Quantitative Structure-retention Relationship Analysis of Nanoparticle Compounds by GA-PLS,GA-KPLS and L-M ANN

• 作者: Abbas Farmany Hadi Noorizadeh Mehrab Noorizadeh
• 来源期刊: 结构化学
• 学科: 化学
• 关键词: 人工神经网络 偏最小二乘法 纳米化合物 遗传算法 定量结构 气相色谱系统 神经网络模型 金纳米粒子
• 年，卷（期）: 2012,（4）
• 页码范围: 569-573
• 页数: 5页
• 分类号: O657.3|TP183
• 语种: 英文

摘要

Genetic algorithm and partial least square(GA-PLS),kernel PLS(KPLS) and Levenberg-Marquardt artificial neural network(L-M ANN) techniques were used to investigate the correlation between retention time(RT) and descriptors for 15 nanoparticle compounds obtained by the comprehensive two-dimensional gas chromatography system(GC × GC).Application of the dodecanethiol monolayer-protected gold nanoparticle(MPN) column was for a high-speed separation as the second column of GC × GC.The L-M ANN model with the final optimum network architecture of [13-5-1] gave a significantly better performance than the other models.This is the first research on the quantitative structure-retention relationship(QSRR) of nanoparticle compounds using the GA-PLS,GA-KPLS and L-M ANN.