基于随机森林模型的陆地卫星-8遥感影像森林植被分类

以黑龙江省漠河县为研究区域,采用陆地卫星-8遥感影像为数据源,结合影像的光谱信息和数字高程模型辅助数据,分别采用最大似然分类法(MLC)和随机森林模型法(RFM)对研究区森林植被进行分类,并分析和评价光谱特征变量对模型的重要性、2种分类方法对森林植被类型分类的适用性。结果表明:随机森林分类方法的总体分类精度为81.65%、卡帕(Kappa)系数为0.812。与传统的MLC方法相比,RFM法均提高了3种森林类型的生产者精度和使用者精度,其中针阔混交林精度提高最多。通过分析特征变量的重要性,发现高程、归一化植被指数、红光波段、近红外波段、短波红外波段对模型分类精度有较重要的影响。说明随机森林模型方法结合多源信息是森林植被类型遥感分类的一种有效手段。

原油可采储量预测新方法探讨

原油可采储量是制定油田开发规划的基础,是评价油田开发效果、编制调整方案的依据.原油可采储量预测方法主要有静态法、童宪章图版法、水驱特征曲线法、递减曲线法和增长曲线法.作者提出了原油可采储量预测的新方法,改进流管法和随机模型法.它们是作者多年研究的体会,其适用性正在大港油田原油可采储量预测工作中进行检验,已取得较好的效果.

语音识别系统的简述

通过对语音识别技术的研究,帮助机器人像人类一样流畅的讲出要表达的意识和建议。常用的语音识别方法有模板匹配法、随机模型法和概率语法分析法,随机模型法是目前的主流方法。

生态学中的尺度问题——尺度上推

尺度推绎是生态学理论和应用的核心。如何在一个异质景观中进行尺度推绎仍然是一个悬而未决的科学难题,是对当今生态学家在全球变化背景下研究环境问题的重大挑战。就目前的研究,一般可分为四大类尺度推绎途径:空间分析法(如分维分析法和小波分析法)、基于相似性的尺度上推方法、基于局域动态模型的尺度上推方法、随机(模型)法。基于相似性的尺度上推方法来源于生物学上的异量关联,可将其思想延伸至空间上,研究物种丰富度、自然河网、地形特征、生态学格局或过程变量和景观指数等。基于局域动态模型的尺度上推方法需要首先确定是否进行跨尺度推绎,以及是否考虑空间单元之间的水平相互作用和反馈,然后再应用具体的方法或途径,如简单聚合法、有效值外推法、直接外推法、期望值外推、显式积分法和空间相互作用模拟法等。随机(模型)法以其它尺度上推方法为基础,根据研究的是单个景观,还是多个景观,采用不同的途径。理解、定量和降低尺度推绎结果的不确定性已经变得越来越重要,但相关研究仍然极少。以上所有有关尺度推绎的方法、途径和结果分析共同构成了尺度推绎的概念框架。

Reliability analysis for seismic stability of tunnel faces in soft rock masses based on a 3D stochastic collapse model

A new horn failure mechanism was constructed for tunnel faces in the soft rock mass by means of the logarithmic spiral curve. The seismic action was incorporated into the horn failure mechanism using the pseudo-static method. Considering the randomness of rock mass parameters and loads, a three-dimensional (3D) stochastic collapse model was established. Reliability analysis of seismic stability of tunnel faces was presented via the kinematical approach and the response surface method. The results show that, the reliability of tunnel faces is significantly affected by the supporting pressure, geological strength index, uniaxial compressive strength, rock bulk density and seismic forces. It is worth noting that, if the effect of seismic force was not considered, the stability of tunnel faces would be obviously overestimated. However, the correlation between horizontal and vertical seismic forces can be ignored under the condition of low calculation accuracy.

Two-stage stochastic approach for spinning reserve allocation in dynamic economic dispatch

A novel approach was proposed to allocate spinning reserve for dynamic economic dispatch.The proposed approach set up a two-stage stochastic programming model to allocate reserve.The model was solved using a decomposed algorithm based on Benders' decomposition.The model and the algorithm were applied to a simple 3-node system and an actual 445-node system for verification,respectively.Test results show that the model can save 84.5 US $ cost for the testing three-node system,and the algorithm can solve the model for 445-node system within 5 min.The test results also illustrate that the proposed approach is efficient and suitable for large system calculation.

Random noise suppression for seismic data using a non-local Bayes algorithm

For random noise suppression of seismic data, we present a non-local Bayes （NL- Bayes） filtering algorithm. The NL-Bayes algorithm uses the Gaussian model instead of the weighted average of all similar patches in the NL-means algorithm to reduce the fuzzy of structural details, thereby improving the denoising performance. In the denoising process of seismic data, the size and the number of patches in the Gaussian model are adaptively calculated according to the standard deviation of noise. The NL-Bayes algorithm requires two iterations to complete seismic data denoising, but the second iteration makes use of denoised seismic data from the first iteration to calculate the better mean and covariance of the patch Gaussian model for improving the similarity of patches and achieving the purpose of denoising. Tests with synthetic and real data sets demonstrate that the NL-Bayes algorithm can effectively improve the SNR and preserve the fidelity of seismic data.

Estimation of Geodetic Parameters with VLBI Data of Last 5 Years

The meaning to research the potential of VLBI for geodetic applications is summarized. And the observation models and their related parameters of geodetic interest are investigated. Then, the principle and method of using the random model in VLBI data processing are investigated. With the world wide VLBI data from 2000-2004, the conditions to compute the parameters of geodetic interest are introduced, and so are the computing methods and processes. And the computed resuits of the parameters of geodetic interest are analyzed.

An efficient latent variable optimization approach with stochastic constraints for complex industrial process

For complex chemical processes,process optimization is usually performed on causal models from first principle models.When the mechanism models cannot be obtained easily,restricted model built by process data is used for dynamic process optimization.A new strategy is proposed for complex process optimization,in which latent variables are used as decision variables and statistics is used to describe constraints.As the constraint condition will be more complex by projecting the original variable to latent space,Hotelling T^2 statistics is introduced for constraint formulation in latent space.In this way,the constraint is simplified when the optimization is solved in low-dimensional space of latent variable.The validity of the methodology is illustrated in pH-level optimal control process and practical polypropylene grade transition process.

OUTLIER TEST IN RANDOMIZED LINEAR MODEL

In this papert we give an approach for detecting one or more outliers inrandomized linear model.The likelihood ratio test statistic and its distributions underthe null hypothesis and the alternative hypothesis are given. Furthermore,the robustnessof the test statistic in a certain sense is proved. Finally,the optimality properties of thetest are derived.

Research on the Computer Network Protocol Test Model based on Genetic and Random Walk Algorithm

In this paper, we conduct research on the computer network protocol test model based on genetic and random walk algorithm.Network protocol is the abstract concept, is important in the process of the development of network system. Fully understand and grasp of thenetwork protocols for managers is there is a big diffi cult. Network covert channel is the evaluation of intrusion detection system and fi rewallsecurity performance of an important means, the paper will start from the angle of the attacker, the fl aws of the research, and use this kind ofdefect to realize network covert channel, the random walk algorithm will be feasible for dealing with this issue. For achieving this, we integratethe genetic and random walk algorithm for systematic optimization.

Spatial Probabilistic Model of Block Failure Capacity of Piles in Clay

A probability based model of block failure capacity of pile foundation in clay soil under axial load is developed. The model was based on the first order second moment method. Instead of using point variability, the soil inherent variability is modelled as random field model. Based on this model, a reliability based factor of safety for designing pile group foundation, taking into account bock failure mechanism, is proposed. Furthermore, using simplified lognormal model, the relationship between the factor of safety used in design practice and target reliability may be derived explicitly.

Application of Extreme Value Theory to Generation and Analysis of Pseudorandom Samples

The article deals with the methodology of pseudorandom data analysis. As a mathematical tool for carrying out the research the extreme value theory was used that creates one of the directions in mathematical statistics, and is related to investigating the extreme deviations from the median values in probability distributions. Also, the methods for estimating unknown parameters and algorithm of random-number generation are discussed. The models of treatment the extreme values are constructed which are based on machine generated sample and approach is proposed for their future application for constructing forecasting models.

Accuracy Improvement of Zenith Tropospheric Delay Estimation Based on GPS Precise Point Positioning Algorithm

In the precise point positioning(PPP),some impossible accurately simulated systematic errors still remained in the GPS observations and will inevitably degrade the precision of zenith tropospheric delay(ZTD) estimation.The stochastic models used in the GPS PPP mode are compared.In this paper,the research results show that the precision of PPP-derived ZTD can be obviously improved through selecting a suitable stochastic model for GPS measurements.Low-elevation observations can cover more troposphere information that can improve the estimation of ZTD.A new stochastic model based on satellite low elevation cosine square is presented.The results show that the stochastic model using satellite elevation-based cosine square function is better than previous stochastic models.

Subspace identification for a stochastic model of plague

In this paper, a stochastic model of plague is first studied by subspace identification. First, the discrete model of plague is obtained based on the classical model. The corresponding stochastic model is proposed for the existence of stochastic disturbances. Second, for the model, the parameter matrices and noise intensity are obtained. Finally, the simulations of the model show that the subspace identification is more precise than least square method.