共查询到18条相似文献，搜索用时 343 毫秒
1.
人工蜂群算法优化的SVM遥感影像分类 总被引：2，自引：0，他引：2
SVM分类器的参数设定对分类精度有着显著的影响,针对现有人工智能算法优化参数易陷入局部最优的现状,提出了一种基于人工蜂群算法改进SVM参数的遥感分类方法(ABC-SVM)。该方法模仿蜜蜂采蜜的行为,以训练样本的交叉验证精度代表蜜源的丰富程度,通过蜂群的分工协作搜索出最优蜜源(即SVM分类器最优参数),最终利用参数优化后的SVM分类器实现遥感影像的分类。本文先后比较了3种人工智能算法(包括人工蜂群算法优化的SVM(ABC-SVM)、遗传算法GA(Genetic Algorithm)优化的SVM(GA-SVM)、粒子群算法PSO(Practical Swarm Optimization)优化的SVM(PSO-SVM))在UCI标准数据集上的分类精度和效率,以及3种人工智能算法优化的SVM算法与未经优化参数的SVM算法在遥感影像上分类的差异。结果显示:(1)在利用UCI数据集测试3种人工智能算法优化的SVM算法的结果中,ABC-SVM显示出更高的分类精度、更高的适应度和更快的收敛速度;(2)在利用遥感影像验证4种分类算法精度的结果中,人工智能算法优化后的SVM比未经参数优化的SVM算法的分类精度更高;其中,ABC-SVM分类精度最高,分别比遗传算法、粒子群算法的结果高1.67%、1.50%。 相似文献
2.
波段选择是高光谱遥感图像分类的重要前提,本文提出了一种用于高光谱遥感图像波段选择的改进二进制布谷鸟算法,通过使用混合二进制编码算法更新子代鸟巢和使用遗传算法交叉方式更新被发现鸟巢两个方面对二进制布谷鸟算法进行改进,找出在图像中起主要作用且相关性低的波段,实现对高光谱遥感图像降维。将本文算法运用于PaviaU数据集和AVIRIS数据集,并与二进制布谷鸟算法、二进制粒子群算法、最小冗余最大相关算法、Relief算法等进行对比分析。结果表明,改进二进制布谷鸟算法波段特征选择效率更高,且选取的波段更具代表性,能够较好地提高后续分类精度。 相似文献
3.
4.
姚创杰 《测绘与空间地理信息》2018,(4):167-173
顾及专题属性的空间聚类分析是空间数据挖掘中一个十分具有挑战性的研究课题。目前,顾及专题属性空间聚类分析一般可以分为划分的方法、层次的方法、基于模型的方法、基于密度的方法和混合的方法等。然而这些算法如何去比较质量、算法如何选取却是一个很少涉及却很重要的问题。本文对实际数据进行聚类分析实验,比较了11种顾及属性的空间聚类算法的质量,从整体质量差异和两两之间质量差异的角度分别进行了定性、定量分析,并分析了算法之间的相似度,这对于用户算法的选择、算法的评价具有指导意义。 相似文献
5.
6.
7.
特征提取和选择是模式识别核心问题之一,它极大地影响着分类器的设计和性能,高维的特征选择更是一个NP难题。针对特征选择这一组合优化及多目标优化问题,本文提出了改进的融合启发信息ACO(Antcolony optimization)特征选择的新方法,该算法比不用启发信息的ACO方法能更好地找出代表问题空间的最优特征子集,降低分类系统的搜索空间,从而提高搜索效率。以航空纹理影像的特征选择和分类问题为例,利用原始蚂蚁算法和改进的蚂蚁算法选择的特征分别进行识别,结果证明该算法不仅能够比没有改进的蚂蚁找出有效特征集、降低图像特征空间维数、减少图像分类的工作量,而且提高了分类识别正确率。 相似文献
8.
针对城市三维GIS中的海量数据组织需求,本文设计并实现了基于关系数据库的三维模型数据库,主要特点是支持地形数据、三维模型几何与纹理数据的一体化存储和属性的自定义动态管理。结合城市三维GIS中的海量数据访问和管理需求,从空间索引、纹理缓存、属性存取、数据加密、数据更新等方面介绍了该架构,指出按模型类别建立分类索引,能够提高空间索引查询效率。 相似文献
9.
为有效融合多光谱图像的光谱信息和全色图像的空间细节信息,提出了一种基于混沌蜂群优化和改进脉冲耦合神经网络(PCNN)的非下采样Shearlet变换(NSST)域图像融合方法。首先对多光谱图像进行Intensity-HueSaturation(IHS)变换,全色图像的直方图按照多光谱图像亮度分量的直方图进行匹配;然后分别对多光谱图像的亮度分量和新全色图像进行NSST变换,对低频分量使用改进加权融合算法进行融合,以互信息作为适应度函数,利用混沌蜂群算法找到最优加权系数。对高频分量采用改进脉冲耦合神经网络(PCNN)方法进行融合,再经NSST逆变换和IHS逆变换得到融合图像。本文方法在主观视觉效果和信息熵、光谱扭曲度等客观定量评价指标上优于基于IHS变换、基于非下采样Contourlet变换(NSCT)和非负矩阵分解(NMF)、基于NSCT和PCNN等5种融合方法。本文方法在提升图像空间分辨率的同时,有效地保留了光谱信息。 相似文献
10.
GIS城市道路最短路径算法研究 总被引：1，自引：0，他引：1
本文紧密结合城市公交的特点,利用改进Dijkstra算法开发出一个针对城市道路系统的最短路径自动搜索信息系统,该系统通过在ArcGIS环境下建立空间数据库和属性数据库,在VB环境下利用改进Dijsktra算法对McObjecta控件进行二次开发而设计完成,能在0.20s完成500多个交叉口的计算并找出其最短路径,是一种... 相似文献
11.
利用倒数灰度熵和改进Chan-Vese模型进行SAR河流图像分割 总被引：2，自引：1，他引：1
为了进一步提高合成孔径雷达(SAR)图像中河流分割的精度和速度,提出了一种基于人工蜂群优化的倒数灰度熵多阈值选取与改进Chan-Vese(CV)模型相结合的分割方法。考虑SAR图像中河流目标和背景类内灰度的均匀性,提出了基于蜂群优化的倒数灰度熵多阈值选取方法,以此对河流图像进行粗分割;针对基本CV模型收敛速度低、对初始条件敏感的问题,利用图像边缘强度取代Dirac函数,将粗分割结果作为改进CV模型的初始条件,对河流图像进行细分割。大量试验结果表明,所提出的分割方法无须设置初始条件,运行速度快,分割精度高。 相似文献
12.
Mehrdad Bijandi Mohammad Karimi Bahman Farhadi Bansouleh Wim van der Knaap 《Transactions in GIS》2021,25(1):551-574
In the process of agricultural land consolidation, the land parcels are optimally redesigned and rearranged in such a way that the dimensions of the resulting parcels are proportional to agricultural criteria such as irrigation discharge, soil texture, and cropping pattern. Besides these criteria, spatial factors like slope, road accessibility, volume of earthwork, and geometrical factors such as size and shape of parcels are also included in the design process of agricultural land partitioning. In this study, a land partitioning model was proposed using a multi‐objective artificial bee colony algorithm (MOABC‐LP) taking into consideration the mentioned factors. Initially, a feasible dimension range of parcels in a block was calculated based on irrigation efficiency. Two partitioning layouts were defined according to the topography and geometry of blocks. The proposed method was applied to a real study area and the results suggest that the land partitioning plan obtained by the MOABC‐LP model, in comparison with a designer's plan, not only makes the shape and size of parcels more compatible with the topographical and agricultural conditions of each block, but also reduces their cut‐and‐fill ratio. 相似文献
13.
Creating appropriate colour schemes is challenging for both novice and experienced cartographers. This paper introduces an artificial bee colony (ABC) algorithm to automatically create various colour schemes. Colour scheme creation is treated as a constrained search problem in a continuous colour space. We considered the gamut of the target device and a series of cartographic rules, such as convention, discrimination, contrast, perceptual uniformity and brightness mirror, in the ABC algorithm and presented detailed initialization, fitness definition, local exploration, and global exploration methods for creating qualitative, sequential and diverging colour schemes. The proposed method is evaluated with a case study, and the results indicate that compared with the brute force search method, the proposed method can create satisfying colour schemes of similar quality but significantly improved efficiency. 相似文献
14.
针对Delaunay三角网空间聚类存在的不足,提出一种顾及属性空间分布不均的空间聚类方法。首先将Delaunay三角网空间位置聚类作为约束条件,采用广度优先搜索方法,以局部参数"属性变化率"作为阈值识别非空间属性相似簇的聚类过程。以城市商业中心为例,验证了该方法能够更客观地识别非空间属性相似的簇,且自适应属性阈值可以满足不同聚类需求,为城市商业中心等空间实体的提取提供了一种有效方法。 相似文献
15.
16.
Mileva Samardžić‐Petrović Suzana Dragićević Miloš Kovačević Branislav Bajat 《Transactions in GIS》2016,20(5):718-734
Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation‐based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM‐based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters. 相似文献
17.
针对多路径误差的空间分布特征,该文提出采用克里金插值法构建多路径误差的空间插值模型。通过采用ArcGIS中克里金插值工具构建的多路径误差的空间插值模型,较好地展现出多路径误差与测站位置、反射源距离等因素的空间分布特征。实验结果表明:对比泛克里金插值法、普通克里金插值法、简单克里金插值法3种方法构建的多路径误差插值模型,普通克里金插值法的效果最好。研究成果直观反映出在林区、多层建筑物等环境下多路径误差影响较大,还预测出未采样区域的多路径误差影响范围,该研究成果可应用于GPS观测站选址、GPS测量技术设计等领域。该文从空间分布特征的角度提出了一种新的研究多路径误差特性的思路,实现了对指定测区内的多路径误差的空间分布特征的探究。 相似文献
18.
Spatial objects have two types of attributes: geometrical attributes and non-geometrical attributes, which belong to two different attribute domains (geometrical and non-geometrical domains). Although geometrically scattered in a geometrical domain, spatial objects may be similar to each other in a non-geometrical domain. Most existing clustering algorithms group spatial datasets into different compact regions in a geometrical domain without considering the aspect of a non-geometrical domain. However, many application scenarios require clustering results in which a cluster has not only high proximity in a geometrical domain, but also high similarity in a non-geometrical domain. This means constraints are imposed on the clustering goal from both geometrical and non-geometrical domains simultaneously. Such a clustering problem is called dual clustering. As distributed clustering applications become more and more popular, it is necessary to tackle the dual clustering problem in distributed databases. The DCAD algorithm is proposed to solve this problem. DCAD consists of two levels of clustering: local clustering and global clustering. First, clustering is conducted at each local site with a local clustering algorithm, and the features of local clusters are extracted. Second, local features from each site are sent to a central site where global clustering is obtained based on those features. Experiments on both artificial and real spatial datasets show that DCAD is effective and efficient. 相似文献