RBF-LBF串联神经网络模式分类法快速测定微量甲醇  

Rapidly identifying micro-amount methanol by the pattern classification method using RBF-LBF cascade neural network

作　　者：高大启[1] 

机构地区：[1]江苏理工大学食品科学研究所,镇江212013

出　　处：《分析仪器》1997年第4期17-20,共4页Analytical Instrumentation

摘　　要：提出了由两层径基函数（RBF）和两层线性基本函数（LBF）网络组成的串联神经网络模式分类方法。对气敏传感器阵列测试八种浓度甲醇溶液挥发蒸汽所得到的样本集进行分类实验表明，这种模式分类方法速度快，分类精度高，优于前向三层径基函数网络和线性基本函数网络模式分类方法。A cascade neural network composed of double-layer radial basis function (RBF) and linear basis function (LBF) is proposed for pattern classification . Experimental results for eight different concentrations of vapor of methanol solution measared by an odor sensor array show that the new pattern classification method has higher analytical speed and claseification precision, and is better than the pattrm claSSfication metnds of fedforward three-layer RBF network and LBF network

关 键 词：径基函数 线性基本函数 神经网络 甲醇 微量 

分 类 号：O623.411[理学—有机化学]