By applying generalized gaussian distribution to statistically model the alternating current coefficient of discrete cosine transform , the technology of the blind image watermark is studied and the performance of the new detector is analyzed 摘要根据数字图像离散余弦变换域交流系数的广义高斯分布模型,对盲图像水印技术进行研究,并给出了水印检测器检测性能的理论分析结果。
The article analyses whether the theory of emh market can explain some phenomena on capital market . we provide some evidence for the non - normal , non - gaussian distribution , auto - correlation , non - linear and heteroskedasticity character of stock price 文章就有效市场假说( emh )对现实资本市场的解释能力进行了分析,发现我国股票市场的股价收益率序列具有非正态性、自相关性、非线性、异方差性等特点。
The transient process of imm is analyzed via monte carlo simulation . simulation results shows that the residual of each filter in imm is still gaussian distribution , but its mean is not zero if the dominating filter cannot match the real target model . 2 仿真结果表明, imm中各子滤波器滤波残差基本服从正态分布,但其均值随滤波模型与系统实际运动模式匹配程度变化而变化,即二者匹配时,滤波结果无偏;不匹配时,滤波结果有偏。
Based on unsupervised learning , sparse coding is suitable to describe images with non - gaussian distribution and can get rid of the high order redundancy among the image pixels . since the basis function of sparse coding has build - in clustering property , it increases the inter - class variations of the features 稀疏编码是一种基于非监督学习的算法,它适合描述具有非高斯分布的数据对象,能够有效地消除图像象素点之间的冗余,并具有内在的聚类特性。
Non - gaussian distribution and noniinear , auto - - correlation and heteroskedasticity character of stock price and return rates , presented that main factors leads to the failure of emh on chinese stock market is emotionai action , information - - based herding , over - - reaction and under - reaction to information of investors and noniinear , non - equiiibriurn propefty of stock market 提出有效市场理论失灵的主要原因是投资者的非理性行为,信息反映的羊群效应,投资者存在反应过度和反应不足现象,股票市场的非均衡特征和股票市场的非线性特征。
Based on the study of strength degradation of material in the fatigue process , a strength degradation model is proposed . a stochastic differential equation , which controls strength degradation , is obtained from the model randomized by markov process . by using the theory of stochastic , the distributions of residual strength at any given lifetime and lifetime of any given residual strength are attained . under a few suitable hypotheses , inverse gaussian distribution of fatigue life is derived , and verified by means of experimental data . the result shows that the model and the method are reasonable 在研究疲劳过程中材料强度退化规律的基础上,建立了一个强度退化模型.对其进行随机化处理,得到控制强度退化过程的随机微分方程.在一定假设条件下,获得了剩余强度概率密度函数的封闭解,并推导出疲劳寿命的反高斯分布形式.给出一种考虑损伤状态对随机涨落影响的近似处理方法.与试验数据的比较结果表明,本文的模型和方法是合理的
Then compound - gaussian distribution model is been introduced and the three adaptive algorithms been derived from the model . by using simulation data and ipix radar sea clutter data that is been added target signals the performances of the detection algorithms are been simulated and analyzed . the same conclusion and the adaptive algorithms " effectiveness are been shown 接着介绍了复合高斯分布模型,在此模型基础上推导得到了三种自适应检测算法,通过使用仿真数据和ipix雷达实测海杂波数据加入目标信号对三种算法检测性能进行了仿真分析和比较,得到了相一致的结果,证明该算法的有效性。
Firstly , according to the characteristic that the doppler frequency shift signal can be approximated as a single sinusoid signal , the extended sinusoid signal retrieval ( pisarenko and esprit ) methods are presented and signal state and measurement formulations are developed , so the kalman filter recursive method is got . the brief introduction of low velocity moving target doppler frequency shift signal wigner - ville transformation and wavelet transformation expression are presented in this paper . secondly , because the clutter is gaussian distribution , cumement and high - order spectrum based methods are presented and the simulation results prove their good performance to suppress gaussian clutter in low velocity moving target doppler frequency shift signal processing 一个方面是根据低速目标的多普勒信号可简化为单一正弦波形式这一特点,得到了扩展的高斯色噪声背景下的谐波恢复算法,即高斯色噪声中的pisarenko谐波恢复法和旋转因子不变法( esprit ) ;并推导了信号的状态方程和观测方程,进而得到基于卡尔曼滤波的递推算法对信号进行提取;本文还简单的介绍了低速运动目标的多普勒频移信号的wigner - ville变换与小波变换;另一个方面是针对杂波服从高斯分布这一特点,提出了对接收信号求累积量和高阶谱来对高斯杂波进行抑制。
Based on survey data from some researches , dead load model and vehicle load model are presented in this paper . it is quite evidence that dead load model is gaussian distribution , and vehicle load is non - gaussian distribution , which operates general traffic and rush hour traffic states 本文在国内外各种调查资料的基础上,分别引入恒荷载模型及车辆荷载模型,其中恒荷载呈正态分布:车辆荷载则为非正态分布,并将其分为一般运行状态及密集运行状态两种情况,分别建立服役期最大值分布函数。
Abstract : based on the study of strength degradation of material in the fatigue process , a strength degradation model is proposed . a stochastic differential equation , which controls strength degradation , is obtained from the model randomized by markov process . by using the theory of stochastic , the distributions of residual strength at any given lifetime and lifetime of any given residual strength are attained . under a few suitable hypotheses , inverse gaussian distribution of fatigue life is derived , and verified by means of experimental data . the result shows that the model and the method are reasonable 文摘:在研究疲劳过程中材料强度退化规律的基础上,建立了一个强度退化模型.对其进行随机化处理,得到控制强度退化过程的随机微分方程.在一定假设条件下,获得了剩余强度概率密度函数的封闭解,并推导出疲劳寿命的反高斯分布形式.给出一种考虑损伤状态对随机涨落影响的近似处理方法.与试验数据的比较结果表明,本文的模型和方法是合理的