共查询到20条相似文献，搜索用时 390 毫秒
1.
针对天然地震与人工爆破波形特征相似、难以区分的情况,结合灰狼优化算法和支持向量机,提出一种地震事件性质辨识新方法.通过梅尔频率倒谱系数法对2013年四川芦山地震地震事件信号和人工爆破信号进行分析,进过预加重、FFT、梅尔滤波及离散余弦变换等步骤,提取静态系数样本熵、一阶差分系数样本熵和二阶差分系数样本熵等作为样本特征集.使用灰狼算法优化支持向量机径向基核函数 RBF中的惩罚系数和核函数半径形成新的 GWO-SVM 分类器,然后对事件进行辨识.结果表明:GWO-SVM 分类器辨识效果明显优于 SVM、RobustBoost集成学习、LDA、PLDA 等分类器,其在1000次循环识别实验下的准确率均值相对 SVM 提高了9．2个百分点,标准差降低了3．2以上;t检验证明 MFCC样本熵各特征具有可靠的地震事件分类效果;GWO-SVM与 MFCC样本熵可作为天然地震事件与人工爆破事件的辨识方法与分类判据. 相似文献
2.
快速、准确地识别天然地震和人工爆破事件是地震台网监测的重要工作之一,也是提高地震观测记录质量、开展地震研究工作的重要基础.针对反向传播神经网络、支持向量机等主流分类识别方法在地震事件分类识别应用上的不足,提出一种基于改进 EWT 和 LogitBoost集成分类器的地震事件分类识别算法.首先,基于S谱能量曲线对传统经验小波变换进行改进,将信号自适应分解为按频率和能量分布的本征模函数;其次,提取 P波与S波最大振幅比,前4个本征模函数的香农熵、对数能量熵,以及去噪后重构信号主频等特征;最后,采用基于集成学习 LogitBoost的决策树集成分类器进行分类.实验结果表明,所提算法具有较高的鲁棒性,能有效解决样本不足的问题,识别准确率达93．1%以上,比集成学习 AdaBoost、反向传播神经网络和支持向量机等方法提高了1%以上,且分类识别效果好. 相似文献
3.
4.
为增强核爆地震模式分类器的泛化能力以提高对核爆炸事件的准确识别能力,论文提出了一种选择支撑向量样本集来表征训练样本集的最近邻支撑向量特征线分类算法,用以训练时扩展核爆地震的训练样本库,提高分类器的泛化能力.该算法用于核爆炸和地震的识别结果发现,和最近邻特征线分类器相比,提出的算法降低了计算复杂度,但识别能力却有些许降低.对新算法的分析发现,纯粹的支撑向量集不能完全代表原始样本空间集,支撑向量比例在其中有重要作用,为发挥支撑向量比例的作用以提高核爆分类器的识别能力,提出了最近邻支撑向量特征线融合算法.最后以核爆地震数据库对上述算法进行了检验和分析,理论分析和识别结果证实,在相同的训练样本选择条件下,最近邻支撑向量特征线融合算法对于核爆炸的识别来说具有较好的泛化能力,正确识别率达到90.3%,且优于支持向量机算法和最近邻特征线算法. 相似文献
5.
6.
辽河盆地东部坳陷储集层由火山多期喷发形成,岩相岩性复杂,岩性以中、基性火山岩为主.本文将火山岩的岩心及岩矿鉴定资料与测井数据进行整合,应用测井数据建立支持向量机(SVM)两分类和多分类岩性识别模式.首先,深入研究支持向量机二分类及"一对一"、"一对多"和有向无环图三种经典多分类算法的基本原理及结构;然后,总结研究区域火山岩岩石特征,分析测井数据的测井响应组合特征,选择40口井中岩心分析和薄片鉴定资料完整、常规五种测井曲线(RLLD,CNL,DEN,AC,GR)齐全的1200个测井数据作为训练样本,构造三种支持向量机岩性识别模式;最后,对4测试井中800个测井数据进行岩性识别,识别结果与取心段岩心描述和岩心/岩屑薄片鉴定资料对比,实验结果表明有向无环图更适合辽河盆地火山岩的识别,识别正确率达到82.3%. 相似文献
7.
目的：探讨数据挖掘中决策树模型在结直肠癌患者肝脏CT图像分类中的应用。方法：分别选取结直肠癌患者肝转移、单纯性肝囊肿以及正常肝脏的CT增强图像各20例。对该60例肝脏CT增强图像分别进行灰度直方图、灰度共生矩阵以及图像变换的纹理特征提取,然后采用朴素贝叶斯分类器和决策树归纳分类器对图像进行分类。最终分类结果与临床事实分类对照,利用十折交叉验证法验证两种分类模型的有效性。结果：基于数据挖掘的决策树模型对结直肠癌患者肝脏CT图像进行分类准确性较高。决策树归纳的分类准确性远高于朴素贝叶斯分类器（准确性96．7％vs76．7％,Kappa值0．95vs0．65,P〈0．05）。结论：基于数据挖掘的决策树模型可以对结直肠癌患者肝脏CT图像进行分类,不仅能够判断肝脏有无相关病灶,而且仅依据图像的基本特性,可以自动识别肝脏乏血供转移瘤与单纯性肝囊肿,为未来计算机辅助诊疗疾病提供有效的参考信息及途径。 相似文献
8.
9.
Sun ZhongPing Shen WenMing Wei Bin Liu XiaoMan Su Wei Zhang Chao Yang JianYu 《中国科学:地球科学(英文版)》2010,53(1):34-44
The object-oriented information extraction technique was used to improve classification accuracy, and addressed the problem that HJ-1 CCD remote sensing images have only four spectral bands with moderate spatial resolution. We used two key techniques: the selection of optimum image segmentation scale and the development of an appropriate object-oriented information extraction strategy. With the principle of minimizing merge cost of merging neighboring pixels/objects, we used spatial autocorrelation index Moran’s I and the variance index to select the optimum segmentation scale. The Nearest Neighborhood (NN) classifier based on sampling and a knowledge-based fuzzy classifier were used in the object-oriented information extraction strategy. In this classification step, feature optimization was used to improve information extraction accuracy using reduced data dimension. These two techniques were applied to land cover information extraction for Shanghai city using a HJ-1 CCD image. Results indicate that the information extraction accuracy of the object-oriented method was much higher than that of the pixel-based method. 相似文献
10.
Hadi Ghasemi Mehdi Zare Yoshimitsu Fukushima Fereidoon Sinaeian 《Soil Dynamics and Earthquake Engineering》2009
Shear wave velocity, measured recently at 107 strong motion stations, is a new empirical basis in the applicability investigation of empirical classification techniques. These stations are classified considering Iranian Practice Code criteria (Standard 2800). To check the applicability of empirical methods, three different empirical techniques are applied to re-classify the stations using previously determined site classes. The first method is based only on the determination of peak periods at each station. It is found that the fundamental periods in different site categories are within the ranges proposed by Japanese Road Association. The second one is upon the site classification index (SI), suggested by Zhao et al. In this study, a new site index term is proposed for quantitative site classification using the empirical H/V spectral ratio (here after HVRS) method. It is shown that the results from this scheme are comparable with those obtained by applying the method of Zhao et al. and are more reliable than the results from using only peak periods. A large number of strong motion stations are classified in Iran for more control of proposed SI applicability. The mean response spectral ratio curves for all data of ISMN stations are found to be fairly consistent with those obtained by Zhao et al. The results show the practicability and efficiency of the proposed method in site classification. However, more shear wave measurements and further information, like surface geology, borehole data etc., are still needed to clarify the uncertainties of such empirical schemes. 相似文献
11.
12.
地震数据本质上是时变的,不仅有效同相轴表现出确定性信号的时变特征,而且复杂地表和构造条件以及深部探测环境总是引入时变的非平稳随机噪声.标准的频率-空间域预测滤波只适合压制平面波信号假设下的平稳随机噪声,而处理非平稳地震随机噪声时,需要将数据体分割为小窗口进行分析,但效果不够理想,而传统非预测类随机噪声压制方法往往适应性不高,因此开发能够保护地震信号时变特征的随机噪声压制方法具有重要的工业价值.压缩感知是近年出现的一个新的采样理论,通过开发信号的稀疏特性,已经在地震数据处理中的数据插值以及噪声压制中得到了应用.本文系统地分析了压缩感知理论框架下的地震随机噪声压制问题,建立了阈值消噪的数学反演目标函数;针对时变有效信息具有的可压缩性,利用有限差分算法求解炮检距连续方程,构建有限差分炮检距连续预测算子(FDOC),在seislet变换框架下,提出一种新的快速稀疏变换域———FDOC-seislet变换,实现地震数据的高度稀疏表征;结合非平稳随机噪声不可压缩的特征,提出了一种整形迭代消噪方法,该方法是一种广义的迭代收缩阈值(IST)算法,在无法计算稀疏变换伴随算子的条件下,仍然能够对强噪声环境中的时变有效信息进行有效恢复.通过对模型数据和实际数据的处理,验证了FDOC-seislet稀疏变换域随机噪声迭代压制方法能够在保护复杂构造地震波信息的前提下,有效地衰减原始数据中的强振幅随机噪声干扰. 相似文献
13.
Lambert冰川-Amery冰架系统是南极冰盖最大的冰流系统之一,对南极冰盖物质平衡研究有着重要的作用.数字高程模型(DEM)是进行南极冰盖研究的基础.本文基于CryoSat-2 L1b波形数据,研究建立了Lambert冰川流域高分辨率DEM.测高卫星返回波形在冰盖区域存在变形,需进行波形重跟踪处理.利用交叉点分析方法对重心偏移法(OCOG)、阈值法和β参数法等常用的波形重跟踪方法对不同类型的CryoSat-2波形的适用性进行了研究.最后,利用克里金插值方法建立了500 m分辨率的Lambert冰川流域DEM——LAS DEM (Lambert Glacier-Amery Ice Shelf system DEM).利用ICESat卫星测高数据和GPS地面实测数据对LAS DEM进行精度验证,并与另外两种基于CryoSat-2数据的南极DEM进行了对比.结果表明:LAS DEM的整体精度约为0.295±2.7 m,优于另外两种CryoSat-2 DEM;在冰盖内陆地区,LAS DEM的高程误差在2 m之内;在Amery冰架上,LAS DEM的精度优于1 m. 相似文献
14.
《Acta Geochimica》2017,(2)
The increased production and price of rare earth elements(REEs) are indicative of their importance and of growing global attention. More accurate and practical exploration procedures are needed for REEs, and for other geochemical resources. One such procedure is a multivariate approach. In this study, five classifiers, including multilayer perceptron(MLP), Bayesian, k-Nearest Neighbors(KNN), Parzen, and support vector machine(SVM),were applied in supervised pattern classification of bulk geochemical samples based on REEs, P, and Fe in the Kiruna type magnetite-apatite deposit of Se-Chahun,Central Iran. This deposit is composed of four rock types:(1) High anomaly(phosphorus iron ore),(2) Low anomaly(metasomatized tuff),(3) Low anomaly(iron ore), and(4)Background(iron ore and others). The proposed methods help to predict the proper classes for new samples from the study area without the need for costly and time-consuming additional studies. In addition, this paper provides a performance comparison of the five models. Results show that all five classifiers have appropriate and acceptable performance. Therefore, pattern classification can be used for evaluation of REE distribution. However, MLP and KNN classifiers show the same results and have the highest CCRs in comparison to Bayesian, Parzen, and SVM classifiers. MLP is more generalizable than KNN and seems to be an applicable approach for classification and predictionof the classes. We hope the predictability of the proposed methods will encourage geochemists to expand the use of numerical models in future work. 相似文献
15.
16.
由于低的 摘 图像对比度、不可预测的前列腺位置和不确定的肠道气体,CT图像中自动和准确的前列腺分割是一个具有挑战性的问题。本文提出了一个基于随机森林的前列腺分割方法。利用自动上下文模型训练一系列的随机森林分类器,然后迭代地把这些训练好的分类器应用在测试图像上以改进前列腺的分类结果。实验结果表明,相比于其他最新方法,我们的方法性能更好。 相似文献
17.
储层岩相分布信息是油藏表征的重要参数,基于地震资料开展储层岩相识别通常具有较强的不确定性.传统方法仅获取唯一确定的岩相分布信息,无法解析反演结果的不确定性,增加了油藏评价的风险.本文引入基于概率统计的多步骤反演方法开展地震岩相识别,通过在其各个环节建立输入与输出参量的统计关系,然后融合各环节概率统计信息构建地震数据与储层岩相的条件概率关系以反演岩相分布概率信息.与传统方法相比,文中方法通过概率统计关系表征了地震岩相识别各个环节中地球物理响应关系的不确定性,并通过融合各环节概率信息实现了不确定性传递的数值模拟,最终反演的岩相概率信息能够客观准确地反映地震岩相识别结果的不确定性,为油藏评价及储层建模提供了重要参考信息.模型数据和实际资料应用验证了方法的有效性. 相似文献
18.
Image classification approaches are widely used in mapping vegetation on remotely sensed images. Vegetation assemblages are equivalent to habitats. Whereas sub-pixel classification approaches potentially can produce more realistic, homogenous habitat maps, pixel-based hard classifier approaches often result in non-homogenous habitat zones. This salt-and-pepper habitat mapping is particularly a challenge on images of savannas, given the characteristic patchy texture of scattered trees and grass. Image segmentation techniques offer possibilities for homogenous habitat classification. This study aimed at establishing the extent to which established, field surveyed and geology-related vegetation types in South Africa’s Kruger National Park (KNP) can be reproduced using image segmentation. Rain season Landsat TM images were used, selected to coincide with the peak in vegetation productivity, which was deemed the time of year when discrimination between key habitats in KNP is most likely to be successful. The multiresolution segmentation mode in eCognition 5.0 was employed, object classification accomplished using the nearest neighbour (NN) classifier, using object texture and training area mean values in the NN feature space.Compared to delineations of the vegetation types of KNP on a digital map of the vegetation zones that was tested, image segmentation successfully mapped the zones (overall accuracy 85.3%, K^ = 82.7%) despite slight shifts in the location of vegetation zone boundaries. Maximum likelihood classification (MLC) of the same images was only 37% accurate (K^ = 24.2%). Whereas the vegetation zones resulting from MLC were non-homogenous, with considerable spectral confusion among the vegetation zones, image segmentation produced more homogenous vegetation zones, comparably more useful for conservation management, because realistic and meaningful habitat maps are important in biodiversity conservation as input data upon which to base management decisions. Image segmentation appears to be a useful approach in mapping savanna vegetation. 相似文献
19.
A new temperature based method to separate rain and snow 总被引：2，自引：0，他引：2
Stefan W. Kienzle 《水文研究》2008,22(26):5067-5085
This paper presents the development and testing of a new method to estimate daily snowfall from precipitation and associated temperature records. The new method requires two variables; the threshold mean daily air temperature at which 50% of precipitation is considered snow, and the temperature range within which mixed precipitation can occur. Sensitivity analyses using 15 climate stations across south‐western Alberta, Canada, and ranging from prairie to alpine regions investigates the sensitivity of those two variables on mean annual snowfall (MAS), the coefficient of determination, and the MAS‐weighted coefficient of determination. Existing methods, including the static threshold method, one linear transition method used by Quick and Pipes, and the Leavesley method employed in the PRMS hydrological modelling system are compared with the new method, using a total of 963 years of daily data from the 15 climate stations used for the sensitivity analyses. Four different approaches to using the two input variables (threshold temperature and range) were tested and statistically compared: mean annual variables based on the 15 stations, mean annual variables for each station, mean monthly variables for each station, and a sine curve representing seasonal variation of the variables. In almost all cases the proposed new method resulted in higher MAS‐weighted coefficients of determination, and, on average, they were significantly different from those of other methods. The paper concludes with a decision tree to help decide which method and approach to apply under a variety of data availabilities. Copyright © 2008 John Wiley & Sons, Ltd. 相似文献
20.
Statistical facies classification from multiple seismic attributes: comparison between Bayesian classification and expectation–maximization method and application in petrophysical inversion 
下载免费PDF全文
下载免费PDF全文 We present here a comparison between two statistical methods for facies classifications: Bayesian classification and expectation–maximization method. The classification can be performed using multiple seismic attributes and can be extended from well logs to three‐dimensional volumes. In this work, we propose, for both methods, a sensitivity study to investigate the impact of the choice of seismic attributes used to condition the classification. In the second part, we integrate the facies classification in a Bayesian inversion setting for the estimation of continuous rock properties, such as porosity and lithological fractions, from the same set of seismic attributes. The advantage of the expectation–maximization method is that this algorithm does not require a training dataset, which is instead required in a traditional Bayesian classifier and still provides similar results. We show the application, comparison, and analysis of these methods in a real case study in the North Sea, where eight sedimentological facies have been defined. The facies classification is computed at the well location and compared with the sedimentological profile and then extended to the 3D reservoir model using up to 14 seismic attributes. 相似文献