共查询到20条相似文献，搜索用时 46 毫秒
1.
为了确保轨道交通隧道施工作业的正常进行及地表建构筑物的稳定安全,采用遗传算法(genetic algorithm,GA)对极限学习机(extreme learning machine,ELM)模型的输入权值和隐含层偏置进行优化,通过构建GA-ELM模型,实现对轨道交通施工隧道地表断面监测点实测数据进行变形预测研究,并将GA-ELM模型与ELM模型、传统BP(back progation)模型的变形预测结果进行对比分析.实验研究结果表明:优化后的ELM模型预测效果得到很好的改善,证明了GA-ELM预测模型在施工隧道地表沉降预测中的可靠性和适用性. 相似文献
2.
3.
4.
针对大坝变形监测数据中存在的非线性关系强和传统大坝预测模型精度不高等问题,本文利用改进蝙蝠算法选取最优的参数作为极限学习机的连接权值和阈值,并提出了一种基于改进蝙蝠算法（IBA）优化极限学习机（ELM）的大坝变形预测模型（IBA-ELM）。将IBA-ELM模型应用于工程实例,通过对某地水库大坝监测数据预测分析,验证IBA-ELM模型、BA-ELM和GA-ELM模型预测结果并进行精度评价,3种模型的预测值与实测值平均绝对误差分别为1.178 3、0.459 8、0.335 6 mm,IBA-ELM模型的预测精度高于另外2种模型,表明IBA-ELM模型能有效提高大坝变形预测能力。 相似文献
5.
6.
7.
《现代测绘》2020,(2)
地铁轨道结构的变形是影响地铁运营安全的重要因素之一,对其变形预测模型展开研究具有重要意义。本文以南京地铁2号线某区段的地铁轨道结构沉降监测实测数据为基础,研究分析了几种不同的沉降预测模型,并对预测效果进行了对比分析。论文首先介绍了时间序列模型之一,自回归模型AR(p);其次,介绍了神经网络BP模型,且确定地铁轨道结构沉降预测的BP模型结构为4×P×1。经工程实例分析,与时间序列模型相比,神经网络BP模型的预测精度能提高约50%,但该模型的缺点是模拟结果不稳定。最后,作者提出了时间序列与BP算法的融合模型,并详细介绍了该模型的具体结构和计算步骤。工程实例结果表明,融合模型的预测精度更高,与时间序列模型相比,精度能提高约60%,且融合模型的稳定性比常规BP模型要好。 相似文献
8.
9.
贝叶斯极限学习机(BELM)具有充分利用数据先验信息,可以自适应估计模型参数的特点。但在样本数量不断增加时,如果每次都对BELM重新训练将会降低计算效率。针对此问题,本文提出一种动态贝叶斯极限学习机(DBELM)方法以应用于变形监测数据实时预报。该方法以BELM训练的模型参数为初值,根据新增样本信息可对初始模型参数进行动态更新,并从理论上推导了相关计算公式。通过对仿真数据和实际变形数据进行详细分析表明:DBELM方法的预报精度要优于BELM、正则化极限学习机(RELM)、极限学习机(ELM)3种方法。特别是在长期持续预报过程中,其预报性能相对于其余3种方法优势明显。这充分表明了所提方法应用于变形监测数据预报领域具有可行性和有效性。 相似文献
10.
城市空间结构及其扩展的模拟是城市科学管理与规划的重要前提,本文基于极限学习机提出了顾及不同非城市用地转化为城市用地差异与强度的城市扩展元胞自动机模型（ELM-CA）。模型验证表明：①ELM-CA模型的模拟精度达到70.30%,相比于逻辑回归和神经网络分别提高了2.21%和1.54%,FoM系数分别提高了0.025 9和0.017 9,Kappa系数分别提高了0.024 7和0.016 9,且Moran I指数接近于实际值,说明极限学习机模型较逻辑回归和神经网络能更有效模拟城市扩展的空间形态及其变化;②ELM模型的训练时间仅为神经网络的1/3左右,体现了ELM学习速度的优势;③在小样本情况下,逻辑回归和神经网络都受到明显的影响,而极限学习机还能保持良好的性能,这个特点使其在样本难以获取的情况下具有明显的优势。两个时相的城市扩展模拟与真实数据的比较表明：基于极限学习机的城市扩展元胞自动机模型（ELM-CA）,简化了CA模型的复杂度,并在小样本情况下能有效提高模拟精度,适合于复杂土地利用条件下城市扩展模拟与预测。 相似文献
11.
开展了基于开源3维渲染引擎OSG(OpenSceneGraph)的火星形貌3维建模与绘制的研究.使用地形数据库创建工具VPB(VirtualPlanetBuilder)创建了整个火星的分页数据库,并利用基于OSG的仿真平台实现了火星形貌数据的3维可视化.实验结果证明,该方法能很好地处理海量地形数据,完成火星形貌的3维重... 相似文献
12.
针对GM(1,1)建模过程存在背景值、时间因素和初始条件3方面的不足,该文提出三重加权TPGM(1,1)预测模型。通过对背景值进行加权生成新的背景值,建立PGM(1,1)模型;在PGM(1,1)基础上考虑到时间因素,在求解灰参数时进行第2次加权建立DPGM(1,1)模型;最后考虑到初始条件对预测模型的影响,在DPGM(1,1)基础上进行第3次加权,建立TPGM(1,1)模型。通过实例分析,比较GM(1,1)、PGM(1,1)、DPGM(1,1)、TPGM(1,1)4种模型在变形监测数据处理中的拟合和预测结果,表明三重加权TPGM(1,1)模型拟合效果更好、预测精度更高;该模型具有前3种模型的优点,同时弥补了传统GM(1,1)存在的不足。 相似文献
13.
As an important canopy structure indicator, leaf area index (LAI) proved to be of considerable implications for forest ecosystem and ecological studies, and efficient techniques for accurate LAI acquisitions have long been highlighted. Airborne light detection and ranging (LiDAR), often termed as airborne laser scanning (ALS), once was extensively investigated for this task but showed limited performance due to its low sampling density. Now, ALS systems exhibit more competing capacities such as high density and multi-return sampling, and hence, people began to ask the questions like—“can ALS now work better on the task of LAI prediction?” As a re-examination, this study investigated the feasibility of LAI retrievals at the individual tree level based on high density and multi-return ALS, by directly considering the vertical distributions of laser points lying within each tree crown instead of by proposing feature variables such as quantiles involving laser point distribution modes at the plot level. The examination was operated in the case of four tree species (i.e. Picea abies, Pinus sylvestris, Populus tremula and Quercus robur) in a mixed forest, with their LAI-related reference data collected by using static terrestrial laser scanning (TLS). In light of the differences between ALS- and TLS-based LAI characterizations, the methods of voxelization of 3D scattered laser points, effective LAI (LAIe) that does not distinguish branches from canopies and unified cumulative LAI (ucLAI) that is often used to characterize the vertical profiles of crown leaf area densities (LADs) was used; then, the relationships between the ALS- and TLS-derived LAIes were determined, and so did ucLAIs. Tests indicated that the tree-level LAIes for the four tree species can be estimated based on the used airborne LiDAR (R2 = 0.07, 0.26, 0.43 and 0.21, respectively) and their ucLAIs can also be derived. Overall, this study has validated the usage of the contemporary high density multi-return airborne LiDARs for LAIe and LAD profile retrievals at the individual tree level, and the contribution are of high potential for advancing forest ecosystem modeling and ecological understanding. 相似文献
14.
Natural and man-made disasters like earthquakes, landslides, avalanches, unplanned mining are some of the most serious factors responsible for earth surface displacement. These incidences can be harmful for the society due to loss of life and also threatful for future urban development. Therefore, continuous monitoring of disasters in terms of displacements is of fundamental importance in a modern well-organized society to understand its effects on the social and economic fabric. Availability of SAR data has been proved to be an excellent source for estimation of surface displacements with high accuracies. However, in India, SAR interferometry-related displacement measurement has still not gained appreciable momentum. More rigorous research needs to be carried out for the efficient use of this new generation technique. This review article is an attempt to discuss the issues related to SAR-based displacement studies so far conducted on Indian Himalayan region and possible advanced alternatives. 相似文献
15.
Low-low satellite-to-satellite tracking: a comparison between analytical linear orbit perturbation theory and numerical integration 总被引：1，自引：0，他引：1
P.N.A.M. Visser 《Journal of Geodesy》2005,79(1-3):160-166
Low-low satellite-to-satellite tracking (ll-SST) range-rate observations have been predicted by two methods: one based on a linear perturbation theory in combination with the Hill equations, and one based on solving the equations of motion of two low-flying satellites by numerical integration. The two methods produce almost equivalent Fourier spectra of the range-rate observations after properly taking into account a few resonant terms. For a typical GRACE-type configuration, where the two satellites trail each other at a distance of 300 km at an altitude of 460 km, and in the presence of the EGM96 gravity field model, complete to spherical harmonic degree and order 70, the agreement between the Fourier spectra is about 1 mm/s compared to a root-mean-square (RMS) value of more than 220 mm/s for the range-rate signal. The discrepancy of 1 mm/s can be reduced significantly when not taking into account perturbations caused by the J2 term. Excluding the J2 term, the agreement between the two methods improves to 0.4 mm/s compared to a RMS value of 6 mm/s for the range-rate signal. These values are 0.01 and 2.3 mm/s when ignoring the spectrum for frequencies below two cycles per orbital revolution, reducing the discrepancy even further to about 0.5% of the signal. The selected linear perturbation theory is thus capable of modeling gravity field induced range-rate observations with very high precision for a large part of the spectrum. 相似文献
16.
17.
基于非参数回归方法,创新性地利用拥堵信息建立模式库,解决了传统分类、回归、神经网络等预测方法的事件特征选取限制及训练样本不足等问题,提高了预测结果的准确性。 相似文献
18.
赵博 《测绘与空间地理信息》2015,(7):177-179
像素工厂是当今世界一流的遥感影像自动化处理系统,集成自动化、并行处理和开放的架构,可以自动处理多种传感器的海量数据,生产各种制图终端。本文结合实际生产介绍了像素工厂批量生产数字地表模型(DSM)和正射影像的关键技术及工艺流程。 相似文献
19.
对黑龙江省位置服务现状进行了分析,提出了建立的黑龙江省位置服务中心的框架。位置服务中心的建立是以手机、PDA及各种移动手持终端定位服务、车辆监控等为主的服务体系,并通过WMS方式对外提供地图服务。文中对位置服务中心的设计理念、体系结构及服务模式进行了详细描述,并对其具体应用进行了探讨,最后对未来3G时代位置服务中心的应用前景进行了展望。 相似文献