BP-ANN结合正交试验设计优化大黄总蒽醌醇提工艺

摘要：目的:优化大黄总蒽醌的醇提工艺。方法:采用渗漉法提取大黄总蒽醌,应用HPLC测定其含量并计算大黄总蒽醌提取率。影响渗漉效果的主要因素有乙醇浓度、乙醇用量、渗漉速度,因此选择上述3个因素作为考察因素,按L9（3~4）的试验安排进行提取,以正交试验的9组数据作为训练样本,应用误差反向传播人工神经网络（BP-ANN）进行建模及分析,以大黄总蒽醌提取率作为考察指标,仿真模拟预测大黄总蒽醌最佳醇提工艺参数。结果:正交试验优化的提取工艺为以60%乙醇浸泡24 h,以1 ml·（min·kg）-1的渗漉速度收集10倍量渗漉液,大黄总蒽醌提取率为2.142%;BP-ANN预测的最佳提取工艺为70%乙醇浸泡24 h,以3 ml·（min·kg）-1的渗漉速度收集10倍量渗漉液,大黄总蒽醌提取率为2.380%。验证试验结果表明,BP-ANN优化工艺与正交试验相比,大黄总蒽醌提取率的的增长率为8.03%,与预测值的相对误差为2.77%。结论:BP-ANN优化工艺的提取效果优于正交试验。     

正交实验法优选地锦草中槲皮素提取工艺

目的研究地锦草中槲皮素的最佳提取条件。方法采用正交试验法,以乙醇浓度(A)、溶剂用量(B)、回流时间(C)、回流次数（D）为研究因素,每个因素选取3个水平进行实验。结果因素A和D对槲皮素含量有显著影响;因素B和C则差异无显著性。结论最佳工艺为用10倍量80%乙醇加热回流3次, 每次1.5 h。     

土壤水分特征曲线模型参数识别的多邻域粒子群算法

Van Genuchten模型(简称VG模型)是目前运用最为广泛的土壤水分特征曲线模型,提出适宜的优化算法进行模型参数识别也是一个非常重要的研究方向。针对标准的粒子群算法易陷入局部最优的缺点,给出了一种多邻域粒子群算法,可以有效地克服粒子群算法易陷入局部最优的缺点,并利用该算法对VG模型参数进行识别,最后用所求解的参数对不同类型土壤持水性能进行了试验。数值实验结果表明,多邻域粒子群算法能够有效地应用于VG模型的参数识别,与其它算法相比在性能和精度上都有所提高,而且对参数的取值范围也可以较大地放宽。因此,多邻域粒子群算法可以作为VG模型参数识别的一种新方法。     

基于克隆选择的免疫粒子群优化算法

粒子群优化算法在进化中随种群多样性降低易出现早熟收敛等问题.针对这一问题,在粒子群算法中引入免疫克隆选择算法的思想,提出了基于克隆选择的免疫粒子群优化算法(Immune Particle Swarm Optimization,ImmunePSO),即在算法进化过程中,引入克隆复制算子、克隆高频变异算子、克隆选择算子.成比例克隆复制可以使优良个体得到保护,加快算法收敛;高频变异为新个体的产生提供了新的途径,可以增加种群的多样性;克隆选择算子从所有子代、父代中选择出最优个体,避免算法退化.最后通过对基本测试函数的仿真试验,验证了算法不仅可以增加种群的多样性,加快算法的收敛速度,而且提高了最优解的精度,有效地避免算法陷入到局部极值.     

基于粒子群算法的Web社区发现

Web社区发现技术是提高网络搜索引擎检索质量的重要途径之一.如何给出利用较少先验信息,并能对网络进行高效划分的算法是网络社区发现的关键.传统算法如Wu-Huberman算法虽能对社区进行快速划分,但需先确定分属不同社区的两个节点,Radichi快速分裂算法依赖于网络中存在的三角形的数目,Duch J提出的极值优化算法对初始解非常敏感.本文提出一种基于粒子群优化算法的网络社区发现方法,并用不同规模的网络图Zachary、Krebs和dolphins网络结构对方法进行测试,实验结果表明,该方法在无先验信息的条件下,以较低的时间复杂度,快速、高效地完成对网络社区的划分.     

响应面法优化盐酸水解提取荷叶槲皮素工艺

目的:优化荷叶中槲皮素提取工艺条件。方法:在单因素试验的基础上,以槲皮素提取量为响应值,选择盐酸体积分数、加热温度和加热时间为因素,采用Box-Behnken响应面法设计优化提取工艺。结果:最优提取工艺为11.0%盐酸、加热时间120min、加热温度79.0。在此工艺下荷叶中槲皮素提取量为12.049 6 mg/g,接近预测值11.794 2 mg/g。结论:优化工艺稳定、可行,可为进一步开发应用荷叶槲皮素提供科学依据。     

地锦草总黄酮提取纯化工艺的优化

地锦草为大戟科植物地锦的干燥全草,主要含槲皮素苷及素、山奈素苷及素、地锦草素等黄酮类化合物[1],具有清热解毒、凉血止血等功效,主要用于治疗各种皮肤病、瘙痒、痢疾、肠炎、咯血、吐血、便血、崩漏、外伤出血、湿热黄疸、乳汁不通、痈肿疔疮及跌打肿痛等疾病.为了进一步研究地锦草有效成分,探索其总黄酮提取最适条件,以总黄酮含量为考察指标,采用正交试验设计方法对地锦草总黄酮提取纯化工艺进行了优化.     

正交设计优化分清五淋胶囊剂醇提最佳工艺

目的:为中药分清五淋丸新剂型的研制寻找最佳提取工艺.方法:采用L9(34)正交设计优化提取条件,以高效液相法测定各样品中主药黄柏的有效成分盐酸小檗碱的含量.通过统计学分析确定分清五淋的最佳提取工艺条件.结果:中药分清五淋胶囊最佳提取工艺条件为A1B2C3D2.即药材加入8倍量的60%乙醇提取两次,每次2.5小时.结论:本实验为中药新剂型的研制提供了科学的依据.     

翻白草中槲皮素的提取工艺优化及含量测定

目的:优选翻白草中槲皮素的最佳提取工艺,建立以高效液相色谱法测定其含量的方法。方法:采用超声波提取法,以槲皮素的提取含量为评价指标,以提取时间、料液比、乙醇浓度和提取次数为考察因素,通过正交试验筛选出最佳提取工艺;采用高效液相色谱法测定槲皮素的含量。结果:翻白草中槲皮素的最佳提取工艺为每次提取40min、料液比1∶15、80%的乙醇、提取3次;槲皮素检测浓度在0.004～0.020mg·mL-1(r=0.999 6)范围内与其峰面积积分值呈良好的线性关系,平均加样回收率为100.17%,RSD=2.27%(n=6)。结论:本方法简便、迅速,可为翻白草的进一步开发利用和有效性研究提供理论依据。     

应用人工神经网络优化分离抗菌药物混合物的液相条件

将人工神经网络法应用于抗菌药物高效液相分离条件的优化。采用正交试验法，以流动相中乙腈初始浓度、线性梯度斜率及pH为优化参数，对7种抗菌药物混合体系进行优化。采用误差反向传输方法建立了神经网络权接拓扑模型，预测最佳分离条件，获得了满意的分离结果。     

Predicting the Fine Particle Fraction of Dry Powder Inhalers Using Artificial Neural Networks

Dry powder inhalers are increasingly popular for delivering drugs to the lungs for the treatment of respiratory diseases, but are complex products with multivariate performance determinants. Heuristic product development guided by in vitro aerosol performance testing is a costly and time-consuming process. This study investigated the feasibility of using artificial neural networks (ANNs) to predict fine particle fraction (FPF) based on formulation device variables. Thirty-one ANN architectures were evaluated for their ability to predict experimentally determined FPF for a self-consistent dataset containing salmeterol xinafoate and salbutamol sulfate dry powder inhalers (237 experimental observations). Principal component analysis was used to identify inputs that significantly affected FPF. Orthogonal arrays (OAs) were used to design ANN architectures, optimized using the Taguchi method. The primary OA ANN r² values ranged between 0.46 and 0.90 and the secondary OA increased the r² values (0.53-0.93). The optimum ANN (9-4-1 architecture, average r² 0.92 ± 0.02) included active pharmaceutical ingredient, formulation, and device inputs identified by principal component analysis, which reflected the recognized importance and interdependency of these factors for orally inhaled product performance. The Taguchi method was effective at identifying successful architecture with the potential for development as a useful generic inhaler ANN model, although this would require much larger datasets and more variable inputs.     

应用人工神经网络—遗传算法优化多西紫杉醇微球制备工艺参数

目的优化多西紫杉醇壳聚糖微球的制备工艺参数。方法应用人工神经网络对微球制备工艺参数与考察指标之间的关系进行模型拟合,并结合遗传算法优化微球的制备工艺参数。结果模型参数优化结果为:壳聚糖浓度3.730 8%、乳化剂用量0.500 4 g、油水体积比1.843 3、药载比25.027 7、交联剂用量2.246 5 mL、搅拌乳化时间63.419 1 min、搅拌速率611.922 8 r.min1。考察指标预测结果是:微球的载药量43.653 8%、粒径8.168 5μm、跨距0.594 0。验证实验数据与网络模型优化结果基本吻合。结论应用人工神经网络建模结合遗传法寻优,可以实现多西紫杉醇壳聚糖微球制备工艺参数的优化。     

正交试验联合反向传播人工神经网络优选熄风止动颗粒提取工艺

目的:优选熄风止动颗粒的提取工艺。方法:采用正交试验联合反向传播人工神经网络(BP-ANN)的方法,以天麻素含量与干膏率的综合评分为指标,对熄风止动颗粒提取工艺的加水量、提取次数及提取时间进行优化,最终确定最佳提取工艺。结果:筛选得到最佳提取工艺为处方量药材加水浸泡1 h后,回流提取2次,第1次提取加水14.4倍量(按干药材质量计),第2次提取加水11倍量,每次提取75 min。结论:正交试验联合BP-ANN优选出的提取工艺提取效率高、能耗低、稳定可靠,可为熄风止动颗粒的工业化生产提供实验依据。     

Effects of processing parameters on particle size of ultrasound prepared chitosan nanoparticles: An Artificial Neural Networks Study

The pharmacokinetic properties of chitosan nanoparticles have been shown to mainly depend on its particle size. The aim of this study was to concurrently evaluate and model the effective parameters, namely, chitosan concentration, buffer pH, amplitude and time of sonication, on the particle size of chitosan nanoparticles. Chitosan solutions were prepared and sonicated with different values for the above mentioned parameters. The data were then modeled using artificial neural networks (ANNs). The results illustrated that all four input parameters affect the size of prepared chitosan nanoparticles. While a reverse effect was observed between the size and the buffer pH as well as time and amplitude of sonication, the concentration was found to directly influence the particle size. The optimum condition to obtain the minimum size of nanoparticles in the range of 50–200 nm was found to be high values of pH and sonication time (i.e. approximately 4.9 and 500 s, respectively) and amplitude values of more than ~55.     

BP神经网络结合遗传算法优化灰树花多糖提取工艺

目的 通过BP神经网络结合遗传算法,对灰树花多糖提取工艺进行优化,以探讨最佳提取工艺。方法 采用水提醇沉法,以多糖提取率为检测指标,采用3因素（提取温度、提取时间、液料比）4水平正交试验对多糖提取工艺进行考察。用BP神经网络模型结合遗传算法对试验结果进行目标寻优,并通过正交分析法进行验证,获得灰树花多糖的最佳提取工艺。结果 BP神经网络结合遗传算法处理分析得到优化结果为提取温度79.6℃,提取时间3.4 h,液料比50：1,此方法下多糖提取率为6.754%。结论 BP神经网络结合遗传算法优化灰树花多糖提取工艺的方法有效可靠,可为同类提取工艺的优化提供新思路。     

Artificial Neural Networks: An Overview and their Use in the Analysis of the AMPHORA-3 Dataset

The Artificial Adaptive Systems (AAS) are theories with which generative algebras are able to create artificial models simulating natural phenomenon. Artificial Neural Networks (ANNs) are the more diffused and best-known learning system models in the AAS. This article describes an overview of ANNs, noting its advantages and limitations for analyzing dynamic, complex, non-linear, multidimensional processes. An example of a specific ANN application to alcohol consumption in Spain, as part of the EU AMPHORA-3 project, during 1961–2006 is presented. Study's limitations are noted and future needed research using ANN methodologies are suggested.     

Prediction of Pharmacokinetic Parameters and the Assessment of Their Variability in Bioequivalence Studies by Artificial Neural Networks

Purpose. The methodology of predicting the pharmacokinetic parameters (AUC, c_max, t_max) and the assessment of their variability in bioequivalence studies has been developed with the use of artificial neural networks. Methods. The data sets included results of 3 distinct bioequivalence studies of oral verapamil products, involving a total of 98 subjects and 312 drug applications. The modeling process involved building feedforward/backpropagation neural networks. Models for pharmacokinetic parameter prediction were also used for the assessment of their variability and for detecting the most influential variables for selected pharmacokinetic parameters. Variables of input neurons based on logistic parameters of the bioequivalence study, clinical-biochemical parameters, and the physical examination of individuals. Results. The average absolute prediction errors of the neural networks for AUC, c_max, and t_max prediction were: 30.54%, 39.56% and 30.74%, respectively. A sensitivity analysis demonstrated that for verapamil the three most influential variables assigned to input neurons were: total protein concentration, aspartate aminotransferase (AST) levels, and heart-rate for AUC, AST levels, total proteins and alanine aminotransferase (ALT) levels, for c_max, and the presence of food, blood pressure, and body-frame for t_max. Conclusions. The developed methodology could supply inclusion or exclusion criteria for subjects to be included in bioequivalence studies.     

Formulation Optimization of Paclitaxel Carried by PEGylated Emulsions Based on Artificial Neural Network

PURPOSE: To develop paclitaxel carried by injectable PEGylated emulsions, an artificial neural network (ANN) was used to optimize the formulation--which has a small particle size, high entrapment efficiency, and good stability--and to investigate the role of each ingredient in the emulsion. METHODS: Paclitaxel emulsions were prepared by a modified ethanol injection method. A computer optimization technique based on a spherical experimental design for three-level, three factors [soybean oil (X1), PEG-DSPE (X2) and polysorbate 80 (X3)] were used to optimize the formulation. The entrapment efficiency of paclitaxel (Y1) was quantified by HPLC; the particle size of the emulsions (Y2) was measured by dynamic laser light scattering and the stability of paclitaxel emulsions was monitored by the changes in drug concentration (Y3) and particle size (Y4) after storage at 4 degrees C. RESULTS: The entrapment efficiency, particle size and stability of paclitaxel emulsions were influenced by PEG-DSPE, polysorbate 80, and soybean oil. Paclitaxel emulsions of small size (262 nm), high entrapment efficiency (96.7%), and good stability were obtained by the optimization. CONCLUSIONS: A novel formulation for paclitaxel emulsions was optimized with ANN and prepared. The contribution indices of each component suggested that PEG-DSPE mainly contributes to the entrapment efficiency and particle size of paclitaxel emulsions, while polysorbate 80 contributes to stability.     

人工神经网络辅助设计褪黑素缓释片处方

应用人工神经网络模型辅助设计褪黑素缓释片处方,将HPMC粘度、HPMC、MCC 和乳糖的量作为输入变量,累积释放百分率作为输出变量,选择反向传播网络,隐含层为1层,隐含层神经元个数为6,建立人工神经网络模型,预测和评价褪黑素缓释片体外释放度,研究缓释片的释放机理.结果显示,该人工神经网络模型能很好地预测褪黑素缓释片的释放量,成功优化褪黑素缓释片处方,其释放机理为溶蚀与扩散的结合,辅料的种类和量会对药物的释放机理产生不同影响.