In this paper, a novel algorithm is presented for direction of arrival（DOA） estimation and array self-calibration in the presence of unknown mutual coupling. In order to highlight the relationship between the array ...In this paper, a novel algorithm is presented for direction of arrival（DOA） estimation and array self-calibration in the presence of unknown mutual coupling. In order to highlight the relationship between the array output and mutual coupling coefficients, we present a novel model of the array output with the unknown mutual coupling coefficients. Based on this model, we use the space alternating generalized expectation-maximization（SAGE） algorithm to jointly estimate the DOA parameters and the mutual coupling coefficients. Unlike many existing counterparts, our method requires neither calibration sources nor initial calibration information. At the same time,our proposed method inherits the characteristics of good convergence and high estimation precision of the SAGE algorithm. By numerical experiments we demonstrate that our proposed method outperforms the existing method for DOA estimation and mutual coupling calibration.展开更多
Cyber losses in terms of number of records breached under cyber incidents commonly feature a significant portion of zeros, specific characteristics of mid-range losses and large losses, which make it hard to model the...Cyber losses in terms of number of records breached under cyber incidents commonly feature a significant portion of zeros, specific characteristics of mid-range losses and large losses, which make it hard to model the whole range of the losses using a standard loss distribution. We tackle this modeling problem by proposing a three-component spliced regression model that can simultaneously model zeros, moderate and large losses and consider heterogeneous effects in mixture components. To apply our proposed model to Privacy Right Clearinghouse (PRC) data breach chronology, we segment geographical groups using unsupervised cluster analysis, and utilize a covariate-dependent probability to model zero losses, finite mixture distributions for moderate body and an extreme value distribution for large losses capturing the heavy-tailed nature of the loss data. Parameters and coefficients are estimated using the Expectation-Maximization (EM) algorithm. Combining with our frequency model (generalized linear mixed model) for data breaches, aggregate loss distributions are investigated and applications on cyber insurance pricing and risk management are discussed.展开更多
粒子滤波器能够给出移动机器人全局定位非线性非高斯模型的近似解.然而,当新感知出现在先验概率的尾部或者与先验相比感知概率太尖时,传统的粒子滤波器会退化导致定位失败.本文提出了一种重要性采样跟中心差分滤波器(cen tra l d iffere...粒子滤波器能够给出移动机器人全局定位非线性非高斯模型的近似解.然而,当新感知出现在先验概率的尾部或者与先验相比感知概率太尖时,传统的粒子滤波器会退化导致定位失败.本文提出了一种重要性采样跟中心差分滤波器(cen tra l d ifference filter,CDF)相结合的新算法,并对测量更新步的加权粒子集应用基于KD-树的加权期望最大(w e igh ted expecta tion m ax im iza tion,W EM)自适应聚类算法获得表示机器人位姿状态后验密度的高斯混合模型(G au ssian m ixtu re m od e l,GMM).实验结果表明,新方法提高了定位准确率,降低了计算复杂度.展开更多
In this paper, we give the expression of the least square solution of the linear quaternion matrix equation AXB = C subject to a consistent system of quaternion matrix equations D1X = F1, XE2 =F2, and derive the maxim...In this paper, we give the expression of the least square solution of the linear quaternion matrix equation AXB = C subject to a consistent system of quaternion matrix equations D1X = F1, XE2 =F2, and derive the maximal and minimal ranks and the leastnorm of the above mentioned solution. The finding of this paper extends some known results in the literature.展开更多
Prediction of protein functions from known genomic sequences is an important mission of bioinformatics. One approach is to classify proteins into functional catego- ries. We have therefore developed a method based on ...Prediction of protein functions from known genomic sequences is an important mission of bioinformatics. One approach is to classify proteins into functional catego- ries. We have therefore developed a method based on protein domain composition and the maximum likelihood estimation (MLE) algorithm to classify proteins according to functions. Using the Saccharomyces cerevisiae genome, we compared the effectiveness of the MLE approach with that of an intui- tive and simple method. The MLE method outperformed the simple method, achieving an estimated specificity of 75.45% and an estimated sensitivity of 40.26%. These results indicate that domain is an important feature of proteins and is closely related to protein function.展开更多
基金supported by the National Natural Science Foundation of China (No. 61302141)
文摘In this paper, a novel algorithm is presented for direction of arrival（DOA） estimation and array self-calibration in the presence of unknown mutual coupling. In order to highlight the relationship between the array output and mutual coupling coefficients, we present a novel model of the array output with the unknown mutual coupling coefficients. Based on this model, we use the space alternating generalized expectation-maximization（SAGE） algorithm to jointly estimate the DOA parameters and the mutual coupling coefficients. Unlike many existing counterparts, our method requires neither calibration sources nor initial calibration information. At the same time,our proposed method inherits the characteristics of good convergence and high estimation precision of the SAGE algorithm. By numerical experiments we demonstrate that our proposed method outperforms the existing method for DOA estimation and mutual coupling calibration.
文摘Cyber losses in terms of number of records breached under cyber incidents commonly feature a significant portion of zeros, specific characteristics of mid-range losses and large losses, which make it hard to model the whole range of the losses using a standard loss distribution. We tackle this modeling problem by proposing a three-component spliced regression model that can simultaneously model zeros, moderate and large losses and consider heterogeneous effects in mixture components. To apply our proposed model to Privacy Right Clearinghouse (PRC) data breach chronology, we segment geographical groups using unsupervised cluster analysis, and utilize a covariate-dependent probability to model zero losses, finite mixture distributions for moderate body and an extreme value distribution for large losses capturing the heavy-tailed nature of the loss data. Parameters and coefficients are estimated using the Expectation-Maximization (EM) algorithm. Combining with our frequency model (generalized linear mixed model) for data breaches, aggregate loss distributions are investigated and applications on cyber insurance pricing and risk management are discussed.
文摘粒子滤波器能够给出移动机器人全局定位非线性非高斯模型的近似解.然而,当新感知出现在先验概率的尾部或者与先验相比感知概率太尖时,传统的粒子滤波器会退化导致定位失败.本文提出了一种重要性采样跟中心差分滤波器(cen tra l d ifference filter,CDF)相结合的新算法,并对测量更新步的加权粒子集应用基于KD-树的加权期望最大(w e igh ted expecta tion m ax im iza tion,W EM)自适应聚类算法获得表示机器人位姿状态后验密度的高斯混合模型(G au ssian m ixtu re m od e l,GMM).实验结果表明,新方法提高了定位准确率,降低了计算复杂度.
文摘In this paper, we give the expression of the least square solution of the linear quaternion matrix equation AXB = C subject to a consistent system of quaternion matrix equations D1X = F1, XE2 =F2, and derive the maximal and minimal ranks and the leastnorm of the above mentioned solution. The finding of this paper extends some known results in the literature.
文摘Prediction of protein functions from known genomic sequences is an important mission of bioinformatics. One approach is to classify proteins into functional catego- ries. We have therefore developed a method based on protein domain composition and the maximum likelihood estimation (MLE) algorithm to classify proteins according to functions. Using the Saccharomyces cerevisiae genome, we compared the effectiveness of the MLE approach with that of an intui- tive and simple method. The MLE method outperformed the simple method, achieving an estimated specificity of 75.45% and an estimated sensitivity of 40.26%. These results indicate that domain is an important feature of proteins and is closely related to protein function.
