achieve precise concentration of Cr⁶⁺identification.更多还原