人工神经网络方法预测气相色谱保留值

本文运用一典型的人工神经网络模型－“反向传播“模型的改进形式，研究了诱导效应指数Ｉ，摩尔折射度Ｒｏ，疏水亲脂参数ＩｇＰ，以及分子联通性指数与气象色谱保留行为的关系，实现了对色谱保留植的预测。神经网络预测模型的最大相对误差不超过８．７％。结果表明，该方法性能良好，可望成为色谱保留值预测的有效手段。     

用人工神经网络处理谷物成分分析

本文用人工神经网络处理谷物的付立叶变换近红外漫反射光谱,对谷物中含量在10~(-1)～10~(-3)的蛋白质、脂肪和6种人体必需氨基酸定量分析数据进行了解析,分析结果与经典化学方法没有系统偏差,且优于逐步回归分析法的结果。     

人工神经网络及其在分析化学中的应用

人工神经网络是一种新兴的计算方法，有着广阔的发展前途，目前在分析化学领域已经有了多方面的应用。本文简要介绍了人工神经网络的原理及其在分析化学中的应用。     

Establishing structure-property correlations and classification of base oils using statistical techniques and artificial neural networks

The present paper describes various classification techniques like cluster analysis, principal component (PC)/factor analysis to classify different types of base stocks. The API classification of base oils (Group I-III) has been compared to a more detailed NMR derived chemical compositional and molecular structural parameters based classification in order to point out the similarities of the base oils in the same group and the differences between the oils placed in different groups. The detailed compositional parameters have been generated using and nuclear magnetic resonance (NMR) spectroscopic methods. Further, oxidation stability, measured in terms of rotating bomb oxidation test (RBOT) life, of non-conventional base stocks and their blends with conventional base stocks, has been quantitatively correlated with their NMR and elemental (sulphur and nitrogen) data with the help of multiple linear regression (MLR) and artificial neural networks (ANN) techniques. The MLR based model developed using NMR and elemental data showed a high correlation between the ‘measured’ and ‘estimated’ RBOT values for both training (R=0.859) and validation (R=0.880) data sets. The ANN based model, developed using fewer number of input variables (only NMR data) also showed high correlation between the ‘measured’ and ‘estimated’ RBOT values for training (R=0.881), validation (R=0.860) and test (R=0.955) data sets.     

高温超导体制备条件的人工神经网络识别

高温超导体的制备条件要求严格,其掺杂量大小、烧结温度控制等都直接影响实验样本的超导性质。近几年高温超导研究已积累大量实验数据,如何应用人工智能方法处理这些数据寻找更好的合成条件颇有意义。人工神经网络方法在许多领域己显示其处理复杂数据和模式识别的优越性,但尚未应用到化合物制备研究方面。本文对此作了初步尝试。     

ANN原子参数法预报合金相晶型及晶格常数

运用人工神经网络方法，以二元合金组成元素的电子结构为基本特征，对二元合金相晶型作了区分，进一步对其晶格常数作了预报，结果令人满意。     

Repeatability and pattern recognition of bacterial fatty acid profiles generated by direct mass spectrometric analysis of in situ thermal hydrolysis/methylation of whole cells

Direct CI mass spectrometry profiling of fatty acid methyl esters (FAMEs) from in situ thermal hydrolysis/methylation (THM) of whole bacterial cells with tetramethylammonium hydroxide (TMAH) has been demonstrated as a potential method for real time and fieldable detection/identification of microorganisms. Bacillus anthracis (Ames), Yersinia pestis (Nair. Kenya), Vibrio cholerae (E1 Tor), Brucella melitensis (Abortus wild) and Francisella tularensis (LVS vaccine) were profiled by this method during a 10-month period. Repeatability of the in situ FAME data was calculated using one-way analysis of variance (ANOVA) and a t-test. Artificial neural network (ANN) and multivariate statistics of the FAME profiles were also compared for bacterial identification/classification. Equivalent results were obtained with a multivariate rule building expert system (MuRES) and the ANN. However, the ANN analysis required much less computer time and was deemed the best choice for this application. In situ THM FAME profiles of the bacterial samples provided comparable results with those obtained from the Microbial Identification System (MIDI) (Newark, DE) wet chemistry-gas chromatographic based system.     

Retention modeling and simultaneous optimization of pH value and gradient steepness in RP‐HPLC using feed‐forward neural networks

A novel approach is proposed for the simultaneous optimization of mobile phase pH and gradient steepness in RP‐HPLC using artificial neural networks. By presetting the initial and final concentration of the organic solvent, a limited number of experiments with different gradient time and pH value of mobile phase are arranged in the two‐dimensional space of mobile phase parameters. The retention behavior of each solute is modeled using an individual artificial neural network. An “early stopping” strategy is adopted to ensure the predicting capability of neural networks. The trained neural networks can be used to predict the retention time of solutes under arbitrary mobile phase conditions in the optimization region. Finally, the optimal separation conditions can be found according to a global resolution function. The effectiveness of this method is validated by optimization of separation conditions for amino acids derivatised by a new fluorescent reagent.     

An investigation into the construction of molecular models by the template joining method

Summary The results of a wide-ranging investigation into some of the different methods available for performing the joining of templates to build molecular models show that the choice of algorithm can significantly affect the quality of the results obtained, and different algorithms are most suited to particular categories of join.     

Trehalose-based cyclodextrin analogs: cyclotrehalans (CTs)

A new concept for the de novo synthesis of artificial glyconanocavities is presented. The use of alternating α,α′-trehalose building blocks and (thio)urea segments allows the efficient synthesis of a new family of cyclooligosaccharides, namely cyclotrehalans (CTs), featuring a convex-shaped cavity with an apolar environment. CTs are designed to exhibit molecular inclusion abilities similar to that of cyclodextrins (CDs). Contrary to CDs, CTs expose the monosaccharide β-face to the inner cavity, while the (thio)urea tethers provides some conformational adaptability. High-yielding syntheses of a series of CTs and a preliminary evaluation of their inclusion properties are reported.