Strength of ensemble learning in multiclass classification of rockburst intensity     

Junfei Zhang  Yuhang Wang  Yuantian Sun  Guichen Li 《国际地质力学数值与分析法杂志》2020,44(13):1833-1853

Rockbust is a violent expulsion of rock due to the extreme release of strain energy stored in surrounding rock mass, leading to considerable damages to underground strucures and equipment, and threatening workers' safety. As the operational depth of engineering projects increases, a larger number of factors influence the mechanism of rockburst. Therefore, accurate classification of rockburst intensity cannot be achieved based on conventional criteria. It is urgent to develop new models with high accuracy and ease to implement in practice. This study proposed an ensemble machine learning method by aggregating seven individual classifiers including back propagation neural network, support vector machine, decision tree, k-nearest neighbours, logistic regression, multiple linear regression and Naïve Bayes. In addition, we proposed nine data imputation methods to replace the missing values in the compiled database including 188 rockburst instances. Five-fold cross validation and the beetle antennae search algorithm are used to tune hyperparameters and voting weights of the individual classifiers. The results show that the rockburst classification accuracy obtained by the classifier ensemble has increased by 15.4% compared with the best individual classifier on the test set. The predictor importance obtained by the classifier ensemble shows that the elastic energy index is the most sensitive input variable for rockburst intensity classification. This robust ensemble method can be extended to solve other classification problems in underground engineering projects.  相似文献   

基于决策融合的SPOT-6影像土地覆被分类研究     

李宏达  高小红  汤敏 《地球信息科学学报》2021,23(5):928-937

多分类器决策融合方法在提高遥感影像分类的准确性和可靠性方面已表现出了巨大潜力,但这一过程中对所有像元多次分类会产生巨大的时间代价,为改善这一问题,本文提出了主分类器的概念。在青海湟水流域确定2个试验区,对7种常用的分类器进行评估,排除精度较低的3种分类器后,选择支持向量机（Support Vector Machine, SVM）、多层感知机（Multilayer Perceptron, MLP）、随机森林（Random Forest, RF）和梯度提升树（Gradient Boosting Decision Tree, GBDT）4种不同的分类器,建立决策规则共同对SPOT-6影像分类。为提高分类效率,以精度最高的GBDT作为主分类器对影像分类后,仅对结果中可信度不高的像元使用多分类器共同决策。研究结果表明,2个区域内主分类器独立完成分类的像元分别占38.10%和65.26%,错分率为1.57%和2.18%;多分类器共同决策的区域,相比GBDT的分类结果,总体精度分别高出2.49%和3.66%。整体上看,决策融合使2个区域的总体分类精度分别提高了1.18%和1.09%,能够有效减少分类结果中的“椒盐噪声”,精度更加均衡。相比现有的决策融合方法,主分类器的使用在保证分类精度的同时有利于分类效率的提高及分类结果保持良好的一致性。  相似文献   

基于高分卫星影像的复杂山区光伏电站信息提取          下载免费PDF全文

刘芸  宋善海  李慧璇  田鹏举  王伟 《中低纬山地气象》2023,47(3):76-80

该文基于高分卫星资料,通过基于规则的面向对象分类、基于最邻近法的监督分类及基于CART分类器的监督分类三种不同分类方法,对复杂山区光伏电站进行提取,对比三种分类提取方法结果并完成精度验证。结果表明,合理的分割参数有利于提高光伏电站提取精度;基于规则的面向对象分类法光伏电站提取精度最佳,最邻近分类法次之,CART分类器分类法最差,可利用基于规则的面向对象分类法较为准确地进行复杂山区光伏电站信息提取,为光伏产业健康、合理发展提供一定的数据支撑。  相似文献   

基于嘴唇色度Fisher分类的驾驶疲劳视觉检测     

孙伟  张小瑞  唐慧强  张为公 《南京气象学院学报》2011,(4):324-330

为提高驾驶疲劳检测的准确率和可靠性,利用唇色和肤色的色度分布差异,挑选3个典型颜色特征构建Fisher分类器用于提取唇色区域.采用区域连通算法对二值唇色区域进行滤波处理,运用改进积分投影算法确定嘴唇边界,根据嘴巴开合度及打呵欠频率判断驾驶员是否疲劳.实验结果表明:基于3个颜色特征构建的Fisher分类器在唇色提取效果上明显优于单一颜色特征的提取效果;改进的积分投影算法能提高嘴唇边界定位的精度和速度;基于打呵欠频率的驾驶疲劳检测方法具有更优的检测准确率和可靠性.融合多个典型颜色特征可改善唇色提取的鲁棒性和可靠性,有助于驾驶疲劳检测效果的提高.  相似文献   

A semi-ellipsoid-model based fuzzy classifier to map grassland in Inner Mongolia,China     

《ISPRS Journal of Photogrammetry and Remote Sensing》2013

Remote sensing techniques offer effective means for mapping plant communities. However, mapping grassland with fine vegetative classes over large areas has been challenging for either the coarse resolutions of remotely sensed images or the high costs of acquiring images with high-resolutions. An improved hybrid-fuzzy-classifier (HFC) derived from a semi-ellipsoid-model (SEM) is developed in this paper to achieve higher accuracy for classifying grasslands with Landsat images. The Xilin River Basin, Inner Mongolia, China, is chosen as the study area, because an acceptable volume of ground truthing data was previously collected by multiple research communities. The accuracy assessment is based on the comparison of the classification outcomes from four types of image sets: (1) Landsat ETM+ August 14, 2004, (2) Landsat TM August 12, 2009, (3) the fused images of ETM+ with CBERS, and (4) TM with CBERS, respectively, and by three classifiers, the proposed HFC-SEM, the tetragonal pyramid model (TPM) based HFC, and the support vector machine method. In all twelve classification experiments, the HFC-SEM classifier had the best overall accuracy statistics. This finding indicates that the medium resolution Landsat images can be used to map grassland vegetation with good vegetative detail when the proper classifier is applied.  相似文献   

Mapping dominant vegetation communities at Meili Snow Mountain,Yunnan Province,China using satellite imagery and plant community data     

Z. Zhang  E. De Clercq  X. K. Ou  R. De Wulf  L. Verbeke 《国际地球制图》2013,28(2):135-153

Mapping dominant vegetation communities is important work for vegetation scientists. It is very difficult to map dominant vegetation communities using multispectral remote sensing data only, especially in mountain areas. However plant community data contain useful information about the relationships between plant communities and their environment. In this paper, plant community data are linked with remote sensing to map vegetation communities. The Bayesian soft classifier was used to produce posterior probability images for each class. These images were used to calculate the prior probabilities. One hundred and eighty plant plots at Meili Snow Mountain, Yunnan Province, China were used to characterize the vegetation distribution for each class along altitude gradients. Then, the frequencies were used to modify the prior probabilities of each class. After stratification in a vegetation part and a non-vegetation part, a maximum-likelihood classification with equal prior probabilities was conducted, yielding an overall accuracy of 82.1% and a kappa accuracy of 0.797. Maximum-likelihood classification with modified prior probabilities in the vegetation part, conducted with a conventional maximum-likelihood classification for the non-vegetation part, yielded an overall accuracy of 87.7%, and a kappa accuracy of 0.861.  相似文献   

基于激光诱导击穿光谱的贺兰石识别分析     

孟长峰  薛俊辉  郭冬发  胡勇 《铀矿地质》2017,(4):234-240

利用激光诱导击穿光谱(Laser Induced Breakdown Spectroscopy:LIBS)分析技术实现对贺兰石样品的实时、快速分析。实验基于LIBS技术采集贺兰石光谱数据,利用三次样条插值、数据平滑、标准正态校正等数据预处理方法,结合线性判别分析进行特征提取,利用贝叶斯分类器实现了贺兰石样品的快速、准确分析。实验结果表明该方法对贺兰石平均识别率为:99.5%,标准差1.31%,说明该方法识别贺兰石效果较好。  相似文献   

Mapping detention basins and deriving their spatial attributes from airborne LiDAR data for hydrological applications     

Hongxing Liu  Lei Wang 《水文研究》2008,22(13):2358-2369

This paper presents a new technique for mapping detention basins and measuring their spatial attributes using high‐resolution airborne LiDAR (Light Detection and Ranging) data. An efficient least‐cost search algorithm is employed to identify surface depressions from a bare‐earth LiDAR digital elevation model (DEM). Surface depressions are automatically delineated into hydrological objects using the connected component identification and indexing algorithm. Various spatial attributes are derived for these hydrologic objects, including location, perimeter, surface area, depth, storage volume and shape properties. Based on spatial attributes, a rule‐based classifier is established to separate detention basins from other types of surface depressions. We have successfully applied our technique to an urban watershed in the Houston Metropolitan area, Texas. Detention basins at regional and residential subdivision levels are mapped out for the watershed, and measurements on the spatial attributes are derived for each detention basin. The quantitative information derived from LiDAR data provides a scientific basis for formulating an appropriate management plan for detention basins and for assessing their effects on flood control and storm water quality treatment. Copyright © 2007 John Wiley & Sons, Ltd.  相似文献   

基于支持向量机的遥感图像分类方法   总被引：19，自引：0，他引：19  

惠文华 《地球科学与环境学报》2006,28(2):93-95

为了提高遥感图像分类的精度,弥补传统最大似然分类方法所固有的分类时样本不足的缺陷,提出了一种基于支持向量机、光谱特征和纹理特征相结合的遥感图像分类方法。采用ETM数据,按照其所提方法进行了具体分类实验,并将实验结果与最大似然法分类的结果进行了比较分析。结果表明,利用基于支持向量机的方法进行遥感图像分类,精度明显优于最大似然法分类的精度。利用光谱特征与纹理特征相结合进行分类比单纯运用光谱特征进行分类效果要好。  相似文献   

北京上海近20 a城市化过程中 土地利用变化异同点探析   总被引：2，自引：2，他引：0  

缪丽娟  崔雪锋  栾一博  何斌 《气象科学》2011,31(4):398-404

城市化进程下土地利用格局变化以及驱动力分析是当前国内学者研究的热点。本文利用C5决策树分类方法分别提取北京、上海1990s以来的三期遥感影像分类图,揭示两市城市用地格局变化的空间规律及其异同点。结果表明：过去的20 a来北京地区以北京市辖区为中心呈现低密度式蔓延扩张;上海城市用地呈“单中心、多卫星城”同时扩张,并且东部沿江地区发展速度较快。将研究区按扩张程度分为：高度扩张区、中度扩张区、低度扩张区。从空间上看,上海城市用地扩张比北京明显,在扩张的过程中占用了大量耕地,上海地区尤为明显。同时,人口增长、产业结构调整等是城市化进程中土地利用变化的主要驱动力因子,需要将来更多的相关研究。  相似文献