首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 140 毫秒
1.
径向基函数神经网络用于重叠色谱峰解析   总被引:2,自引:0,他引:2  
李一波  黄小原  沙明  孟宪生 《色谱》2001,19(2):112-115
 在高斯基径向基函数神经网络 (RBFNN)学习算法中引入了鲁棒性和随机全局寻优的两阶段遗传算法 :结构学习和参数优化。通过两阶段学习算法的交替使用 ,使网络具有结构自学习和参数优化的能力 ,而后将网络应用于组分数未知的重叠色谱峰解析。该方法具有不需人为干预 ,可自动确定网络结构即组分数的优点 ;并且解析精度较高 ,适用于多组分重叠色谱峰的解析 ;对完全重叠色谱峰也具有良好的解析能力。  相似文献   

2.
基于傅立叶变换的人工神经网络近红外光谱定量分析法   总被引:2,自引:0,他引:2  
将原始光谱进行一定的预处理后,以其快速傅立叶变换FFT的前N个系数作为人工神经网络(ANN)的输入量,不仅确保了大量有用信息参与模型的建立,同时实现了优越的滤波功能。以汽油的辛烷值和煤粉干燥基高位发热量(Qgr.d)的近红外光谱建模,当采用前20个FFT系数的傅立叶变换-径向基网络(FFT-RBF)时,辛烷值模型的预测误差均方根(RMSEP)可达0.152,相关系数为0.976,当采用前30个FFT系数时,快速FFT-RBF煤粉干燥基高位发热量模型的RMSEP为0.256,相关系数为0.923,说明FFT-RBF模型有着很好的预测能力。研究表明基于傅立叶变换的人工神经网络近红外光谱定量分析法,特别是FFT-RBF具有良好的预测能力。  相似文献   

3.
采用水平衰减全反射(HATR)傅里叶变换红外光谱法(FTIR)测定了SD大鼠胰腺正常组织与非正常组织的谱图,提出了一种新的基于FTIR的连续小波特征提取与径向基人工神经网络分类方法以提高FTIR对早期SD大鼠胰腺癌的诊断准确率。利用连续小波多分辨率分析法提取FTIR特征量,对于提取的特征量采用径向基函数神经网络进行模式分类。对SD大鼠的胰腺正常组织、早期癌组织及进展期癌组织的FTIR,利用连续小波多分辨率分析法提取9个特征量,进行RBF神经网络分类判断。当目标误差为0.01,径向基函数的分布常数为5时,网络达到最优化,总的正确识别率为96.67%。并对影响分类结果的网络参数、目标误差和分布常数对分类样品的影响做了讨论。实验结果表明:此方法对早期胰腺癌具有较高的诊断率。  相似文献   

4.
蛋白质二级结构预测的人工神经网络方法研究   总被引:2,自引:0,他引:2  
本文比较了五种神经网络方法预测蛋白质二级结构的准确率,并做出初步评价。五种神经网络分别是:误差反传前向网络(BP),径向基函数网络(RBF),广义回归神经网络(GRNN),串并联叠层网络(CF),Elman网络(ELM)。结果显示:GRNN的预测准确率达85.7%,优于其它网络。本文还讨论了训练集样本数及参数的优化对GRNN预测准确率的影响。  相似文献   

5.
自适应模糊偏最小二乘方法在药物构效关系建模中的应用   总被引:2,自引:0,他引:2  
作为一种局部逼近方法,自适应神经模糊推理系统(ANFIS)适于为药物定量构效关系(QSAR)建模。描述药物分子结构的参数较多,常存在耦合关系,会增加建模难度,并影响模型的预报性能。为此,将ANFIS和偏最小二乘(PLS)相结合,先由PLS从样本数据中提取成分,再由ANFIS实现每对成分间的非线性映射,并基于输出误差进一步修正所提取的成分,使之对因变量具有最优的解释能力,由此构建为EB-AFPLS方法。该法已成功地应用于HIV-1蛋白酶抑制剂的QSAR建模,效果良好,显示出很强的学习能力,所建模型的预报性能也优于其它方法。  相似文献   

6.
采用Hyperchem 8.0软件,通过分子动力学MM+和半经验AM1算法,优化并计算得到30种1,4-二氢吡啶衍生物的17种量子化学参数。运用Statistica 8.0软件中的主成分分析法,结合线性回归分析法,筛选出3个最佳参数与1,4-二氢吡啶衍生物的抗结核活性关联,构建定量构效关系(QSAR)模型。所建多元线性回归方程的相关系数R2为0.75,留一法交叉检验系数q2为0.72,活性实验值与预测值相关性较好。采用该模型设计并制备得到1种具有良好水溶性和潜在抗结核活性的N3,N5-二(对磺酸钾基)苯基-2,6-二甲基-3,5-二甲酰氨基-1,4-二氢吡啶(TM),用1H NMR、IR、MS和元素分析表征结构,并考察了紫外和荧光性能。良好的稳定性和预测能力使该QSAR模型有望用于结核病候选药物的筛选。  相似文献   

7.
冯长君  何红梅  李靖 《化学通报》2019,82(10):946-949
基于比较分子力场分析(CoMFA)方法建立21种新型三唑并噻二唑衍生物对PTP1B的抑制活性(pMP)的三维定量构效关系(3D-QSAR)。训练集中17个化合物用于建立预测模型,测试集5个化合物作为模型验证。已建立的CoMFA模型的交叉验证系数(Rcv2)、非交叉验证系数(R2)分别为0.432、0.975,说明所建模型具有较强的稳定性和良好的预测能力。该模型中立体场、静电场贡献率依次为59.2%、40.8%,表明影响抑制活性(pMP)的主要因素是取代基的空间位阻及疏水性,其次是取代基的氢键及配位作用。基于此研究结果,设计了3个具有较高抑制活性的新化合物,有待医学实验验证。  相似文献   

8.
谭福能  何媛媛  隋卫平 《应用化学》2014,31(12):1399-1404
将壳聚糖改性为(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖(2-H-3-B-P-HPCS),并以(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖和聚乙二醇(PEG)为原料制备(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖/聚乙二醇互穿网络凝胶,研究了(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖浓度、聚乙二醇的用量、交联剂戊二醛用量、反应温度对该凝胶溶胀性能的影响。通过红外光谱分析和扫描电子显微镜的方法比较了壳聚糖、(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖和(2-羟基-3-丁氧基)丙基-羟丙基壳聚糖/聚乙二醇互穿网络凝胶结构和形态上的不同。以阿昔洛韦为模型药物研究了其释药性能。结果表明,该凝胶均具有良好的溶胀性、pH敏感性和药物缓释作用,有望用作新型的药物载体。  相似文献   

9.
曹晨忠  霍平  高硕  周再春 《色谱》2005,23(4):329-335
 将单取代烷烃RX(X=卤素,OH,SH,NH2等)分子结构分为两个区域(R和X)来提取分子结构参数,从三方面影响因素(烷基R、取代基X、R与X的相互作用)来定量关联RX的气相色谱保留时间。实验测定了37种单取代烷烃RX的气相色谱保留时间,并以键连接矩阵特征根之和EVM、烷基极化效应指数PEI、取代基质量分数w和取代基上氢原子所带部分正电荷ΔNH 4个参数为变量,建立了定量结构-保留相关模型。该模型具有良好的预测能力和外推能力,对醇在不同色谱柱上的保留指数进行了预测,结果与测定值符合得较好。  相似文献   

10.
冯长君  杨杰元  杨雪颖  杨沛艳  冯惠 《化学通报》2022,85(10):1249-1254
通过多元线性回归和人工神经网络方法建立66种多氯联苯生物降解速率常数(K1)的定量构效关系(QSAR). 基于电性距离矢量(Mk),建立了lnK1的最佳三参数(M91、M25和M15)线性模型,其传统相关系数(R2)、交叉验证系数(Rcv2)分别为0.833、0.809。经R2、Rcv2、VIF、FIT、AIC检验,所建模型具有较强的稳定性和良好的预测能力. 将M91、M25、M15作为人工神经网络的输入层结点,采用3:10:1的网络结构,利用BP算法获得了一个令人满意的lnK1模型,训练集、验证集、测试集和总体的R2依次为0.991、0.995、0.997和 0.993。与多元线性回归模型相比,非线性lnK1-BP模型具有更好的预测能力。这两种回归方法相辅相成,线性回归方法为神经网络模型提供了具体的物理解释,而神经网络方法为线性模型提供了更准确的预测结果。  相似文献   

11.
Determination of benzo[a]pyrene (BaP) in cigarette smoke can be very important for the tobacco quality control and the assessment of its harm to human health. In this study, mid-infrared spectroscopy (MIR) coupled to chemometric algorithm (DPSO-WPT-PLS), which was based on the wavelet packet transform (WPT), discrete particle swarm optimization algorithm (DPSO) and partial least squares regression (PLS), was used to quantify harmful ingredient benzo[a]pyrene in the cigarette mainstream smoke with promising result. Furthermore, the proposed method provided better performance compared to several other chemometric models, i.e., PLS, radial basis function-based PLS (RBF-PLS), PLS with stepwise regression variable selection (Stepwise-PLS) as well as WPT-PLS with informative wavelet coefficients selected by correlation coefficient test (rtest-WPT-PLS). It can be expected that the proposed strategy could become a new effective, rapid quantitative analysis technique in analyzing the harmful ingredient BaP in cigarette mainstream smoke.  相似文献   

12.
The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.  相似文献   

13.
Near-infrared (NIR) spectroscopy, in combination with chemometrics, enables nondestructive analysis of solid samples without time-consuming sample preparation methods. A new method for the nondestructive determination of compound amoxicillin powder drug via NIR spectroscopy combined with an improved neural network model based on principal component analysis (PCA) and radial basis function (RBF) neural networks is investigated. The PCA technique is applied to extraction relevant features from lots of spectra data in order to reduce the input variables of the RBF neural networks. Various optimum principal component analysis-radial basis function (PCA-RBF) network models based on conventional spectra and preprocessing spectra (standard normal variate (SNV) and multiplicative scatter correction (MSC)) have been established and compared. Principal component regression (PCR) and partial least squares (PLS) multivariate calibrations are also used, which are compared with PCA-RBF neural networks. Experiment results show that the proposed PCA-RBF method is more efficient than PCR and PLS multivariate calibrations. And the PCA-RBF approach with SNV preprocessing spectra is found to provide the best performance.  相似文献   

14.
A differential kinetic spectrophotometric method was researched and developed for the simultaneous determination of iron and aluminium in food samples. It was based on the direct reaction kinetics and spectrophotometry of these two metal ions with Chrome Azurol S (CAS) in ethylenediamine-hydrochloric acid buffer (pH 6.3). The results were interpreted with the use of chemometrics. The kinetic runs and the visible spectra of the complex formation reaction were studied between 540 and 750 nm every 30 s over a total period of 285 s. A set of synthetic metal mixture samples was used to build calibrations models. These were based on the spectral and kinetic two-way data matrices, which were processed separately by the radial basis function-artificial neural network (global RBF-ANN) method. The prediction performance of these models was poorer than that from the combined kinetic-spectral three-way array, which was similarly processed by the same method (% relative prediction error (RPET) = 5.6). These results demonstrate that improved predictions can be obtained from the data array, which has more information, and that appropriate chemometrics methods can enhance analytical performance of simple techniques such as spectrophotometry.Other chemometrics models were then applied: N-way partial least squares (NPLS), parallel factor analysis (PARAFAC), back propagation-artificial neural network (BP-ANN), single radial basis function-artificial neural network (RBF-ANN), and principal component neural network (PC-RBF-ANN). There was no substantial difference between the methods with the overall %RPET range being 5.0-5.8. These two values corresponded to the NPLS and BP-ANN models, respectively. The proposed method was applied for the determination of iron and aluminium in some commercial food samples with satisfactory results.  相似文献   

15.
Ni Y  Wang Y  Kokot S 《Talanta》2006,69(1):216-225
A linear sweep stripping voltammetric (LSSV) method has been researched and developed for simultaneous quantitative determination of mixtures of three antibiotic drugs, ofloxacin, norfloxacin and ciprofloxacin. It relies on reductive reaction of the antibiotics at a mercury electrode in a Britton-Robinson buffer (pH 3.78). The voltammograms of these three compounds overlap strongly, and show non-linear character. Thus, it is difficult to analyse the compounds individually in their mixtures. In this work, chemometrics methods such as classical least squares (CLS), principal component regression (PCR), partial least squares (PLS) and radial basis function-artificial neural networks (RBF-ANN) were applied for the simultaneous determination of these compounds. The prediction performance of the calibration models constructed on the basis of these methods was compared. It was shown that satisfactory quantitative results were obtained with the use of the RBF-ANN calibration model relative prediction error (RPET) of 8.1% and an average recovery of 101%. This method is able to accommodate non-linear data quite well. The proposed analytical method based on LSSV was applied for the analysis of ofloxacin, norfloxacin and ciprofloxacin antibiotics in bird feedstuffs and their spiked samples, as well as in eye drops with satisfactory results.  相似文献   

16.
17.
18.
Hasani M  Emami F 《Talanta》2008,75(1):116-126
Mixtures of 2-, 3-, and 4-nitoroanilines, are simultaneously analyzed with spectrophotometry, based on their different kinetic properties. These nitroanilines react differentially with 1,2-naphtoquinone-4-sulphonate (NQS) at pH 7 in micellar medium to produce colored product. The differential kinetic spectra were monitored and recorded at 500 nm, and the data obtained from the experiments were processed by chemometric approaches, such as back-propagation neural networks (BPNNs), radial basis function neural networks (RBFNNs), and partial least squares (PLS). Experimental conditions were optimized and training the network was performed using principal components (PCs) of the original data. A set of synthetic mixtures of nitroanilines was evaluated and the results obtained by the application of these chemometric approaches were discussed and compared. The analytical performance of the models was characterized by relative standard errors. It was found that the artificial neural networks model affords relatively better results than PLS. The proposed method was applied to the determination of considered nitroanilines in water samples.  相似文献   

19.
A new approach is described that is able to predict the most probable metabolic sites on the basis of a statistical analysis of various metabolic transformations reported in the literature. The approach is applied to the prediction of aromatic hydroxylation sites for diverse sets of substrates. Training is performed using the aromatic hydroxylation reactions from the Metabolism database (Accelrys). Validation is carried out on heterogeneous sets of aromatic compounds reported in the Metabolite database (MDL). The average accuracy of prediction of experimentally observed hydroxylation sites estimated for 1552 substrates from Metabolite is 84.5%. The proposed approach is compared with two electronic models for P450 mediated aromatic hydroxylation: the oxenoid model using the atomic oxygen and the model using the methoxy radical as a model for the heme active oxygen species. For benzene derivatives, the proposed method is inferior to the oxenoid model and as accurate as the methoxy-radical model. For hetero- and polycyclic compounds, the oxenoid model is not applicable, and the statistical method is the most accurate. Broad applicability and high speed of calculations provide the basis for using the proposed statistical approach for high-throughput metabolism prediction in the early stages of drug discovery.  相似文献   

20.
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号