塔吉克斯坦经济与资源环境协调发展评价研究

如今世界各国都在寻求经济与资源环境的可协调发展,以实现经济的可持续发展。塔吉克斯坦经济发展正处于起步阶段,为了避免走“先污染,后治理”的老路子,文章运用2000—2011年数据,结合变异系数法和协调度模型,得出塔吉克斯坦经济与资源环境协调度很好,但是建立在工业发展滞后的基础上,表现为经济发展综合质量与资源环境综合质量较低,资源环境承载经济增长的负荷较低。针对这种结果,为了实现经济与资源环境达到更好的协调发展度提出建议。     

An Improved Method for Object Extracting based on Context Information Using Multisouce Data

This paper proposed a new method which combines the airborne LiDAR data with aerial image to extract Rolling Stones on mountainous.Firstly,the aerial image is processed with multi-scale segmentation to get segmentation objects,and the LiDAR data are processed by classification,interpolation,difference for elevation information.Then compute the segmentation object based on visible-band difference vegetation index to remove the interference of vegetation information,and the nonvegetated segmentation objects are obtained.In order to effectively use the shadow,this paper put forward the normalized difference shadow index and use threshold segmentation to get shadow object.And then the automatic extraction algorithm based on the shadow and elevation information is used to preliminary obtain the rolling stones information.Finally,The height threshold filtering is set according to the actual demand to get the final rolling information.This paper took a certain area of Hong Kong aviation image and LiDAR data as experimental data to validate the proposed method.The results show that the method can well extract the Rolling Stones and effectivly distinguish the exposed bedrock,roads and similar spectral information of ground objects as Rolling Stones.The extraction accuracy of Rolling Stones is above 88% which basically satisfies the needs of rockfall in lands department.     

Extraction and Analysis of Hyperspectral Data and Characteristics from Pedicularis on Bayanbulak Grassland in Xinjiang

Through the field acquisition of three vegetation spectral datas,flowering Pedicularis,non flowering Pedicularis and common vegetation on Bayanbulak grassland,the first derivative,the two derivative and the reciprocal logarithm transformation were used to the smoothed and denoised data to analyze the difference sensitive bands of vegetation.The results showed that in visible light,non flowering Pedicularis and common vegetation showed the overall consistency,but the spectral curve of flowering Pedicularis showed a significant difference.In the red band and near infrared band at 750nm,non flowering Pedicularis reflectance increased significantly,and the three kinds of spectral reflectance showed significant differences.The reciprocal logarithmic transformation in the visible 580~680 nm band could be used to distinguish the Pedicularis as sensitive area.The spectral reflectance difference between the three at 655 nm was the most obvious.That solved the non flowering Pedicularis and common vegetation confusable problems.The improved normalized difference vegetation index by calculation,to further validate and showed the reciprocal logarithmic transformed values NDVI RLR could be distinguished the difference of flowering Pedicularis,non flowering Pedicularis and common vegetation.The extraction and analysis of hyperspectral data and characteristics from Pedicularis provided a theoretical basis for remote sensing monitoring of Pedicularis,and Remote sensing technology has great significance in Pedicularis resource survey and monitoring application.     

改进Smote算法在不平衡数据集上的分类研究

在不平衡数据集中,过抽样算法如Smote(Synthetic Minority Oversampling)算法、R-Smote算法与SD-ISmote算法可能会模糊多数类与少数类的边界以及使用噪声数据合成新样本。本文提出的ImprovedSmote算法使用少数数据集的簇心与其对应类别的少数集数据,在簇心与不大于样本属性数的对应类别少数集数据形成的图形内随机插值来生成新数据。ImprovedSmote算法结合C4.5决策树与神经网络算法在实验数据集上的结果比Smote, R-Smote与SD-ISmote算法更好,可以有效地提高分类器分类性能。     

基于密度峰和划分的快速聚类算法

传统基于划分的聚类算法需要人工给定聚类数,且由于算法采取刚性划分,可能会导致将较大或延伸状的聚类簇分割的现象,导致错误的聚类结果。密度峰聚类是近年提出的一种新的基于密度的聚类算法,该算法不需要预先指定聚类数目,且能够发现非球形簇。将密度峰思想引入基于划分的聚类算法,提出一种基于密度峰和划分的快速聚类算法（DDBSCAN）,该算法首先获取一组簇的核心对象(密度峰),用于描述簇的“骨骼”,而后将周围的点划分到最近的核心对象,最后通过判断划分边界处的密度情况合并簇。实验证明,该算法能有效地适应任意形状、大小不一的数据集,与传统基于密度的聚类算法相比收敛速度更快。     

基于改进量子粒子群算法的支持向量机参数优化方法

支持向量机参数的选择对建模精度和泛化性能等有着重要的影响,提出量子粒子群优化(QPSO)改进算法优化支持向量机（SVM）参数的方法。该方法首先将混合扰动算子引入QPSO算法中,用于获取平均最优位置,建立一种基于混合扰动算子的QPSO算法改进方法（IQPSO）,然后用IQPSO算法的全局优化能力对支持向量机惩罚系数和核参数进行综合寻优,求取最优化参数组合,从而提高支持向量机的求解速度和解的精确性。利用测试函数和UCI测试数据,对IQPSO-SVM进行仿真测试与分类,实验结果表明,IQPSO能获得很好的优化结果,IQPSO-SVM具有较好的泛化性能。     

自适应权重CV模型在超声相控阵图像分割中的应用

图像分割是超声相控阵无损检测图像三维重建的关键环节,分割精度和效率是图像三维重建准确性与实时性的重要保障。由于超声相控阵无损检测图像中含有大量噪声且灰度不均匀,在使用传统的CV模型分割检测图像时采用固定迭代步长,这导致分割效率较低且精度不高。本文利用分水岭算法过分割的特性,在对图像做分水岭变换后,统计各区域中的像素数目与灰度信息,从而得到一个权重矩阵并引入CV模型中,得到一种自适应权重CV模型。在水平集函数迭代过程中,权重矩阵可以根据图像信息自适应调整迭代步长。实验表明,与CV模型和LBF模型相比,本文提出的权重CV模型在分割超声相控阵无损检测图像时,具有更高的效率和分割精度。