期刊文献+
共找到135篇文章
< 1 2 7 >
每页显示 20 50 100
Determination of inter- and intra-subtype/species varia-tions in polymerase acidic protein from influenza A virus using amino-acid pair predictability 被引量:2
1
作者 Shaomin Yan Guang Wu 《Journal of Biomedical Science and Engineering》 2009年第4期273-279,共7页
The polymerase acidic protein is an important family of proteins from influenza A virus, which is classified as many different subtypes or spe-cies. Thus, an important question is if these classifications are numerica... The polymerase acidic protein is an important family of proteins from influenza A virus, which is classified as many different subtypes or spe-cies. Thus, an important question is if these classifications are numerically distinguishable with respect to the polymerase acidic protein. The amino-acid pair predictability was used to transfer 2432 polymerase acidic proteins into 2432 scalar data. The one-way ANOVA found these polymerase acidic proteins distinguish-able in terms of subtypes and species. However, the large residuals in ANOVA suggested a pos-sible large intra-subtype/species variation. Therefore, the inter- and intra-subtype/species variations were studied using the model II ANOVA. The results showed that the in-tra-subtype/species variations accounted most of variation, which was 100% in total for both inter- and intra- subtype/species variations. Our analysis threw lights on the issue of how to de-termine a wide variety of patterns of antigenic variation across space and time, and within and between subtypes as well as hosts. 展开更多
关键词 amino-acid pair Influenza A Virus lnter- and Intra- Model II ANOVA POLYMERASE Acidic Protein SPECIES SUBTYPE Variation
下载PDF
Mutation pattern in human adrenoleukodystrophy protein in terms of amino-acid pair predictability
2
作者 Shao-Min Yan Guang Wu 《Journal of Biomedical Science and Engineering》 2010年第3期262-267,共6页
The mutation pattern in protein is a very important feature and is studied through various approaches including the study on mutation pattern in domains where amino acids are converted into numbers from letters. In th... The mutation pattern in protein is a very important feature and is studied through various approaches including the study on mutation pattern in domains where amino acids are converted into numbers from letters. In this study, we converted the amino acids in human adrenoleukodystrophy protein with its 128 missense mutations into random domain using the amino-acid pair predictability, and then we studied their mutation patterns. The results show 1) the mutations are more likely to target the amino-acid pairs whose actual frequency is larger than their predicted one, 2) the mutations are more likely to form the amino-acid pairs whose actual frequency is smaller than their predicted frequency, 3) mutations are more likely to occur at unpredictable amino-acid pairs, and 4) mutations have the trend to narrow the difference between predicted and actual frequencies of amino-acid pairs. 展开更多
关键词 ADRENOLEUKODYSTROPHY amino-acid pair predictability MUTATION PATTERN
下载PDF
Exploring the mechanism of action of herb pair Pinellia Ternata-Magnolia Officinalis in the treatment of liver cancer based on network pharmacology and molecular docking
3
作者 Zi-Wei Du Meng-Wei Xu +6 位作者 Rui Peng Min Fang Yan Liu Guang-Shuai Zhang Si Yan Li-Na Yang Shuang-Lin Qin 《Pharmacology Discovery》 2024年第1期51-65,共15页
Background:Explore the anti-tumor mechanism of herb pair Pinellia ternate-Magnolia officinalis(BX-HP)in liver cancer through network pharmacology using molecular docking methods.Method:The active ingredients and corre... Background:Explore the anti-tumor mechanism of herb pair Pinellia ternate-Magnolia officinalis(BX-HP)in liver cancer through network pharmacology using molecular docking methods.Method:The active ingredients and corresponding targets of the herb pair Pinellia ternate-Magnolia officinalis were obtained from the HERB database.The relevant targets for liver cancer were obtained from GeneCards,DisGeNET,TTD,and Drugbank databases.Obtain common targets between herb pair Pinellia ternate-Magnolia officinalis and liver cancer through the Bioinformatics platform,establish a PPI network diagram using STRING software,and perform GO functional enrichment and KEGG pathway enrichment analysis on the DAVID platform.AutoDockTools 1.5.7 software and molecular dynamics simulation analysis are used to evaluate the binding of components to target proteins.HERB database,SwissTargetPrediction database,SwissADME database,UniProt database,GeneCards database,TTD database,DRUGBANK database,DisGeNET database,String,DAVID.Bioinformatics platform,PDB database,PubChem and TCMSP database.Result:A total of 22 active ingredients with a Probability>0.1 targets in Magnolia officinalis were screened,26 active ingredients with a Probability>0.1 targets in Pinellia ternata,ten vital active ingredients,corresponding to 979 and 803 targets with a Probability>0.1 targets,2536 liver cancer-related targets,and 279 targets in the herb pair Pinellia ternata-Magnolia officinalis.The GO functional enrichment analysis resulted in 1297 entries,namely 971 biological process entries,118 cell localization entries,and 208 molecular function entries.Three signaling pathways were annotated through the KEGG pathway.Based on molecular docking,ten vital active ingredients and five target proteins were validated to exhibit an excellent binding affinity.The above data indicates that combining the herb pair Pinellia ternata-Magnolia officinalis may treat liver cancer through specific targets and signaling pathways.Conclusion:Herb pair Pinellia ternata-Magnolia officinalis has a synergistic effect on treating liver cancer through multicomponent,multitarget,and multi-pathway approaches.This study provides a sufficient theoretical basis for subsequent research. 展开更多
关键词 liver cancer herb pair Pinellia ternata-Magnolia officinalis target prediction network pharmacology molecular docking MECHANISM
下载PDF
Application of dynamic set-pair analysis in coal and gas outburst prediction 被引量:3
4
作者 曹庆奎 李丽杰 于兵 《Journal of Coal Science & Engineering(China)》 2008年第1期77-80,共4页
Analyzed the factors which affected the coal and gas outburst,then established the corresponding indicator system.Built a dynamic set-pair analysis prediction model which combined of Markov model and set-pair analysis... Analyzed the factors which affected the coal and gas outburst,then established the corresponding indicator system.Built a dynamic set-pair analysis prediction model which combined of Markov model and set-pair analysis model,and then it applied to coal and gas outburst prediction.Finally,compared the prediction results with the actual results As provided a reference to the coalmine in safety decision-making.The research results indicate that there are four districts in high dangerous level,two districts in middle level and one district in low level,which consistent with the actual situation;the dynamic set-pair analysis model has a good effect in predicting coal and gas outburst.Especially in the continuous time intervals,according to the data of mined exploration and the connec- tion degree analysis,we can deduce the dangerous levels of unexplored districts from the historical data.In different districts,the relevant indicators can be adjusted accordingly,so as to enhance the accuracy of the prediction. 展开更多
关键词 动力学分析 井喷 预防措施
下载PDF
Application of Ordinal Set Pair Analysis in Annual Rainfall Prediction of Liao River Basin
5
作者 ZHANG Xiao-zhuang1,LIU Yin-di2,ZHAO Peng3,ZHANG Ze-zhong2 1.Guodian Diqing Shangri-la Generating Limited Liability Company,Shangri-la 674402,China 2.North China University of Water Resources and Electric Power,Zhengzhou 450011,China 3.Three Gorges Project Administration of Yangtze River Three Gorges Corporation,Yichang 443133,China 《Meteorological and Environmental Research》 CAS 2011年第7期47-49,52,共4页
[Objective] The research aimed to study the application of ordinal set pair analysis in the annual precipitation prediction of Liao River basin.[Method] The ordinal theory was introduced into the set pair analysis mod... [Objective] The research aimed to study the application of ordinal set pair analysis in the annual precipitation prediction of Liao River basin.[Method] The ordinal theory was introduced into the set pair analysis modeling,and the prediction model of set pair analysis was improved.A kind of rainfall prediction model based on the ordinal set pair analysis (OSPA) was put forward.The time sequence of annual rainfall in the hydrological rainfall station of Liao River basin during 1956-2006 was the research objective.The annual rainfall during 1998-2006 was predicted by the model,and the error analysis was given.[Result] In the relative errors of predicted results by ordinal set pair analysis,there were six relative errors within 5%,which occupied 66.7% of the total prediction number.One relative error was during 5%-10%,which occupied 11.1% of the total prediction number.Two relative errors were during 10%-15%,which occupied 22.2% of the total prediction number.All the relative errors were less than 20%,which met the precision requirement of annual rainfall prediction in Forecast Specification of Hydrological Information.[Conclusion] The rainfall prediction based on the ordinal set pair analysis model had high precision,and the prediction result was ideal.It was suitable for the annual rainfall prediction. 展开更多
关键词 Annual rainfall prediction Ordinal set pair analysis Liao River basin China
下载PDF
改进CLR的预测算法在铁路机车牵引系统故障维修中的应用
6
作者 李曼 宾紫嫣 +1 位作者 周鑫燚 覃思瑶 《铁道运输与经济》 北大核心 2024年第3期156-163,188,共9页
准确及时地预测机车系统故障是有效保障铁路运输安全与合理制定设备维护策略的关键。现有故障预测多集中于对特征数据的挖掘与分析。利用校准标签排名(CLR)结合自适应簇数的聚类算法对牵引系统故障类型进行预测,通过聚类获得故障类型深... 准确及时地预测机车系统故障是有效保障铁路运输安全与合理制定设备维护策略的关键。现有故障预测多集中于对特征数据的挖掘与分析。利用校准标签排名(CLR)结合自适应簇数的聚类算法对牵引系统故障类型进行预测,通过聚类获得故障类型深层特性,采用CLR算法从系统特征参数获取故障类型的相关性排名。通过加入人工校准标签来预测故障类型的相关性,同时减轻类不平衡问题的负面影响。相较于经典CLR算法,改进后的算法有一定幅度的性能提升。以牵引系统主变压器实际故障数据集为例,对冷凝器漏油、冷却风机异音等多种故障类型进行预测,结果表明:单个损失降低了78.8%,汉明损失提升了15.6%,故障维修方式预测准确率达96.4%,为设备故障预测性维护工作提供理论支撑。 展开更多
关键词 故障维修预测 牵引系统 成对比较排序 CLR 人工校准标签
下载PDF
Dynamic Characteristics of Lubrication and Wear Prediction of Slipper/Swash-Plate in Axial Piston Pumps 被引量:1
7
作者 Jichen Zhou Junjie Zhou +2 位作者 Chongbo Jing Shihua Yuan Anlin Luo 《Journal of Beijing Institute of Technology》 EI CAS 2019年第3期519-528,共10页
A novel dynamic model describing the slipper posture of the swash plate in axial piston pumps is proposed, taking into account the hydrodynamic and squeezing effects, which involves three degrees of freedom. The varia... A novel dynamic model describing the slipper posture of the swash plate in axial piston pumps is proposed, taking into account the hydrodynamic and squeezing effects, which involves three degrees of freedom. The variation in the lubricating film thickness and the slipper tilt are accurately calculated. The influence of hydrodynamic effects and charging pressure on the slipper lubrication is discussed. The minimum film thickness, the overturning angle and the azimuth angle are obtained.Then, the trajectory of minimum thickness on the friction surface of the swash plate is predicted, the accuracy of which can be verified with the abrasion distribution of an actual swash plate. Research results can predict the durability and provide theoretical help for the design of the slipper. 展开更多
关键词 slipper/swash-plate pair LUBRICATION DYNAMIC characteristics WEAR predicting
下载PDF
A NEW ALGORITHM FOR ADAPTIVE LATTICE FILTERAND ITS APPLICATION IN THE SPEECH LINEARPREDICTIVE SYNTHESIS 被引量:1
8
作者 Jiang Taihui (institute of Information Science, Wuji University Jiangmen, Guangdong 529020) 《Journal of Electronics(China)》 1996年第4期325-332,共8页
In this paper, an adaptive line spectral pair filter is derived from an adaptive lattice filter. A least-mean-square(LMS) type adaptive algorithm used to calculate directly the line spectral pair(LSP) coefficients on ... In this paper, an adaptive line spectral pair filter is derived from an adaptive lattice filter. A least-mean-square(LMS) type adaptive algorithm used to calculate directly the line spectral pair(LSP) coefficients on a stage-by-stage basis is presented. Experimental results show that the algorithm has higher convergence rate and lower misadjustment as compared with the other algorithms. The LSP coefficients calculated by the algorithm have been used to carry out speech linear predictive synthesis, resulting in better results than PARCOR coefficients. 展开更多
关键词 Line SPECTRAL pair FILTER Adaptive LATTICE FILTER Linear prediction LMS algorithm
下载PDF
Mechanism of Magnoliae Flos and Xanthii Fructus herb pair in treatment of allergic rhinitis based on network pharmacology 被引量:1
9
作者 Yu-Qiang Lu Hui Ding +2 位作者 Zhao-Lin Shi Hai-Bo Lin Guo-Cheng Zhang 《Drug Combination Therapy》 2022年第2期28-36,共9页
Objective: To explore the molecular mechanism of Magnoliae Flos and Xanthii Fructus herb pair for allergic rhinitis based on network pharmacology. Methods: From the Traditional Chinese Medicine Systems Pharmacology da... Objective: To explore the molecular mechanism of Magnoliae Flos and Xanthii Fructus herb pair for allergic rhinitis based on network pharmacology. Methods: From the Traditional Chinese Medicine Systems Pharmacology database, Uniprot database, and Gene Cards database, the relevant chemical constituents information, pharmacokinetic information and hub target of allergic rhinitis were obtained. The protein-protein interaction network was constructed by STRING online database, analyzed and showed by the Cytoscape software. The screened target information was analyzed by the Metascape database for Gene Ontology biological function and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis. Results: Main components of Magnoliae Flos and Xanthii Fructus herb pair, such as aloe-emodin, stigmasterol, beta-sitosterol and Yangambin, depend on the interaction of Nitric Oxide Synthase 3, Tumor Necrosis Factor, Caspase-3 and other functions involve G protein-coupled (amine) receptor activity, RNA polymerase II basic transcription factor binding, protease binding, heme binding, and integrin binding;can regulate calcium signal pathway, serotonergic synapse, Kyoto Encyclopedia of Genes and Genomes signal pathway, tryptophan inflammatory mediator regulation pathway, estrogen signal pathway alone or in combination, and play a role in the treatment of allergic rhinitis. Conclusion: Magnoliae Flos combined with Xanthii Fructus can regulate biomolecular network in multiple targets and pathways to treat allergic rhinitis. 展开更多
关键词 network pharmacology allergic rhinitis Magnoliae Flos and Xanthii Fructus herb pair target prediction mechanism of action
下载PDF
基于Pair-Copula函数的空间预测模型及其应用
10
作者 郭益敏 杨炜明 《重庆工商大学学报(自然科学版)》 2017年第3期17-20,共4页
对于空间数据的插值预测,大多采用传统的空间插值方法如反距离加权插值法和克里金插值法,这2种方法在边缘分布或存在异常值的情况下会导致预测精度相对较低;采用基于Copula理论的方法克服了这一问题。通过Pair-Copula函数描述了空间相... 对于空间数据的插值预测,大多采用传统的空间插值方法如反距离加权插值法和克里金插值法,这2种方法在边缘分布或存在异常值的情况下会导致预测精度相对较低;采用基于Copula理论的方法克服了这一问题。通过Pair-Copula函数描述了空间相依结构并利用MCMC方法(贝叶斯估计法)估计参数,讨论基于空间数据对未观测位置相关数据进行了空间插值预测;结合重庆市雾霾数据对该方法与反距离加权插值法、普通克里金和泛克里金插值法进行比较,结果发现基于Pair-Copula函数的空间预测模型具有更高的精度。 展开更多
关键词 pair-Copula函数 空间相依结构 空间预测
下载PDF
深部矿山巷道大变形综合预测方法研究 被引量:4
11
作者 周英豪 王文杰 +1 位作者 雷扬 寇永渊 《矿业安全与环保》 北大核心 2023年第1期47-53,共7页
为了准确预测深井巷道在不同阶段的挤压大变形程度,以金川二矿区深部巷道为研究对象开展研究,将大变形划分为4个等级。根据挤压大变形的S型变形规律,利用Logistic模型对监测数据进行回归预测,获得大变形的总体发展趋势及最终变形量,为... 为了准确预测深井巷道在不同阶段的挤压大变形程度,以金川二矿区深部巷道为研究对象开展研究,将大变形划分为4个等级。根据挤压大变形的S型变形规律,利用Logistic模型对监测数据进行回归预测,获得大变形的总体发展趋势及最终变形量,为巷道生产维护阶段的等级预测提供参考;综合考虑应力状态、地质环境、施工条件及围岩性质等因素,利用层次分析法赋权,建立AHP-集对分析的大变形预测模型;基于最大隶属度原则和置信度准则进行等级辨识,对巷道勘察设计阶段潜在大变形等级进行超前预测。结果表明:针对不同阶段的预测模型预测等级与实际情况相吻合,可为深部矿山巷道支护设计及维护提供依据。 展开更多
关键词 深部巷道 挤压大变形 分级预测 LOGISTIC模型 集对分析 层次分析法
下载PDF
基于三元组键值对超关系学习的知识图谱链接预测
12
作者 甄春成 王琼 +2 位作者 龚芝 李庆珍 周湘贞 《济南大学学报(自然科学版)》 CAS 北大核心 2023年第3期295-302,共8页
为了提高挖掘超关系数据中的隐含关系的能力,提出一种基于三元组键值对超关系学习的知识图谱链接预测模型;所提模型不仅捕捉编码在三元组中知识图谱的主要结构信息,而且通过对三元组及其相关键值对进行学习,采集每个三元组及其相关联的... 为了提高挖掘超关系数据中的隐含关系的能力,提出一种基于三元组键值对超关系学习的知识图谱链接预测模型;所提模型不仅捕捉编码在三元组中知识图谱的主要结构信息,而且通过对三元组及其相关键值对进行学习,采集每个三元组及其相关联的键值对之间的相关性;通过最小值操作,对基本三元组、键值对以及相关性特征向量进行合并,利用全连接投影得到预测得分。结果表明,与其他预测模型相比,所提模型在JF17K数据集和WikiPeople数据集的键、值预测平均倒数排名表现更佳,在链接预测中排名分别小于10、1的三元组的平均占比的预测性能更优。 展开更多
关键词 知识图谱 链接预测 超关系学习 结构信息 键值对
下载PDF
复杂环境条件下路桥隧道工程施工安全风险预测 被引量:1
13
作者 赵生军 《江苏航运职业技术学院学报》 2023年第2期37-43,共7页
路桥隧道工程施工环境复杂,进行施工过程中的安全风险预测十分必要。通过分析路桥隧道工程施工风险因素并对所获取的因素进行筛选,实现风险指标体系构建;通过熵权法确定各指标权重;基于集对分析理论的施工风险同异反预测模型。选取风险... 路桥隧道工程施工环境复杂,进行施工过程中的安全风险预测十分必要。通过分析路桥隧道工程施工风险因素并对所获取的因素进行筛选,实现风险指标体系构建;通过熵权法确定各指标权重;基于集对分析理论的施工风险同异反预测模型。选取风险程度微弱的“低度风险”为参照目标集合,通过其与路桥隧道工程施工风险的同势、反势、均势状态判断实现施工安全风险预测。实验结果表明,该方法可计算出风险指标权重,预测路桥隧道工程施工风险发展趋势以及确定风险等级。 展开更多
关键词 复杂环境 路桥隧道工程 施工安全风险 熵权法 集对势 同异反预测模型
下载PDF
考虑位移滞后效应的降雨型滑坡SSA-DELM位移预测模型研究
14
作者 廖兴灵 简文彬 +1 位作者 樊秀峰 章德生 《水利与建筑工程学报》 2023年第2期128-136,共9页
针对东南丘陵山地降雨型滑坡变形发展特征,现有滑坡预测模型应用存在局限,结合滑坡变形特点研究基于智能算法的滑坡预测模型。以福建安溪尧山滑坡为例,选取2019年9月至2022年6月滑坡监测数据进行研究,采用集对分析、灰关联法、麻雀搜索... 针对东南丘陵山地降雨型滑坡变形发展特征,现有滑坡预测模型应用存在局限,结合滑坡变形特点研究基于智能算法的滑坡预测模型。以福建安溪尧山滑坡为例,选取2019年9月至2022年6月滑坡监测数据进行研究,采用集对分析、灰关联法、麻雀搜索算法及深度极限学习机对滑坡位移进行预测,提出了一种考虑滑坡位移滞后时间基于深度学习的滑坡位移预测模型。结果表明:SSA-DELM模型的MAE、MAPE、RMSE相较于已有的BP神经网络、SVM模型均更小,同时模型结合了滑坡影响因子以及水位-位移滞后特征,具有明确的物理意义,位移预测效果较好且精度较高,可推广应用于类似的滑坡位移预测中。 展开更多
关键词 位移预测 滞后 集对分析 麻雀搜索算法 深度极限学习机
下载PDF
基于注意力机制的RNA碱基关联图预测方法
15
作者 曹一航 黄强 《生物化学与生物物理进展》 SCIE CAS CSCD 北大核心 2023年第3期657-667,共11页
目的长链非编码RNA在遗传、代谢和基因表达调控等方面发挥着重要作用。然而,传统的实验方法解析RNA的三级结构耗时长、费用高且操作要求高。此外,通过计算方法来预测RNA的三级结构在近十年来无突破性进展。因此,需要提出新的预测算法来... 目的长链非编码RNA在遗传、代谢和基因表达调控等方面发挥着重要作用。然而,传统的实验方法解析RNA的三级结构耗时长、费用高且操作要求高。此外,通过计算方法来预测RNA的三级结构在近十年来无突破性进展。因此,需要提出新的预测算法来准确的预测RNA的三级结构。所以,本文发展可以用于提高RNA三级结构预测准确性的碱基关联图预测方法。方法为了利用RNA理化特征信息,本文应用多层全卷积神经网络和循环神经网络的深度学习算法来预测RNA碱基间的接触概率,并通过注意力机制处理RNA序列中碱基间相互依赖的特征。结果通过多层神经网络与注意力机制结合,本文方法能够有效得到RNA特征值中局部和全局的信息,提高了模型的鲁棒性和泛化能力。检验计算表明,所提出模型对序列长度L的4种标准(L/10、L/5、L/2、L)碱基关联图的预测准确率分别达到0.84、0.82、0.82和0.75。结论基于注意力机制的深度学习预测算法能够提高RNA碱基关联图预测的准确率,从而帮助RNA三级结构的预测。 展开更多
关键词 深度学习 RNA碱基关联图 结构预测 注意力机制
下载PDF
基于预测多对非对称直方图的可逆信息隐藏
16
作者 胡晨莹 赵琰 《计算机工程与科学》 CSCD 北大核心 2023年第3期453-461,共9页
非对称预测误差直方图算法能够生成较0值偏左与较0值偏右的2个非对称直方图,在嵌入过程中,2个直方图向相反方向移动,使得部分被修改过的像素能够还原为原始像素,即发生补偿还原反应。针对该特点,结合多对直方图平移算法,生成2对非对称... 非对称预测误差直方图算法能够生成较0值偏左与较0值偏右的2个非对称直方图,在嵌入过程中,2个直方图向相反方向移动,使得部分被修改过的像素能够还原为原始像素,即发生补偿还原反应。针对该特点,结合多对直方图平移算法,生成2对非对称直方图,通过2轮非对称直方图嵌入即共4层数据嵌入,提高被修改过的像素发生补偿还原的概率。此外,通过研究数据嵌入后与原始图像峰值点和像素值的变化范围,将所有图像块分类,优先选取可嵌入概率高的图像块,减少不必要的像素修改。与其他算法相比,所提算法利用非对称直方图算法的补偿还原反应,并结合图像本身像素值分布特点,减少像素的无效修改,较好地保证了载密图像的质量。 展开更多
关键词 可逆信息隐藏 非对称直方图 多直方图 预测误差 直方图平移
下载PDF
基于输出误差模型优化的甲板运动预报算法研究
17
作者 王鑫琦 朱齐丹 《智能系统学报》 CSCD 北大核心 2023年第1期75-85,共11页
本文提出了一种适用于多种复杂海况的大型舰船甲板运动预报方法,目的在于提高算法对不同海域复杂海况的适用性,以及对甲板运动模型的辨识精度与预报精度。该方法通过将量测数据的时间滞后处理引入输出误差模型来描述甲板运动的动力学模... 本文提出了一种适用于多种复杂海况的大型舰船甲板运动预报方法,目的在于提高算法对不同海域复杂海况的适用性,以及对甲板运动模型的辨识精度与预报精度。该方法通过将量测数据的时间滞后处理引入输出误差模型来描述甲板运动的动力学模型,引入定阶准则确定了模型最优阶数数对。在此基础上应用了辅助模型递推最小二乘算法进行系统参数辨识并估计输出误差模型中的状态变量。实验结果表明,本文所提出的预报方法在系统参数辨识阶段可以将递推最小二乘算法的辨识精度提高5.13%,并且在预报阶段可以有效地将甲板运动的幅值与相位预测精度提高3.17%。该方法在复杂海况下具备良好的预测性能,适用于大型舰船甲板运动预报。 展开更多
关键词 大型舰船 甲板极短期运动预报 时间滞后 模型最优阶数数对 系统参数辨识 输出误差模型 状态变
下载PDF
集对分析理论在风电场风速区间预测中的应用 被引量:26
18
作者 郭钰锋 孙頔 +3 位作者 于继来 于达仁 郭涛 马呈霞 《电力系统自动化》 EI CSCD 北大核心 2014年第2期6-11,共6页
风力发电的出力直接取决于风速,因此需要提高风速的预测精度。考虑到风速点预测精度的提高有较难克服的瓶颈,文中提出一种针对风速的区间预测方法,将集对分析原理引入风速的区间预测中,利用风向、温度、气压、湿度等影响因素的训练数据... 风力发电的出力直接取决于风速,因此需要提高风速的预测精度。考虑到风速点预测精度的提高有较难克服的瓶颈,文中提出一种针对风速的区间预测方法,将集对分析原理引入风速的区间预测中,利用风向、温度、气压、湿度等影响因素的训练数据,并考虑风速点预测的结果误差分布及风速变化率的影响,确定未来某时间段内风速的预测值所属的分类集合,以该分类集合的上下限作为风速预测区间的上下限,从而实现了风速的区间预测。以国内某风电场的数据进行训练和预测,验证了基于集对分析理论的风速区间预测方法的有效性,同时所提方法的预测结果可以用于风电场功率预测。 展开更多
关键词 风力发电 集对分析 风速预测 区间预测
下载PDF
基于模糊层次和集对分析的尾矿库安全评价及预测 被引量:32
19
作者 尹君 王玉杰 +1 位作者 吕林 陈先锋 《金属矿山》 CAS 北大核心 2010年第10期159-161,188,共4页
从尾矿库安全管理面临的决策需求出发,通过对尾矿库危险源进行分析,建立了尾矿库安全评价预测指标体系,详细探讨了差异度和集对势在尾矿库安全评价和预测方面的应用。分别应用模糊层次分析法和集对分析理论对尾矿库进行安全评价和预测,... 从尾矿库安全管理面临的决策需求出发,通过对尾矿库危险源进行分析,建立了尾矿库安全评价预测指标体系,详细探讨了差异度和集对势在尾矿库安全评价和预测方面的应用。分别应用模糊层次分析法和集对分析理论对尾矿库进行安全评价和预测,确立了尾矿库的安全等级,反映尾矿库安全管理水平,分析尾矿库安全状况发展趋势,探索了一条安全评价与预测相结合的新途径,为尾矿库的安全管理和运行提供有效支持。 展开更多
关键词 模糊层次分析 集对分析 尾矿库 安全评价 安全预测
下载PDF
软件可靠性预测中不同核函数的预测能力评估 被引量:22
20
作者 楼俊钢 蒋云良 +1 位作者 申情 江建慧 《计算机学报》 EI CSCD 北大核心 2013年第6期1303-1311,共9页
基于核函数回归估计理论的软件可靠性预测建模引起诸多研究者的兴趣.此类研究中,核函数选择问题尤为重要.然而目前还很少有针对所给软件失效数据进行核函数选择或者构建核函数的工作.在14个常用软件失效数据集上应用配对t-检验对基于核... 基于核函数回归估计理论的软件可靠性预测建模引起诸多研究者的兴趣.此类研究中,核函数选择问题尤为重要.然而目前还很少有针对所给软件失效数据进行核函数选择或者构建核函数的工作.在14个常用软件失效数据集上应用配对t-检验对基于核函数理论的软件可靠性预测模型中核函数选择问题进行研究.使用的核函数回归估计方法包括核主成分回归算法、核偏最小二乘回归算法、支持向量回归算法、相关向量回归算法;核函数包括高斯核函数、线性核函数、多项式核函数、柯西核函数、拉普拉斯核函数、对称三角核函数、双曲正割核函数、平方正弦基核函数.实验结果表明:不同类型的核函数在不同数据集上表现差异较大,高斯核函数在所有数据集上表现较为稳定,预测结果最好. 展开更多
关键词 核函数回归算法 软件可靠性模型 核函数 配对t-检验 预测性能
下载PDF
上一页 1 2 7 下一页 到第
使用帮助 返回顶部