Kohonen网络与BP网络的集成应用研究     

丁香乾  曹均阔  贺英 《中国海洋大学学报(自然科学版)》2003,33(4):615-620

本文介绍了 Kohonen神经网络对输入数据进行聚类方法在卷烟配方中的应用 ,提出了从核心样本动态搜索 BP网络训练样本的新探索 ,摒弃了过去 BP算法中训练样本固定不变 ,互不相交的方法 ,实现了 BP网络和 Kohonen网络动态无缝集成。  相似文献   

LabVIEW设计中压力传感器的RBF神经网络温度补偿   总被引：5，自引：0，他引：5  

毕海军  傅圣雪  冯遵成 《中国海洋大学学报(自然科学版)》2004,34(6):1041-1044

在石油平台注水压力监测系统设计中 ,采用LabVIEW虚拟仪器平台 ,嵌入逼近能力强和收敛速度快的RBF神经网络 ,以人工环境实验数据为样本进行训练 ,实现了压力传感器的智能网络温度补偿。结果显示 ,此方法能够在压力、温度变化较大的恶劣环境下 ,获得很高的补偿精度。  相似文献   

基于网络药理学探究补阳还五汤治疗颈椎病的作用机制          下载免费PDF全文

王淑江  叶豪  龙胜利 《应用海洋学学报》2024,40(1):174

目的：基于网络药理学与分子对接技术分析补阳还五汤治疗颈椎病的作用机制。方法：使用TCMSP、化学专业数据库获取补阳还五汤的活性成分,并对潜在靶点进行预测及规范。分别从PharmGKB、DisGeNET、OMIM、GeneCards数据库中得到颈椎病疾病靶点,利用韦恩图获取补阳还五汤与颈椎病的交集靶点。通过CytoScape软件构建中药-活性成分-疾病靶点和蛋白质-蛋白质相互作用（PPI）网络,获得核心有效成分与关键靶点,利用David数据库对潜在靶点进行富集分析。最后运用AutoDock Vina软件对补阳还五汤核心有效成分与关键靶点进行分子对接验证。结果：共获得补阳还五汤治疗颈椎病的有效活性成分97个,包括槲皮素、山柰酚、黄芩素、木犀草素等;交集靶点64个,关键靶点有白细胞介素-6（IL-6）、肿瘤坏死因子（TNF）、丝氨酸/苏氨酸蛋白激酶1（AKT1）、白细胞介素-1B（IL-1B）等;主要涉及肿瘤坏死因子（TNF）、白细胞介素-17（IL-17）、磷脂酰肌醇3-激酶（PI3K）/蛋白激酶B（Akt）等信号通路,分子对接结果显示核心有效成分与关键靶点之间结合紧密,为补阳还五汤治疗颈椎病提供相应条件。结论：该研究在总体上预测了补阳还五汤治疗颈椎病的活性成分、靶点和信号通路,作用途径广泛,为下一步的临床应用提供参考及思路。  相似文献   

人工神经网络在地质学判别分析中的应用     

孙效功  王硕儒 《中国海洋大学学报(自然科学版)》1994,(2)

将现代人工神经网络方法应用于地质学的判别分析，通过实例计算表明，无论是对于两组判别分析还是多组判别分析，人工神经网络方法都是切实可行的。  相似文献   

A Linear Programming Model for Seabed Oil-Gas Pipe Network     

LI Hongwei  TAN Jiahua Ph. D. Candidate  School of Naval Architecture  Ocean Engineering  Shanghai Jiaotong University 《中国海洋工程》1998,(4)

This paper analyzes the pipe network system of oil-gas collection and transportation foroffshore oilfield development.A"0-1"integer linear programming model is constructed to optimize theinvestment of seabed pipe network.The mathematical model is solved by the spanning tree method ofgraph theory and network analysis.All spanning trees of a network graph compose all the feasible solu-tions of the mathematical model.The optimal solution of the model is the spanning tree with the minimumcost among all spanning trees.This method can be used to optimize the seabed pipe network system andgive a minimum cost plan for the development of offshore marginal oilfield groups.  相似文献   

Sources and hydrothermal alteration of organic matter in Quaternary sediments: A synthesis of studies from the Central Gulf of California     

Bernd R. T. Simoneit 《Marine and Petroleum Geology》1986,3(4)

Deep sea drilling in the Central Gulf of California, a young and active spreading centre, shows that the high heat flow typical of these regions causes extensive alteration of sediment organic matter, especially near sills and above magma chambers where hydrothermal activity is concentrated. Even on the nearby passive margin, where there are no sills, heat flow is moderately high and hydrocarbon generation has begun in immature sequences. Migrating light hydrocarbons are detected especially where hydrothermal activity is concentrated. Thermogenic methane is more widespread, though not in the passive margin bordering the spreading centre. Despite the incidence of hydrocarbon generation and migration, the amounts of hydrocarbons involved are relatively small and apparently do not lead to commercially significant accumulations of petroleum.The organic matter in these sediments is mostly marine because the Gulf of California generally has low runoff from land and highly productive surface waters. Turbidites rich in terrigenous organic material are locally abundant in the mainly pelagic section in the Guaymas Basin. The highest concentrations of organic matter are found in laminated diatomites deposited on the Guaymas passive margin within the oxygen minimum zone.  相似文献   

Biological processes and environmental factors regulating the dynamics of the Norwegian Skagerrak cod populations since 1919   总被引：1，自引：1，他引：1  

Fromentin  Jean-Marc; Gjosaeter  Jakob; Bjornstad  Ottar N.; Stenseth  N. Chr. 《ICES Journal of Marine Science》2000,57(2):330-338

  相似文献   

应用遗传神经网格方法分析赤潮监测数据   总被引：1，自引：1，他引：1  

杨建强  高振会  孙培艳  石强  李钦亮 《海洋科学进展》2002,20(2):77-82

简要介绍了遗传神经网络方法的原理 ,探讨了应用遗传神经网络方法研究辽东湾海域丹麦细柱藻 (Leptocylindrusdanicus)赤潮与其环境因子之间的关系 ,计算了各环境因子对丹麦细柱藻赤潮的贡献。结果表明 ,温度、盐度、DIN的变化对研究海域丹麦细柱藻种群密度的增长有比较重要的影响 ,DIN是营养限制因子。遗传神经网络是分析赤潮监测数据的有效方法 ,值得进一步探索  相似文献   

Parabolic Wave Propagation Modelling in Orthogonal Coordinate Systems     

袁德奎  林斌良肖鸿 《中国海洋工程》2004,18(3):445-456

This paper presents a numerical model study of the propagation of water waves using the parabolic approximation of the mild-slope equation in the orthogonal coordinate system. Two types of coordinate systems are studied: (a) a general form of orthogonal coordinate system and (b) the conformal system, a special form of orthogonal coordinate system. Two typical examples, namely, expanded breakwaters and a circular channel, are studied to validate the model. First, the examples are studied by use of the general orthogonal coordinates. Then the same examples are computed by use of the confonnal system. The computational results show that the confonnal coordinate system generally gives better predictions than the general orthogonal system. A numerical technique for generating the conformal grid is combined with the numerical model to improve the practicability of the model. The comparison between the result from the numerical grid system and that from the analytical grid system shows that reliable computational results can be obtained by use of the numerical confonnal grid system.  相似文献   

Neural network for wave forecasting among multi-stations     

Ching-Piao Tsai  Chang Lin  Jia-N Shen 《Ocean Engineering》2002,29(13):1685-1695

Unlike in the open sea, the use of wind information for forecasting waves may encounter more ambiguous uncertainties in the coastal or harbor area due to the influence of complicated geometric configurations. Thus this paper attempts to forecast the waves based on learning the characteristics of observed waves, rather than the use of the wind information. This is reported in this paper by the application of the artificial neural network (ANN), in which the back-propagation algorithm is employed in the learning process for obtaining the desired results. This model evaluated the interconnection weights among multi-stations based on the previous short-term data, from which a time series of waves at a station can be generated for forecasting or data supplement based on using the neighbor stations data. Field data are used for testing the applicability of the ANN model. The results show that the ANN model performs well for both wave forecasting and data supplement when using a short-term observed wave data.  相似文献