检索结果-南通市图书馆

A Method for Crude Oil Selection and Blending Optimization Based on Improved Cuckoo Search Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Petroleum Processing & Petrochemical Technology 2014年第4期16卷 70-78页

作者： yang huihua Ma Wei Zhang Xiaofeng Li Hu Tian Songbai Guangxi Experiment Center of Information Science Guilin University of Electronic Technology Research Institute of Petroleum Processing SINOPEC

Refineries often need to find similar crude oil to replace the scarce crude oil for stabilizing the feedstock property. We introduced the method for calculation of crude blended properties firstly, and then created a crude oil selection and blending optimization model based on the data of crude oil property. The model is a mixed-integer nonlinear programming(MINLP) with constraints, and the target is to maximize the similarity between the blended crude oil and the objective crude oil. Furthermore, the model takes into account the selection of crude oils and their blending ratios simultaneously, and transforms the problem of looking for similar crude oil into the crude oil selection and blending optimization problem. We applied the Improved Cuckoo Search(ICS) algorithm to solving the model. Through the simulations, ICS was compared with the genetic algorithm, the particle swarm optimization algorithm and the CPLEX solver. The results show that ICS has very good optimization efficiency. The blending solution can provide a reference for refineries to find the similar crude oil. And the method proposed can also give some references to selection and blending optimization of other materials.

关键词： crude oil similarity crude oil selection blending optimization mixed-integer nonlinear programming CuckooSearch algorithm

SpectraTr:A novel deep learning model for qualitative analysis of drug spectroscopy based on transformer structure

在线全文

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2022年第3期15卷 107-117页

作者： Pengyou Fu Yue Wen Yuke Zhang Lingqiao Li Yanchun Feng Lihui Yin huihua yang School of Computer Science and Information Security Guilin University of Electronic Technology 1 Jinji Road Guilin 541004P.R.China School of Artīcial Intelligence Beijing University of Posts and Telecommunications 10 Xitucheng Road Beijing 100876P.R.China School of International Beijing University of Posts and Telecommunications 10 Xitucheng Road Beijing 100876P.R.China National Institutes for Food and Drug Control 10 Tiantanxili Road Beijing 100050P.R.China

The drug supervision methods based on near-infrared spectroscopy analysis are heavily dependent on the chemometrics model which characterizes the relationship between spectral data and drug *** preliminary application of convolution neural network in spectral analysis demonstrates excellent end-to-end prediction ability,but it is sensitive to the hyper-parameters of the *** transformer is a deep-learning model based on self-attention mechanism that compares convolutional neural networks(CNNs)in predictive performance and has an easy-todesign model ***,a novel calibration model named SpectraTr,based on the transformer structure,is proposed and used for the qualitative analysis of drug *** experimental results of seven classes of drug and 18 classes of drug show that the proposed SpectraTr model can automatically extract features from a huge number of spectra,is not dependent on pre-processing algorithms,and is insensitive to model *** the ratio of the training set to test set is 8:2,the prediction accuracy of the SpectraTr model reaches 100%and 99.52%,respectively,which outperforms PLS DA,SVM,SAE,and *** model is also tested on a public drug data set,and achieved classification accuracy of 96.97%without preprocessing algorithm,which is 34.85%,28.28%,5.05%,and 2.73%higher than PLS DA,SVM,SAE,and CNN,*** research shows that the SpectraTr model performs exceptionally well in spectral analysis and is expected to be a novel deep calibration model after Autoencoder networks(AEs)and CNN.

关键词： Near-infrared spectroscopy analysis drug supervision transformer structure deep learning chemometrics

VPD modifies CO_(2) fertilization effect on tomato plants via abscisic acid and jasmonic acid signaling pathways

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Horticultural Plant Journal 2024年第5期10卷 1165-1176页

作者： Dalong Zhang huihua yang Xiaolu Chen Yan Li Yunzhou Li Hongye Liu Xulin Wu Min Wei College of Horticultural Science and Engineering Shandong Agricultural UniversityTai'anShandong 271018China College of Agriculture Guizhou UniversityGuiyangGuizhou 550025China

Atmospheric CO_(2)concentration is elevated globally,which has“CO_(2)fertilization effects”and potentially improves plant photosynthesis,yield,and *** the beneficial effect of CO_(2)fertilization being modulated by vapor pressure deficit(VPD),the underlying mechanism is highly *** the present study,the potential roles of hormones in determining CO_(2)fertilization effects under contrasting high and low VPD conditions were investigated by integrated physiological and transcriptomic *** CO_(2)fertilization effects were offset under high VPD conditions and were constrained by plant water stress and photosynthetic CO_(2)*** VPD induced a large passive water driving force,which disrupted the water balance and consequently caused plant water *** water potential,turgor pressure,and hydraulic conductance declined under high VPD *** physiological evidence combined with transcriptomic analyses demonstrated that abscisic acid(ABA)and jasmonic acid(JA)potentially acted as drought-signaling molecules in response to high VPD *** foliar ABA and JA content triggered stomatal closure to prevent excessive water loss under high VPD stress,which simultaneously increased the diffusion resistance for CO_(2)uptake from atmosphere to leaf intercellular *** VPD also significantly increased mesophyll resistance for CO_(2)transport from stomatal cavity to fixation site inside *** chloroplast“sink”CO_(2)availability was constrained by stomatal and mesophyll resistance under high VPD stress,despite the atmospheric“source”CO_(2)concentration being ***,ABA-and JA-mediated drought-resistant mechanisms potentially modified the beneficial effect of CO_(2)fertilization on photosynthesis,plant growth,and yield *** study provides valuable information for improving the utilization efficiency of CO_(2)fertilization and a better understanding of the physiological processes.

关键词： Abscisic acid CO_(2) fertilization Jasmonic acid Mesophyll conductance Stomatal conductance Vapor pressure deficit

Deep belief network-based drug identification using near infrared spectroscopy

在线全文

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2017年第2期10卷 1-10页

作者： huihua yang Baichao Hu Xipeng Pan Shengke Yan Yanchun Feng Xuebo Zhang Lihui Yin Changqin Hu College of Electronic Engineering and Automation Guilin University of Electronic Technology 1 Jinji Road Guilin 541004P.R.China A utomation School Beijing University of Posts 8 Telecommunications 10 Xitucheng Road Beijing 100876P.R.China National Institutes for Food and Drug Control 10 Tiantanxili Road Beijing 100050P.R.China

Near infrared spectroscopy(NIRS)analysis technology,combined with chemometrics,can be effectively used in quick and nondestructive analysis of quality and *** this paper,an effective drug identification method by using deep belief network(DBN)with dropout mecha-nism(dropout-DBN)to model NIRS is introduced,in which dropout is employed to overcome the overfitting problem coming from the small *** paper tests proposed method under datasets of different sizes with the example of near infrared diffuse refectance spectroscopy of erythromycin ethylsuccinate drugs and other drugs,aluminum and nonaluminum ***,it gives experiments to compare the proposed method's performance with back propagation(BP)neural network,support vector machines(SVMs)and sparse denoising auto-encoder(SDAE).The results show that for both binary classification and multi-classification,dropout mechanism can improve the classification accuracy,and dropout-DBN can achieve best classification accuracy in almost all *** is similar to dropout-DBN in the aspects of classification accuracy and algorithm stability,which are higher than that of BP neural network and SVM *** terms of training time,dropout-DBN model is superior to SDAE model,but inferior to BP neural network and SVM ***,dropout-DBN can be used as a modeling tool with effective binary and multi-class classification performance on a spectrum sample set of small size.

关键词： Deep belief networks near infrared spectroscopy drug classification dropout

Application of near-infrared spectroscopy for the rapid analysis of Lonicerae Japonicae Flos solution extracted by water

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2014年第4期7卷 42-50页

作者： Xue Xiao Jinfang Ma Fahuan Ge Xiangdong Zhang huihua yang Qionghin Liang Yiming Wang Guoan Luo Nansha Research Institute Sun Yat-Sen.University Guang zhou 511458 P.R.China Department of Chemistry Tsinghua University Beijing 100084P.R.China

A rapid quantitative analytical method for three components of Lonicerae Japornicae Flos solution(Lonicera Japonica Thumb.)extracted by water was developed using near-infrared(NIR)spectroscopy and the partial least-squares(PLS)*** NIR spectra of 81 samples collected from a production line were *** concentrations of secologanic acid,chlorogenicacid and galuteolin were detemmined by using high-performance liquid chromatography-diodearray detection as the reference *** pretreatment methods for the NIR spectra wereusedi during PLS *** most appropriate latent variable number of the PLS factor wasselected based on the standard error of cross-validation(SECV).The performance of the finalPLS models was evaluated according to SECV,standard error of predliction(SEP)and deter-mination coeficient(R^(2)).The compounds secologanic acid,chlorogenic acid and galuteolin hadSEP values of 0.030,0.061 and 1.668μg/mL,respectively and R^(2) values over *** workshows that NIR spectroscopy is a rapid and convenient method for the analysis of LoniceraeJaponicae Flos solution extracted by *** proposed method can help in the application ofprocs analytical technology in the pha maceutical industry,particularly in tra ditional Chinesemedicine injections.

关键词： Lonicerae Japonicae Flos Qingkailing injection near-infrared partial least-squares rapid analysis

Multi-manufacturer drug identification based on near infrared spectroscopy and deep transfer learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2020年第4期3卷 39-50页

作者： Lingqiao Li Xipeng Pan Wenli Chen Manman Wei Yanchun Feng Lihui Yin Changqin Hu huihua yang School of Automation Beijing University of Posts and Telecommunications 10 Xitucheng Road Beijing 100876P.R.China School of Computer Science and Information Security Guilin University of Electronic Technology 1 Jinji Road Guilin 541004P.R.China National Institutes for Food and Drug Control 10 Tiantanxili Road Beijing 100050 P.R.China

Near infrared(NIR)spectrum analysis technology has outstanding advantages such as rapid,nondestructive,pollution-free,and is widely used in food,pharmaceutical,petrochemical,agricultural products production and testing *** neural network(CNN)is one of the most successful methods in big data analysis because of its powerful feature ex-traction and abstraction ability,and it is especially suitable for solving multi-classification ***-based transfer learning is a machine learning technique,which migrates para-meters of trained model to the new one to improve the *** transfer learning strategy can speed up the learning efficiency of the model instead of learning from *** view of the difficulty in acquisition of drug NIR spectral data and high labeling cost,this paper proposes three simple but very effective transfer learning methods for multi-manufacturer identification of drugs based on one-dimensional *** with the original CNN,the transfer learning method can achieve better classification performance with fewer NIR spectral data,which greatly reduces the dependence on labeled NIR spectral *** the same time,this paper also compares and discusses three different transfer learning methods,and selects the most suitable transfer learning model for drug NIR spectral data *** with the current popular methods,such as SVM,BP,AE and ELM,the proposed method achieves higher classification accuracy and scalability in multi-variety and multi-manufacturer NIR spectrum classification experiments.

关键词： Near-infrared spectroscopy transfer learning drug identification multi-manufacturer

基于RF＿AdaBoost模型的血液种属鉴别算法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

高等学校化学学报 2020年第1期41卷 94-101页

作者：魏曼曼路皓翔杨辉华桂林电子科技大学计算机与信息安全学院桂林541004 桂林电子科技大学电子工程与自动化学院桂林541004 北京邮电大学自动化学院北京100876

针对人类和非人类血液种属鉴别对无损、高效分析方法的需求,结合随机森林(Random Forest)和AdaBoost(Adaptive Boosting Algorithm)算法,提出了一种血液种属鉴别方法(RF_AdaBoost).该方法将RF作为AdaBoost的弱分类器,以达到提高模型鉴... 详细信息

针对人类和非人类血液种属鉴别对无损、高效分析方法的需求,结合随机森林(Random Forest)和AdaBoost(Adaptive Boosting Algorithm)算法,提出了一种血液种属鉴别方法(RF_AdaBoost).该方法将RF作为AdaBoost的弱分类器,以达到提高模型鉴别准确度,增强模型鲁棒性的目的.采用RF、支持向量机(SVM)、极限学习机(ELM)、核极限学习机(KELM)、堆栈自编码网络(SAE)、反向传播网络(BP)、主成分分析⁃线性判别法(PCA⁃LDA)及偏最小二乘判别分析(PLS⁃DA)与RF_AdaBoost模型进行对比,以不同规模血液拉曼光谱数据训练集进行鉴别实验评估其性能.结果表明,随着训练样本的增加,RF_AdaBoost鉴别准确度最高达100%,预测标准偏差趋于0.与其它模型相比,RF_AdaBoost具有较高的分类准确度及较强的稳定性,为血液种属的鉴别工作提供了新方法.

关键词：拉曼光谱随机森林 AdaBoost算法集成学习血液种属鉴别

在线全文

学校读者我要写书评

暂无评论

低速非达西渗流条件下水平气井产能预测公式

油气井测试 2008年第6期17卷 19-20,31页

作者：刘萍杨辉华西南油气分公司工程技术研究院四川德阳618000 石油工程西南有限公司井下作业分公司四川德阳618000

目前,多采用常规的产能公式对低渗气井进行产能预测,对于水平井一般忽略启动压力梯度,导致了预测结果与生产实际存在较大的误差。通过对低渗气藏渗流机理分析研究,在直井考虑启动压力梯度产能公式基础上,利用保角变换关系,推导出适合于... 详细信息

目前,多采用常规的产能公式对低渗气井进行产能预测,对于水平井一般忽略启动压力梯度,导致了预测结果与生产实际存在较大的误差。通过对低渗气藏渗流机理分析研究,在直井考虑启动压力梯度产能公式基础上,利用保角变换关系,推导出适合于低渗气藏水平井产能预测公式。通过实例计算进行分析认为,低渗气藏水平井产能预测中必须考虑启动压力梯度的影响。

关键词：低渗透气藏启动压力梯度水平井产能预测

基于BPSO-SVM的网络入侵特征选择和检测

在线全文

学校读者我要写书评

暂无评论

计算机工程 2006年第8期32卷 37-39页

作者：高海华杨辉华王行愚华东理工大学信息科学与工程学院上海200237

采用改进的二进制粒子群优化进行入侵特征子集选择,粒子群中每个粒子代表一个选择的特征子集,结合支持向量机使用该特征子集所对应的数据集进行分类,正确分类结果作为该粒子的适应度,通过粒子群优化实现最优入侵特征选择。改进的BPSO方... 详细信息

采用改进的二进制粒子群优化进行入侵特征子集选择,粒子群中每个粒子代表一个选择的特征子集,结合支持向量机使用该特征子集所对应的数据集进行分类,正确分类结果作为该粒子的适应度,通过粒子群优化实现最优入侵特征选择。改进的BPSO方法中通过引入粒子群依概率整体变异来避免陷入局部最优,同时采用粒子禁忌搜索列表来扩大粒子搜索范围和避免重复计算;SVM中采用基于粒度的网格搜索来获得最优核参数。最后用KDD 99标准数据集进行实验研究,结果表明该方法能获得满意的检测效果。

关键词：二进制粒子群优化支持向量机异常检测特征选择