...
首页> 外文期刊>Журнал аналитической химии >Estimating parameters of optical membrane pH-sensors using artificial neural networks
【24h】

Estimating parameters of optical membrane pH-sensors using artificial neural networks

机译:使用人工神经网络估计光学膜pH传感器的参数

获取原文
获取原文并翻译 | 示例
           

摘要

Artificial neural networks were used for describing sensing elements of optical membrane pH-sensors with covalently immobilized acid-base indicators and for predicting their parameters. With a training sample of a small size and a limited amount of experimental data, it is reasonable to use a multilayer network that contains several hidden layers. The starting parameters were combined into separate input blocks describing protolytic and absorption properties of immobilized indicators land taking into account the presence of hydrophilic groups in their molecules, the thickness of the absorbing layer in the membrane, and dynamic parameters. It is demonstrated that the neural network can be taught and used for predicting the dynamic and absorption properties of sensing elements. It is proposed to perform a chemical interpretation of calculated results based on an analysis of the matrices of weights.
机译:人工神经网络用于描述具有共价固定的酸碱指示剂的光学膜pH传感器的传感元件,并预测其参数。对于小规模的训练样本和有限的实验数据,使用包含多个隐藏层的多层网络是合理的。起始参数被组合到单独的输入块中,这些输入块描述了固定化指示剂分子的蛋白水解和吸收特性,同时考虑到其分子中是否存在亲水基团,膜中吸收层的厚度以及动态参数。证明了神经网络可以被教导并用于预测传感元件的动态和吸收特性。建议基于权重矩阵的分析对计算结果进行化学解释。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号