检索结果-内蒙古大学图书馆

Unsupervised classification of polarimetric SAR images by EM algorithm

IEICE TRANSACTIONS ON COMMUNICATIONS 2007年第12期E90B卷 3632-3642页

作者： Khan, Kamran-Ullah Yang, Jian Zhang, Weijie Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

In this paper, the expectation maximization (EM) algorithm is used for unsupervised classification of polarimetric synthetic aperture radar (SAR) images. The EM algorithm provides an estimate of the parameters of the underlying probability distribution functions (pdf's) for each class. The feature vector is 9-dimensional, consisting of the six magnitudes and three angles of the elements of a coherency matrix. Each of the elements of the feature vector is assigned a specific parametric pdf. In this work, all the features are supposed to be statistically independent. Then we present a two-stage unsupervised clustering procedure. The EM algorithm is first run for a few iterations to obtain an initial partition of, for example, four clusters. A randomly selected sample of, for example, 2% pixels of the polarimetric SAR image may be used for unsupervised training. In the second stage, the EM algorithm may be run again to reclassify the first stage clusters into smaller sub-clusters. Each cluster from the first stage will be processed separately in the second stage. This approach makes further classification possible as shown in the results. The training cost is also reduced as the number of feature vector in a specific cluster is much smaller than the whole image.

关键词： expectation maximization (EM) clustering unsupervised classification probability distribution function

来源：评论

学校读者我要写书评

暂无评论

Sensing orthogonal frequency division multiplexing systems for cognitive radio with cyclic prefix and pilot tones

引用

IET COMMUNICATIONS 2012年第1期6卷 97-106页

作者： Chen, Z. Luan, T. Zhang, X. -D. Tsinghua Univ Dept Automat Natl Lab Informat Sci & Technol State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China

The detection of orthogonal frequency division multiplexing (OFDM) for cognitive radio is considered in this paper. A frequency-selective fading channel is considered and the receiving process is modeled with timing and frequency offsets. Firstly, the authors propose a new decision statistic based on time-domain cross-correlation of the cyclic prefix (CP) embedded in OFDM signals. The probability distribution functions (PDFs) of the statistics under both hypotheses of primary signal absence and presence are derived. Estimation of the timing and frequency offset is obtained through the maximum likelihood method and the received signals are modified. Then another new decision statistic based on frequency-domain cross-correlation of the pilot tones (PTs) is proposed whose PDF is also analyzed. Then, through the likelihood ratio test, the authors utilize CP and PT jointly and propose a global test statistic. The theoretical probabilities of false alarm (PFA) and detection are derived, and the theoretical threshold for any given PFA is proposed. The simulation results show that the proposed spectrum-sensing scheme has excellent performance, especially under very low signal-to-noise ratio (SNR).

关键词： time-domain cross-correlation false alarm probability spectrum-sensing scheme timing offset maximum likelihood method signal-to-noise ratio maximum likelihood estimation probability fading channels decision statistic Modulation and coding methods pilot tones OFDM orthogonal frequency division multiplexing OFDM modulation likelihood ratio test PFA global test statistic probability distribution function PDF frequency-selective fading channel frequency-domain cross-correlation cyclic prefix Radio links and equipment cognitive radio frequency offset SNR Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

KS entropy and mean Lyapunov exponent for coupled map lattices

引用

PHYSICA A 2001年第1-4期292卷 182-192页

作者： Shibata, H Sojo Univ Dept Gen Educ Kumamoto 8600082 Japan

The statistics of Kolmogorov-Sinai (KS) entropy for a coupled map lattice model are analyzed from the viewpoint of the thermodynamic formalism. It is shown that the fluctuation of KS entropy for a coupled map lattice model satisfies the large deviation statistics. Also, the probability density of Lyapunov exponents (PDLE) is studied and it is shown that the PDLE gives the measure of the irregularity for the spatio-temporal patterns. Mean Lyapunov exponent is introduced and compared with KS entropy. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： mean Lyapunov exponent KS entropy coupled map lattices probability distribution function thermodynamic formalism

来源：评论

学校读者我要写书评

暂无评论

A probabilistic approach to solve the economic dispatch problem with intermittent renewable energy sources

引用

ENERGY 2015年 82卷 949-959页

作者： Osorio, G. J. Lujano-Rojas, J. M. Matias, J. C. O. Catalao, J. P. S. Univ Beira Interior P-6201001 Covilha Portugal INESC ID Lisbon Portugal Univ Lisbon IST P-1699 Lisbon Portugal

In this paper, a methodology for solving the ED (economic dispatch) problem considering the uncertainty of wind power generation and generators reliability is presented. The corresponding PDF (probability distribution function) of available wind power generation is discretized and introduced in the optimization problem in order to probabilistically describe the power generation of each thermal unit, wind power curtailment, ENS (energy not supplied), excess of power generation, and total generation cost. The reliability of each unit is incorporated by estimating the joint PDF of power generation and failure events, while the PDF of ENS is incorporated by convoluting the PDF of ENS due to the forecasting error and any failure event. The performance of the proposed approach is analyzed by studying two power systems of 5 and 10 units. The proposed method is compared to MCS (Monte Carlo Simulation) approach, being able to reproduce the PDF in a reasonable manner, specifically when system reliability is not taken into account. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Economic dispatch problem Greenhouse gas emissions Power system reliability Wind power forecasting error probability distribution function

来源：评论

学校读者我要写书评

暂无评论

STOCHASTIC MODELING AND ANALYSIS OF PROPAGATION DELAYS IN GAAS ADDERS

引用

IEEE TRANSACTIONS ON COMPUTERS 1991年第1期40卷 31-45页

作者： PERUNICIC, B LAKHANI, S MILUTINOVIC, V PURDUE UNIV SCH ELECT ENGN W LAFAYETTE IN 47907 USA UNIV BELGRADE SCH ELECT ENGN YU-11000 BELGRADE YUGOSLAVIA

There are a number of important differences between GaAs and Silicon which are relevant for computer architecture/design. One difference, which may have an important impact on computer architecture design, is that GaAs gates, when exposed to high radiation levels, may change their propagation delay. In other words, gates continue to function, but with different gate delays. Typically, at the design time, certain clock or other margins are included, and the problem is to determine the probability with which a given margin will work at the post-radiation time. In this paper, we introduce an original methodology which solves the problem for combinational circuits of arbitrary topology (without loops). We demonstrate its capabilities through the modeling and analysis of propagation delays in GaAs adders. This methodology is directly applicable to a number of analogous problems in other fields.

关键词： ADDERS CARRY-LOOK-AHEAD ADDER CARRY-SELECT ADDER FULL ADDER probability distribution function PROPAGATION DELAY RAYLEIGH RIPPLE-CARRY ADDER STOCHASTIC MODELING

来源：评论

学校读者我要写书评

暂无评论

Breakpoint detection in non-stationary runoff time series under uncertainty

引用

JOURNAL OF HYDROLOGY 2020年 590卷 125458-125458页

作者： Farsi, Niloofar Mahjouri, Najmeh Ghasemi, Hamid KN Toosi Univ Technol Fac Civil Engn Tehran Iran

Most conventional hydrological time series models, used for forecasting or synthetic data generation, are based on the stationary hypothesis. Hydrologic variables such as surface runoff discharge exhibit non-stationary behavior due to the effects of climate change or human activities. In this paper, a new methodology is proposed to analyze the uncertainty of the number and location of breakpoints in runoff time series. The non-stationary runoff time series is simulated by segmenting the series into stationary pieces, which follow an Auto-Regressive Moving Average (ARMA) process, based on the minimum description length (MDL) principle. The length of each piece and the order of the piecewise ARMA model are optimized using the Genetic Algorithm (GA). Several runoff time series with variable lengths are generated based on the observed data and the probability distribution function(s) (PDFs) of breakpoint location(s) are constructed. An optimal set of breakpoint locations are found for each generated runoff time series by minimizing the objective function based on the MDL. Finally, the PDF(s) of breakpoint location(s) is (are) constructed using the results of the mentioned optimization model. To evaluate the proposed methodology, it is applied to the case study of Zayandehrud River in Iran. According to the obtained breakpoint PDF for the runoff time series, three breakpoints around years of 1987, 1996 and 2006 are identified. The results are analyzed by investigating the time series of agricultural lands derived using remote sensing data and studying the impacts of interbasin water transfer projects implemented in the study area. Overall, investigating human-induced changes in the study area confirms the obtained shape of the PDF of runoff breakpoint and shows the good performance of the developed method for finding the number and location of breakpoints in the runoff time series.

关键词： Breakpoint Uncertainty Non-stationarity Runoff time series probability distribution function

来源：评论

学校读者我要写书评

暂无评论

Hydrologic controls on basin- scale distribution of benthic invertebrates

引用

WATER RESOURCES RESEARCH 2014年第4期50卷 2903-2920页

作者： Ceola, Serena Bertuzzo, Enrico Singer, Gabriel Battin, Tom J. Montanari, Alberto Rinaldo, Andrea Univ Bologna Dept DICAM Bologna Italy Ecole Polytech Fed Lausanne Sch Architecture Civil & Environm Engn Lab Ecohydrol Lausanne Switzerland Univ Vienna Dept Limnol & Oceanog Vienna Austria Leibniz Inst Freshwater Ecol & Inland Fisheries Dept Ecohydrol Berlin Germany WasserCluster Lunz Interuniv Ctr Aquat Ecosyst Res Lunz am See Austria Univ Padua Dipartimento Ingn Civile Edile & Ambientale Padua Italy

Streamflow variability is a major determinant of basin-scale distributions of benthic invertebrates. Here we present a novel procedure based on a probabilistic approach aiming at a spatially explicit quantitative assessment of benthic invertebrate abundance as derived from near-bed flow variability. Although the proposed approach neglects ecological determinants other than hydraulic ones, it is nevertheless relevant in view of its implications on the predictability of basin-scale patterns of organisms. In the present context, aquatic invertebrates are considered, given that they are widely employed as sensitive indicators of fluvial ecosystem health and human-induced perturbations. Moving from the analytical characterization of site-specific probability distribution functions of streamflow and bottom shear stress, we achieve a spatial extension to an entire stream network. Bottom shear stress distributions, coupled with habitat suitability curves derived from field studies, are used to produce maps of invertebrate suitability to shear stress conditions. Therefore, the proposed framework allows one to inspect the possible impacts on river ecology of human-induced perturbations of streamflow variability. We apply this framework to an Austrian river network for which rainfall and streamflow time series, river network hydraulic properties, and local information on invertebrate abundance for a limited number of sites are available. A comparison between observed species density versus modeled suitability to shear stress is also presented. Although the proposed strategy focuses on a single controlling factor and thus represents an ecological minimal model, it allows derivation of important implications for water resource management and fluvial ecosystem protection.

关键词： hydrology bottom shear stress streamflow benthic invertebrate probability distribution function

来源：评论

学校读者我要写书评

暂无评论

Lambert function and a new non-extensive form of entropy

引用

IMA JOURNAL OF APPLIED MATHEMATICS 2007年第6期72卷 785-800页

作者： Shafee, Fariel Princeton Univ Dept Phys Princeton NJ USA

We propose a new way of defining entropy of a system, which gives a general form that is non-extensive like Tsallis entropy, but is linearly dependent on component entropies, like Renyi entropy, which is extensive. This entropy has a conceptually novel but simple origin and is mathematically easy to define by a very simple expression involving a derivative. It leads to a probability distribution function involving the Lambert function resulting from optimizing the entropy, which has hitherto never appeared in this context, and is somewhat more complex than the Shannon or Boltzmann form, but is nevertheless mathematically quite tractable. We have compared it numerically with the Tsallis and Shannon entropies. We have also considered constraints on the energy spectra imposed by the properties of the Lambert function, which are absent in the Shannon form. It may turn out to be a more appropriate candidate in a physical situation where the probability distribution does not suit any of the previously defined forms, especially when the probability density function sought is expected to be stiffer than that resulting from maximizing the other entropies. We consider the problem of defining free energy and other thermodynamic functions when the entropy is given as a general function of the probability distribution, including that for non-extensive forms. We then find that the free energy, which is central to the determination of all other quantities of interest in a thermodynamic context, can be obtained uniquely, at least numerically, even when it is the root of a transcendental equation. In particular, we examine the cases of the Tsallis form and the new form proposed by us. We compare the free energy, the internal energy and the specific heat of a simple system of two energy states for each of these forms and find significant departures for some quantities, while some others are less sensitive to the parametrization.

关键词： Lambert function non-extensive entropy probability distribution function free energy

来源：评论

学校读者我要写书评

暂无评论

Geometrical Monte Carlo model of liquid-phase sintering

引用

MATHEMATICS AND COMPUTERS IN SIMULATION 2010年第7期80卷 1469-1486页

作者： Luque, A. Aldazabal, J. Martinez-Esnaola, J. M. Martin-Meizoso, A. Sevillano, J. Gil Farr, R. S. Univ Navarra Dept Mat CEIT San Sebastian 20018 Spain Univ Navarra Tecnun San Sebastian 20018 Spain Unilever Res Labs NL-3133 AT Vlaardingen Netherlands

Liquid-phase sintering (LPS) is an industrial process used to consolidate materials composed of two different kinds of metallic and/or ceramic powders. At constant temperature, the amount of the present liquid-phase is constant However, the shape of particles of solid phase changes over time In general, the rounding of particles and the growth of big particles at the expense of the small ones are observed This process is known as Ostwald ripening. In this work, we propose a Monte Carlo (MC) model to simulate the microstructural evolution during LPS The discretizing elements of the system. namely the voxels. change state between solid and liquid. according to previously defined melting and solidification probability distribution functions (PDFs) The generated PDFs take into account the geometrical characteristics of the system particles in terms of number of solid neighbours that surround a randomly chosen voxel The geometrical MC model that we present is able to reproduce the Ostwald ripening behaviour and, in particular, matches the case in which the process occurs limited by the attachment/detachment of the solid phase to/from the surface of the particle (C) 2009 IMACS Published by Elsevier B V All rights reserved.

关键词： Liquid-phase sintering Ostwald ripening Monte Carlo model probability distribution function Reaction limited kinetics

来源：评论

学校读者我要写书评

暂无评论

Fragmented edge structure coding for Chinese writer identification

引用

NEUROCOMPUTING 2012年 86卷 45-51页

作者： Wen, Jing Fang, Bin Chen, JunLin Tang, YuanYan Chen, HengXin Chongqing Univ Coll Comp Chongqing 400044 Peoples R China

As a branch of biometrics, handwriting-based writer identification is an active research topic in pattern recognition. This paper presents a theoretically very simple, yet efficient, multiresolution approach to off-line, text-independent Chinese writer identification based on edge structure code (ESC) distribution feature and nonparametric discrimination of sample. ESC distribution feature is based on probability distribution function, which characterizes the frequent structures distribution of edge fragments on multiple scales. Experiments were conducted on an open HIT-MW database which is widely used for performance evaluation. Experimental results show that the proposed method was able to improve the identification accuracy. Crown Copyright (C) 2012 Published by Elsevier B.V. All rights reserved.

关键词： Text-independent writer identification Edge fragments Encoding feature probability distribution function Chi-square distance Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：