Estimation of scale parameter under a symmetric loss function 一種對稱損失函數(shù)下刻度參數(shù)的最優(yōu)同變估計
Estimation of scale parameter of the normal distribution under a symmetric loss function 一種對稱損失函數(shù)下正態(tài)總體刻度參數(shù)的估計
Estimation of scale parameter of normal distribution under q - symmetric entropy loss function 對稱熵損失函數(shù)下正態(tài)總體刻度參數(shù)的估計
Confidence interval for scale parameter of normal distribution from incomplete observational data 正態(tài)分布尺度參數(shù)基于殘缺觀測數(shù)據(jù)的置信區(qū)間
Minimax estimation in scale parameter families as the parameter interval being bounded under squared loss function 平方損失下區(qū)間有界的尺度函數(shù)極小極大估計
Entropy is applied to find the proper wavelet scale parameter , with which the analysis results are more precise than with other parameters 本文首次把“信息熵”引如電壓暫降的檢測工作中,用于尋找最優(yōu)的小波尺度,使檢測結(jié)果更加準確。
Based on the laplacian distribution model of dct coefficients , we deduce a theoretical relationship between the scaling parameter in some typical watermarking algorithms and the degradation of watermarked images 研究了圖象信息隱藏技術中普遍關注的幾個典型性能的定量評估方法,得到了相應的隱藏算法參數(shù)調(diào)節(jié)策略和攻擊規(guī)避準測。
We proposed an improved simulated annealing algorithm with neighbor function based on self - optimization of scale parameter . furthermore incorporating disaster - modification and the improved annealing into genetic algorithm , an improved genetic - annealing algorithm is proposed . in order to solve the deceptive minimum problem , an improved evolutionary strategy combined with similarity detection and improved mutation operator 提出了鄰域尺度函數(shù)自尋優(yōu)的模擬褪火算法,結(jié)合遺傳算法,引入災變算子,提出了改進遺傳模擬褪火算法;為了解決尋優(yōu)過程中的最小欺騙問題,我們提出了相似性檢測,結(jié)合改進的適應值無關變異算子,提出了基于相似性檢測和適應值無關變異算子的進化策略算法。
We find that fitness of returns on stocks to non - normal stable distributions in china stock market is very good by fitness test ; study measurements of return and risk of a portfolio conditional on non - normal stable distributions and put forward mean - scale parameter model ; find that mean - scale parameter model can explain asset allocation puzzle by empirical analysis 通過擬合優(yōu)度檢驗發(fā)現(xiàn)我國的股票收益率與非正態(tài)穩(wěn)定分布的擬合效果非常好;研究了非正態(tài)穩(wěn)定分布條件下投資組合收益和風險的度量,建立了均值尺度參數(shù)投資組合模型;通過實證分析發(fā)現(xiàn)均值尺度參數(shù)模型能夠解釋資產(chǎn)配置之謎。
( 2 ) in the study of multivariate phenomena , each time variable should possess its own scaling parameter in order to allow maximal flexibility in time - frequency . the notion of multifrequency multifunction wavelets , to be introduced , is based on this point of view . multifrequency wavelets , via directional multiresolution analysis , generated by a single function is extended to multifrequency multifunction wavelets generated by a finite number of functions ( 2 )在研究多變量問題時,為了使時頻分析具有最大的靈活性,要求每個時間變量都有它自己的尺度參數(shù),鑒于此,本文從尺度函數(shù)構(gòu)成正交基或riesz基出發(fā),把一維多函數(shù)小波推廣到二維多頻率多函數(shù)小波,解決了構(gòu)造正交或雙正交多頻率多函數(shù)小波所需要的理論依據(jù)。