HPD Prediction Intervals for Rayleigh Distribution

Using Jeffreys' non-informative prior, the predictive pdf of a future observation and that of the k-th order statistic of a future sample from a Rayleigh distribution have been obtained. Bayes predictive estimators and highest posterior density (HPD) prediction intervals for the future observation and the k-th order statistic are derived. A numerical example is given.     

Prediction Intervals for the 2-Parameter Exponential Distribution Using Incomplete Data

This paper constructs prediction intervals for the l-th smallest observation and the mean lifetime of a future sample taken from a 2-parameter exponential distribution. The intervals are based on incomplete data, that is, where data may be missing from both extremes and/or elsewhere. These results are extended to some other distributions and provide conservative prediction intervals for the class of distributions with increasing failure rate.     

基于逆高斯分布的复合高斯海杂波建模研究

复合高斯(CG)分布模型广泛应用于非高斯杂波建模,其纹理分量决定了杂波的非高斯特性。该文采用逆高斯分布的纹理分量建立了一种双参数复合高斯分布海杂波模型,即逆高斯-复合高斯(IG-CG)分布,并推导了其统计特性。同时,利用IPIX 型雷达杂波数据进行拟合分析,结果表明该文建立的双参数IG-CG 分布模型相对于单参数IG-CG 分布模型和K 分布模型,其残差平方和平均降低了30%和60%,能够更加准确地与实测数据相吻合。      

基于逆高斯几率模型的心率预测算法

心跳间隔时间序列可模拟为逆高斯模型,由点过程自适应算法估计模型时变参数和预测心率.本文在现有的一步参数预测算法基础上,首先利用模型参数均值和加权因子修正算法提高模型时变参数的预测精度;然后利用线性预测简化了点过程自适应滤波预测算法,实现了心率变化的实时分析.实验仿真表明:改进后的算法对心率分析和预测有很好的效果.     

Prediction Intervals for IFR Distributions

Several prediction intervals for the class of increasing failure rate distributions are obtained. They extend some known results on 1-or 2-parameter exponential distributions. The use of these results requires no new tables.     

Bivariate Gamma Distribution from Complex Inverse Wishart Matrix

In this letter, a new form of bivariate gamma distribution is proposed from the complex inverse Wishart matrix. We have derived the closed-form expressions for the probability density function and the joint central moments of this bivariate gamma distribution. Finally, the analytical results are used to obtain the outage probability for a multiple-inputmultiple-output wireless communication systems with two transmit antennas.     

Instrumentation Location Diversity Paradigm for Future Astronomy Observations

Capital constrained organizations desiring to conduct astronomy observations face significant challenges due to the high cost of acquiring telescopes and computing facilities. Approaches such as re-using discarded earth stations can reduce telescope acquisition costs. In addition, an increasing population also reduces land suitability and availability for establishing radio quiet zones. These challenges affect the ability of capital constrained astronomy organizations in high population density regions to conduct astronomy observations. This paper proposes the use of drones to address these challenges. Drone based telescopes and computing systems in the airspace are less reliant on land resources. They can be used to conduct astronomy observations in high population regions. The paper presents the architecture of the drone based astronomy system and discusses relations between the drone and terrestrial astronomy systems. The performance benefits of the proposed architecture are investigated by formulating a model and conducing numerical simulation. It can be seen that using the proposed architecture reduces ownership costs by up to 51.2% on average and improves the power efficiency by up to 33% on average. In addition, the use of the proposed drone based telescope architecture enhances the angular resolution by 74.3% on average.

     

基于正态逆高斯模型的非下采样Contourlet变换图像去噪

提出一种基于正态逆高斯先验模型的非下采样Contourlet变换图像去噪算法.在非下采样Contourlet变换域中,以正态逆高斯模型为先验模型,对图像分解系数的稀疏分布统计建模,估计每个子带内的模型参数,在贝叶斯最大后验概率估计准则下推导出与正态逆高斯模型相应的阈值函数表达式,以此对图像进行去噪处理.对于被加性高斯白...     

一种改进的高斯逆威沙特概率假设密度扩展目标跟踪算法

假设扩展目标(ET)的扩展和量测数目分别为椭圆和泊松模型,高斯逆威沙特概率假设密度(GIW-PHD)能够估计扩展目标的运动和扩展状态。然而,该滤波器对空间邻近目标的数目、非椭圆目标和受到遮挡目标的扩展估计不够准确。针对这些问题,该文提出一种改进的GIW-PHD。首先,假设目标扩展为一个相同尺寸的参考椭圆,通过设计新的散射矩阵得到改进的随机矩阵(RM)方法。然后,将改进的RM方法与假设量测数目服从多伯努利分布的ET-PHD结合,得到改进的GIW-PHD滤波器。仿真和实验结果表明,与传统GIW-PHD相比,改进的GIW- PHD估计的目标数目和量测数目较多,扩展较大的椭圆和非椭圆目标的扩展更准确。     

非线性高斯系统边缘分布多目标贝叶斯滤波器

为解决存在数据关联不确定、检测不确定和杂波情况下的多目标跟踪问题,提出了一种新的多目标贝叶斯滤波器.代替维持多目标状态的联合后验密度,所提出的贝叶斯滤波器联合传递各个目标状态的边缘分布和它们的存在概率.为了处理目标运动和传感器测量模型中的非线性,利用无迹变换技术提出了一种非线性高斯条件下边缘分布贝叶斯滤波器的近似实现算法.仿真实验结果表明,与PHD(Probability Hypothesis Density)滤波器相比,所提出的滤波器具有更好的多目标跟踪能力.     

非对准高斯光束入射下的小孔衍射光强分布

点衍射干涉仪中小孔的对准情况直接决定小孔衍射光斑的形状及位置,也影响着后续光路的布置.基于瑞利-索末菲衍射理论,对非对准高斯光束入射下的小孔衍射光强分布进行了研究,给出了平移、离焦、倾斜三种对准误差下的光强分布解析表达式,分析得出了不同直径小孔在不同对准误差下的衍射光强分布情况.研究表明:平移对准误差会使衍射光斑形状发生变化,但对衍射光斑中心的位置没有影响,随着平移对准误差的增大,沿平移方向的第一暗环呈月牙状并逐渐消失;离焦对准误差对衍射光斑的位置和形状均无明显影响,但衍射光强值会随着离焦量的增加而减小;倾斜对准误差会使衍射光斑中心位置发生偏移,但衍射光斑的形状不会发生变化,并且偏移方向与斜入射方向一致,偏移量与倾斜角之间呈线性关系.     

通信产品系统可靠性预计和分配

本文主要介绍系统可靠性建模、可靠性分配和预计的一种思路，便于在今后的产品设计过程中加强可靠性系统设计。     

Estimates of the Wigner Distribution in Gaussian Noise Environment

The influence of Gaussian noise to the Wigner distribution is considered.Due to the quadratic nature of the Wigner distribution, the resulting noise exhibits impulse nature even in the case of Gaussian input noise. Estimators of the Wigner distribution which take into account this fact are considered.They can outperform the standard and the robust Wignerdistribution.     

Confidence Intervals for the Ratio of Two Poisson Means and Poisson Predictor Intervals

Easy-to-use charts are presented for confidence intervals for the ratio of two Poisson mean occurrence rates and for predictor intervals for the future value of a Poisson random variable, given a previously observed value. The use of the charts is illustrated and their theoretical basis is given.     

Spectral Estimation of a Narrow-Band Gaussian Process from the Distribution of the Distance Between Adjacent Zeros

An approximate expression for the probability density of the interzero distance for a narrow-band Gaussian process is given. Spectral estimation from this distribution is discussed. The first and second moment of the signal spectrum may be estimated, but little information of the detailed form of the spectrum is revealed.     

多个斯威林4型目标输出信号近似服从高斯分布研究

为了将对瑞利目标的检测与分辨方法应用于多个斯威林4型目标的检测与分辨,该文主要研究了多个斯威林4型目标存在时输出信号近似为高斯分布的条件。首先推导了多个斯威林4型目标存在时雷达接收机输出信号的概率分布;在此基础上,通过仿真获得了输出信号近似为高斯分布的条件,即多个目标中回波功率最大的两个目标的信噪比相差不大于7dB。     

Prediction of time series using wavelet Gaussian process for wireless sensor networks

Wireless Networks - The detection and transmission of a physical variable over time, by a node of a sensor network to its sink node, represents a significant communication overload and consequently...     

移动通信网无线信号场强预测的反演实现

本文提出了一种新的移动通信网无线信号场强预测技术，该技术基于消除快速衰落后得到的可靠与稳定的扫频测量数据，通过反演的途径实现中值场强预测。该技术既可以摆脱对地形地物数据库或三维数字地图的直接依赖，同时也可以得到满足移动网络优化实际需要的较高预测精度。     

基于高斯分布的自适应红外图像增强算法

针对红外图像信噪比和对比度低,结合红外图像直方图分布的特点,提出了一种基于高斯分布的自适应红外图像增强算法.该算法采用高斯分布函数平滑红外图像直方图中的主峰,以抑制红外图像背景和噪声的加强.算法中的高斯分布函数可根据原红外图像直方图的分布情况自适应产生,不需要人为设定,将所生成的高斯分布函数对原直方图进行转换后再进行直方图均衡处理,即可实现红外图像的增强.实验结果表明,该算法能有效地突显红外图像的目标,抑制其背景,具有较好的增强效果.     

The Distribution of Error Probability for Rayleigh Fading and Gaussian Noise

The distribution function of the probability of error in the presence of Rayleigh fading and Gaussian noise is determined for the basic binary modulation schemes of coherent frequencyshift keying (CFSK), noncoherent frequency-shift keying (NCFSK), differential phase-shift keying (DPSK), and coherent phase-shift keying (CPSK). General expressions for the distribution function of error probability are also derived when linear maximal-ratio diversity combining is employed. Results are given for various values of average error probability and various orders of diversity.