基于遗传算法的神经网络对难溶硫化物K_(sp)的预测

采用遗传算法训练神经网络的权重系数 ,并将该神经网络用于对 13种难溶硫化物Ksp的预测 ,预测Ksp值和实验Ksp值的相关系数为 0 .9985 7,结果表明基于遗传算法的神经网络用于难溶硫化物Ksp研究的可行性     

小波神经网络-遗传算法用于2-(9-咔唑)乙基氯甲酸酯衍生化氨基酸的胶束电动力学色谱分离优化

将小波神经网络和遗传算法应用到2-(9-咔唑)-乙基氯甲酸酯衍生化氨基酸的胶束电动力学色谱分离优化。小波神经网络结合正交试验设计用于分离过程的多因素模型建立。以训练好的小波神经网络模型为目标函数,采用实数编码的遗传算法搜寻确定最佳分离条件,在此条件下分离得到的归一化分离度积与正交试验设计中最佳条件相比,提高了12．5％。     

基于正则化网络-遗传算法的属性筛选及其在化学模式识别中的应用

采用贝叶斯正则化方法训练，以得到推广性优良的神经网络，并提出启发性的遗传算法。通过灵敏度分析对正则化网络实施剪枝，从而在高维模式中筛选出能代表其分类特性的最小最优属性特征子集。此方法应用于高维留兰香模式的属性筛选与模式分类，效果良好，明显优于其它方法。     

基于遗传算法结合神经网络的航空润滑油粘度近红外光谱分析

研究了基于遗传算法(GA)的波长选择方法结合反向传播神经网络(BP-ANN)建模用于在用航空润滑油-40℃运动粘度的近红外光谱分析。采集样品光谱经均值中心化和SavitzkyGolay平滑求导法预处理后,通过分段组合建模初选最优波段,利用遗传算法进一步筛选了对粘度预测敏感的波长点建模。该波长选择方法与相关系数法相比,所建模型预测准确度高。在建模采用的非线性BP-ANN法中,先通过主成分分析(PCA)分解光谱数据,将得分矩阵输入3层神经网络训练,通过参数优化建立最优模型。所建模型对8个在用油进行分析,各预测值与标准值的相对误差均低于2%,并且经t检验不存在显著性差异,模型预测能力较强,应用于在用润滑油质量的快速分析效果好,为油品在线监控提供了参考。     

遗传算法-贝叶斯正则化BP神经网络拟合滴定糖蜜中有机酸

分别用常规BP神经网络、贝叶斯正则化BP神经网络及遗传算法-贝叶斯正则化BP神经网络,对多组分有机酸的滴定数据进行主成分非线性拟合.结果显示,贝叶斯正则化能限制网络权值,避免过拟合;遗传算法则使网络的全局优化能力和稳健性提高.对26个测试样本中的乙酸、乳酸、草酸、琥珀酸、柠檬酸和乌头酸6种组分,以及柠檬酸和乌头酸的总量...     

辨识药物定量构效关系的模糊神经网络方法研究

提出一种基于遗传算法的新型模糊神经网络方法,用于计算Benzodiazepines(BZs)类药物的定量构效关系.这类模糊神经网络综合了神经网络、遗传算法与模糊逻辑的各自优势,具有优良的定量构效关系辨识能力,其学习速度较快,不易陷入局部最小区域;网络知识以模糊语言变量的形式加以表达,不仅易于理解,而且能有效地利用已有的专家经验.一旦通过学习获得规律后,不仅能很好地预测化合物的活性,还能对后续的药物分子设计提供有益的理论指导.     

纤维堆囊菌发酵液中埃博霉素含量的HPLC法分析

采用反馈神经网络结合遗传算法(BPANN-GA)对高效液相色谱(HPLC)法同时测定纤维堆囊菌(Sorangium cellulosum)代谢物中埃博霉素A(Epo A)和埃博霉素B(Epo B)含量的条件进行优化, 采用均匀设计(U₁₂³)方案对流动相中乙腈的体积分数、色谱柱温度和流动相的pH等3个因素进行实验设计; 以色谱函数(COF)值为优化指标, 运用双层反馈神经网络建立色谱优化函数(COF)值, 考察因素间的预测模型, 采用Levenberg-Marquardt backpropagation算法对所建立的神经网络预测模型进行训练, 以逼近度(D_a)为优化参数, 选择预测模型的最适隐含层节点数. 最优预测模型预测的COF值与实验值之间的相关系数(R)达到0.98165, 采用遗传算法在实验考察范围内进行全局寻优, 得到最优化的HPLC分析条件: 流动相中乙腈体积分数为29.2%, 色谱柱温度为34 ℃, 流动相pH为4.23. 在此最优条件下对纤维堆囊菌代谢产物进行HPLC分析, 结果表明, 该方法对两种埃博霉素色谱峰均具有较好的分离度.     

近红外光谱法用于纯化过程中鞣花酸含量的监控

采用近红外光谱技术结合遗传算法优化的小波神经网络,对大孔树脂纯化过程中橄榄果中的鞣花酸含量进行监控。通过小波变换对光谱进行去噪、压缩,作为人工神经网络的输入,同时以遗传算法优化神经网络的权值与阈值,并与常用的偏最小二乘(PLS)线性模型的建模效果进行比较。实验结果表明,两者都能够较准确的预测鞣花酸的含量,相对而言,人工神经网络(ANN)效果较好。     

基于粒子群优化算法的神经网络在农药定量构效关系建模中的应用

神经网络模型能有效模拟非线性输入输出关系,但其常规训练算法为BP或其它梯度算法,导致训练时间较长且易陷入局部极小点。本实验探讨用粒子群优化算法训练神经网络,并应用到苯乙酰胺类农药的定量构效关系建模中,对未知化合物的活性进行预测来指导新药的设计和合成。仿真结果表明,粒子群优化算法训练的神经网络不仅收敛速度明显加快,而且其预报精度也得到了较大的提高。     

遗传神经网络分光光度法同时测定低合金钢中钛、钼和钨

构造遗传算法的多组分适应度函数,应用遗传算法自适应概率搜索能力优化神经网络结构,使网络结构和参数与输入数据达到最优匹配,建立用于多组分同时测定的遗传神经网络.在钛(钼、钨)-二溴羟基苯基荧光酮-乳化剂OP同时测定显色体系中,钛、钼和钨配合物的表观摩尔吸光率分别为1.03×105,1.31×105,1.21×105L·moL-1·cm-1.应用遗传神经网络(GA-ANN)分光光度法同时测定低合金钢标准样品中钛、钼和钨.     

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.     

Prediction of Programmed-temperature Retention Values of Naphthas by Artificial Neural Networks

Abstract

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.     

Prediction of programmed-temperature retention values of naphthas by artificial neural networks

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.     

Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

In this research, a process for developing normal-phase liquid chromatography solvent systems has been proposed. In contrast to the development of conditions via thin-layer chromatography (TLC), this process is based on the architecture of two hierarchically connected neural network-based components. Using a large database of reaction procedures allows those two components to perform an essential role in the machine-learning-based prediction of chromatographic purification conditions, i.e., solvents and the ratio between solvents. In our paper, we build two datasets and test various molecular vectorization approaches, such as extended-connectivity fingerprints, learned embedding, and auto-encoders along with different types of deep neural networks to demonstrate a novel method for modeling chromatographic solvent systems employing two neural networks in sequence. Afterward, we present our findings and provide insights on the most effective methods for solving prediction tasks. Our approach results in a system of two neural networks with long short-term memory (LSTM)-based auto-encoders, where the first predicts solvent labels (by reaching the classification accuracy of 0.950 ± 0.001) and in the case of two solvents, the second one predicts the ratio between two solvents (R² metric equal to 0.982 ± 0.001). Our approach can be used as a guidance instrument in laboratories to accelerate scouting for suitable chromatography conditions.     

Application of artificial neural networks to the classification of soils from São Paulo State using near-infrared spectroscopy

This paper describes how artificial neural networks can be used to classify multivariate data. Two types of neural networks were applied: a counter propagation neural network (CP-ANN) and a radial basis function network (RBFN). These strategies were used to classify soil samples from different geographical regions in Brazil by means of their near-infrared (diffuse reflectance) spectra. The results were better with CP-ANN (classification error 8.6%) than with RBFN (classification error 11.0%).     

Prediction of molecular-dynamics simulation results using feedforward neural networks: reaction of a C2 dimer with an activated diamond (100) surface

A new approach involving neural networks combined with molecular dynamics has been used for the determination of reaction probabilities as a function of various input parameters for the reactions associated with the chemical-vapor deposition of carbon dimers on a diamond (100) surface. The data generated by the simulations have been used to train and test neural networks. The probabilities of chemisorption, scattering, and desorption as a function of input parameters, such as rotational energy, translational energy, and direction of the incident velocity vector of the carbon dimer, have been considered. The very good agreement obtained between the predictions of neural networks and those provided by molecular dynamics and the fact that, after training the network, the determination of the interpolated probabilities as a function of various input parameters involves only the evaluation of simple analytical expressions rather than computationally intensive algorithms show that neural networks are extremely powerful tools for interpolating the probabilities and rates of chemical reactions. We also find that a neural network fits the underlying trends in the data rather than the statistical variations present in the molecular-dynamics results. Consequently, neural networks can also provide a computationally convenient means of averaging the statistical variations inherent in molecular-dynamics calculations. In the present case the application of this method is found to reduce the statistical uncertainty in the molecular-dynamics results by about a factor of 3.5.     

Peptide sequence determination from high-energy collision-induced dissociation spectra using artificial neural networks

This paper reports a newly developed technique that uses artificial neural networks to aid in the automated interpretation of peptide sequence from high-energy collision-induced dissociation (CID) tandem mass spectra of peptides. Two artificial neural networks classify fragment ions before the commencement of an iterative sequencing algorithm. The first neural network provides an estimation of whether fragment ions belong to 1 of 11 specific categories, whereas the second network attempts to determine to which category each ion belongs. Based upon numerical results from the two networks, the program generates an idealized spectrum that contains only a single ion type. From this simplified spectrum, the program’s sequencing module, which incorporates a small rule base of fragmentation knowledge, directly generates sequences in a stepwise fashion through a high-speed iterative process. The results with this prototype algorithm, in which the neural networks were trained on a set of reference spectra, suggest that this method is a viable approach to rapid computer interpretation of peptide CID spectra.     

氢键碱度的神经网络法计算

氢键在生命科学和化学等领域均起着十分重要的作用.化合物可以通过提供质子和接受质子等两种方式与其它化合物形成分子间氢键,其形成氢键的能力分别称为氢键酸度（hydrogen-bondacidity）和氢键碱度(hydrogen-bondbasicity).可以用正辛醇／水分配系数和环己烷／水分配系数的对数差（ΔlogP）[1]、溶剂化显色参数[2－3]等表示化合物形成氢键的能力,其中应用较多的是Abraham等[4]提出的总氢键酸度（）和总氢键碱度（）.但由于和要通过实验得到,繁琐不便,限制了它们的广泛应用.本文用神经网络法研究了理论计算得到的量子化学参数与之间的相…     

The study of the relationship between the new topological index A(m) and the gas chromatographic retention indices of hydrocarbons by artificial neural networks

The newly developed topological indices A_m1-A_m3 and the molecular connectivity indices ^mX were applied to multivariate analysis in structure-property correlation studies. The topological indices calculated from the chemical structures of some hydrocarbons were used to represent the molecular structures. The prediction of the retention indices of the hydrocarbons on three different kinds of stationary phase in gas chromatography can be achieved applying artificial neural networks and multiple linear regression models. The results from the artificial neural networks approach were compared with those of multiple linear regression models. It is shown that the predictive ability of artificial neural networks is superior to that of multiple linear regression method under the experimental conditions in this paper. Both the topological indices ²X and A_m1 can improve the predicted results of the retention indices of the hydrocarbons on the stationary phase studied.