A Direct Derivation of the Exact Fisher Information Matrix for Bivariate Bessel Distribution of Type I

This paper deals with a direct derivation of Fisher’s information matrix for bivariate Bessel distribution of type I. Some tools for the numerical computation and some tabulations of the Fisher’s information matrix are provided.

Research on Industrial Relevance Degree and Industrial Financial Situation Risk Matrix Construction——Based on Chinese Information Technology Industry

Based on Input-Output Table in 2010 issued by National Bureau of Statistics of China, with the help of input-output model and with the calculation of indexes of industrial relevance degree in Chinese information technology industry, the paper reveals the industrial relevance in Chinese information technology industry. The paper also selects the relevant industries which are highly associated with the development of Chinese information technology industry based on industrial relevance degree to analyze the influences of these industries on the financial situation risk fluctuation in information technology industry and to design the matrix of financial situation risk in information technology industry. Then, the paper offers countermeasures and suggestions for the development of our information technology industry.

The matrix representation for the mathematic structure of Shannon’s information measures

Shannon’s information measure is a crucial concept in Information Theory. And the research, for the mathematics structure of Shannon’s information measure, is to recognize the essence of information measure. The linear relation between Shannon’s information measures and some signed measure space by using the formal symbols substitution rule is discussed. Furthermore, the coefficient matrix recurrent formula of the linear relation is obtained. Then the coefficient matrix is proved to be invertible via mathematical induction. This shows that the linear relation is one-to-one, and according to this, it can be concluded that a compact space can be generated from Shannon’s information measures.

Research on fault-tolerant control of networked control systems based on information scheduling

A kind of networked control system is studied; the networked control system with noise disturbance is modeled based on information scheduling and control co-design. Augmented state matrix analysis method is introduced, and robust fault-tolerant control problem of networked control systems with noise disturbance under actuator failures is studied. The parametric expression of the controller under actuator failures is given. Furthermore, the result is analyzed by simulation tests, which not only satisfies the networked control systems stability, but also decreases the data information number in network channel and makes full use of the network resources.

Evaluation Criteria Based on Mutual Information for Classifications Including Rejected Class

与用表演措施的常规评估标准不同，信息理论基于在场的标准在机器学习的应用的一个唯一的有益的特征。然而，我们仍然远非正在拥有熵类型标准的深入的理解，说，在与常规基于表演的标准的关系。这份报纸学习通用分类问题，它包括一拒绝，或未知，班。我们在场基本公式和分类基于信息学习的图解的图理论。一个靠近形式的方程为通用分类问题在规范的相互的信息和扩充混乱矩阵之间被导出。敏感方程的三个定理和定理集合为学习在相互的信息和常规表演索引之间的关系被给。我们也与常规标准比较举与相互的信息标准的优点和限制有关的数字例子和几讨论。

OPERATOR-VALUED FREE FISHER INFORMATION OF RANDOM MATRICES

The free Fisher information of an operator random matrix is studied. When the covariance of a random matrix is a conditional expectation, the free Fisher information of such a matrix is the double of this conditional expectation’s Watatani index.

Novel Fault Detection Optimization Algorithm for Single Event Effect system Based on Multi-information Entropy Fusion

Fault detection caused by single event effect( SEE) in system was studied,and an improved fault detection algorithm by fusing multi-information entropy for detecting soft error was proposed based on multi-objective detection approach and classification management method. In the improved fault detection algorithm, the analysis model of posteriori information with corresponding multi-fault alternative detection points was formulated through correlation information matrix, and the maximum incremental information entropy was chosen as the classification principle for the optimal detection points. A system design example was given to prove the rationality and feasibility of this algorithm.This fault detection algorithm can achieve the purpose of fault detection and resource configuration with high efficiency.

Reduction of Systematic Error in Radiopharmaceutical Activity by Entropy Based Mutual Information

The quality of the radiation dose depends upon the gamma count rate of the radionuclide used. Any reduction in error in the count rate is reflected in the reduction in error in the activity and consequently on the quality of dose. All the efforts so far have been directed only to minimize the random errors in count rate by repetition. In the absence of probability distribution for the systematic errors, we propose to minimize these errors by estimating the upper and lower limits by the technique of determinant in equalities developed by us. Using the algorithm we have developed based on the tech- nique of determinant inequalities and the concept of maximization of mutual information (MI), we show how to process element by element of the covariance matrix to minimize the correlated systematic errors in the count rate of 113 mIn. The element wise processing of covariance matrix is so unique by our technique that it gives experimentalists enough maneuverability to mitigate different factors causing systematic errors in the count rate and consequently the activity of 113 mIn.

Tree-based ecosystem services supply and multifunctionality of church forests and their agricultural matrix near Lake Tana,Ethiopia

Ecosystem services(ES)are the connection between nature and society,and are essential for the well-being of local communities that depend on them.In Ethiopia,church forests and the surrounding agricultural matrix supply numerous ES.However,the ES delivered by both land use types have not yet been assessed simultaneously.Here we surveyed both church forests and their agricultural matrices,aiming to quantify,compare and unravel the drivers underlying tree-based ES supply,density and multifunctionality.We found that almost all church forests and half of the agricultural matrices provided high ES densities.ES multifunctionality was higher in the agricultural matrices,suggesting that people deliberately conserve or plant multifunctional tree species.Furthermore,the supply of all categories of ES was positively correlated with church forest age(p-value<0.001)in the agricultural matrix,while the extent of church forest was positively correlated with the density of all categories ecosystem services score in the church forests(p-value<0.001).Our results can be used to prioritize conservation efforts at sites that provide high levels of ES supply,ES density and ES multifunctionality,and to prioritize restoration efforts at sites with low levels thereof.

基于FAHP的高职院校教师信息化教学能力综合评价

参考教育部教师工作司“中国高校教师专业发展调研”项目研究成果,从高职教师信息化教学能力应有的内涵出发,建立分析框架,确定相关评价指标的权重;构建模糊系统,采用FAHP分析方法,提出了一套高职教师信息化教学能力综合评价方法,以期为高职院校教师及教学管理人员的信息化能力提升提供参考。

加权信息量支持下融合InSAR形变特征的滑坡易发性评价

使用SBAS-InSAR处理六盘水市水城区2018-07~2019-08共69景Sentinel-1A卫星影像,获取地表形变作为动态评价因子,用于完善传统滑坡易发性评价研究缺乏动态特征数据应用的问题。结果表明,使用10种静态评价因子融合InSAR形变特征数据作为动态评价因子,在耦合层次分析法与信息量法的加权信息量模型下对比仅使用静态特征数据,ROC曲线下面积分别为0.756 02和0.888 68,模型性能提升约13.3%;再将历史灾害点叠加于2种分区图下检验分区精度,相比于未融入形变特征,融入形变特征可纠正约12.44%的误分类区域,能较好地提升分区的可靠性。

模态测试不确定性影响因素分析及传感器布置应用

模态测试结果的准确性会受测试数据采集、数据处理、建模假设和参数估计等不确定性因素的影响.为研究模态测试中模态参数的不确定性水平及不同影响因素对其的影响规律,本文采用状态空间模型和费希尔信息矩阵的快速模态参数不确定性分析方法,探讨包括振动信号的采样时长、采样频率、采样信噪比和结构的阻尼比等多种因素对模态参数不确定性水平的影响,同时提出利用模态参数不确定性水平来优化传感器布置策略的实用性建议.结果表明:模态参数的不确定性水平随采样时长、采样频率、信噪比和传感器数量的增加而降低,随结构阻尼比的增大而升高;对于均匀分布结构,多数传感器布置在结构顶部和中上部,少数布置在中下部时,模态参数的整体不确定性水平较低,是一种相对较优的传感器布置方案.

期权隐含尾部风险信息的系统性风险预警功能研究

系统性风险预警是防范化解系统性风险的重要举措。期权市场隐含着大量有价值且具前瞻性的信息。本文从上证50ETF期权价格中提取隐含尾部风险信息,检验期权隐含尾部风险信息的系统性风险预警功能。实证结果表明,期权隐含尾部风险信息对我国系统性风险具有显著的预测能力,在控制其他风险预警指标后,结果仍然显著。期权隐含尾部风险信息对不同部门系统性风险的预测能力存在差异,对股票市场风险和债券市场的预测效果最好。将期权隐含尾部风险信息加入传统风险预警指标体系后,能够大幅提升预警指标的预警效果,降低噪声信号比。

基于矩阵信息几何样本筛选下局域联合处理的低空风切变风速估计方法

针对非均匀杂波环境下,机载气象雷达低空风切变风速估计不准确的问题,本文提出了一种基于矩阵信息几何样本筛选下局域联合处理(Joint Domain Localized,JDL)的低空风切变风速估计方法。该方法首先提取雷达回波信号的特征信息建模为矩阵流形,然后通过选取几何度量方式估计几何均值矩阵,利用广义内积法(Generalized Inner Product,GIP)计算几何均值矩阵与各样本间相似度,并从训练样本中筛选样本相似度较高的训练样本估计待检测单元的杂波协方差矩阵,最后利用JDL方法构造降维变换矩阵,对杂波协方差矩阵进行降维处理,并构造降维处理器对非均匀杂波进行抑制,从而实现低空风切变风速估计。

基于快速评价方法的土地利用变化分析

为构建快速评价方法,及时掌握区域土地利用变化动态,促进土地资源的科学合理利用,推进自然资源可持续发展,利用影像自动分割技术,对2010年、2020年两期遥感数据进行地类信息采集,利用ArcGIS模型构建技术,采用土地利用动态变化度、地学信息图谱及土地利用转移矩阵等方法对研究区土地利用情况进行综合分析。结果显示,2010—2020年研究区林地面积增加244.81 hm~2,住宅用地面积增加69.68 hm~2,水域及水利设施用地面积增加33.60 hm~2;耕地和草地面积分别减少262.81 hm~2、30.71 hm~2,其他地类面积变化不大。从土地利用动态变化度来看,公共管理与公共服务用地增幅显著,达到24.62%。从地学信息图谱及土地利用转移矩阵来看,林地增加来源地类主要为耕地、园地及草地,整个研究区域均有分布,主要受到退耕还林政策及在影像分割和目视解译过程中的林下耕地影响。通过一系列研究较快地摸清了土地利用数量、布局及各地类之间相互转化的剧烈程度,可为土地利用可持续发展及相关部门开展研究提供决策依据。

基于CNN-Transformer模型的自动扶梯轴承故障诊断方法研究

针对自动扶梯滚动轴承故障诊断模型诊断识别率不高的问题,提出一种CNN与Transformer相结合的滚动轴承故障诊断方法。该方法采用CNN注意力和Transformer时域注意力融合机制,从信号的通道和时域两个维度提取最有利于识别的特征信息,降低信道和噪声等影响。根据特征信息的重要程度进行权重分配,以提升故障识别率。基于滚动轴承数据集,将所提算法模型和CNN、RNN、SVM算法进行对比。结果表明,该方法识别轴承故障的准确度更高,实现了对轴承故障的准确分类。

基于稳健距离的大数据Logistic回归最优子抽样

大数据统计分析在有限的计算资源下面临一些挑战性问题,用子数据代替全数据进行统计分析成为一种选择。文章基于最小协方差行列式的稳健距离,为大数据Logistic回归模型提出了一种更高效的子数据选择算法。通过大量的数值模拟,在不同的标准下比较了所提算法与其他已有算法的性能。结果表明,所提算法具有较高的估计效率和计算效率,与全数据相比,计算时间显著减少。与其他算法相比,所提算法得到的子数据信息矩阵行列式的值更大。同时,当协变量之间存在高度相关性时,所提算法具有稳健性。最后,通过对实际数据集的分析,说明了所提算法的预测误差更小。

基于梯度选择的轻量化差分隐私保护联邦学习

为了应对机器学习过程中可能出现的用户隐私问题,联邦学习作为首个无需用户上传真实数据、仅上传模型更新的协作式在线学习解决方案,已经受到人们的广泛关注与研究。然而,它要求用户在本地训练且上传的模型更新中仍可能包含敏感信息,从而带来了新的隐私保护问题。与此同时,必须在用户本地进行完整训练的特点也使得联邦学习过程中的运算与通信开销问题成为一项挑战,亟需人们建立一种轻量化的联邦学习架构体系。出于进一步的隐私需求考虑,文中使用了带有差分隐私机制的联邦学习框架。另外,首次提出了基于Fisher信息矩阵的Dropout机制——FisherDropout,用于对联邦学习过程中在客户端训练产生梯度更新的每个维度进行优化选择,从而极大地节约运算成本、通信成本以及隐私预算,建立了一种兼具隐私性与轻量化优势的联邦学习框架。在真实世界数据集上的大量实验验证了该方案的有效性。实验结果表明,相比其他联邦学习框架,FisherDropout机制在最好的情况下可以节约76.8%~83.6%的通信开销以及23.0%~26.2%的运算开销,在差分隐私保护中隐私性与可用性的均衡方面同样具有突出优势。

损耗SU(2)和SU(1,1)干涉仪中灵敏度过高估计的研究

基于损耗SU(2)和SU(1,1)干涉仪模型,以干涉仪中的相位估值的为研究方向,在理论上研究了与双参量相位估值相比,进行单参量相位估值的时候存在的高估量子Fisher信息(quantum Fisher information,QFI)的一般表达式;以相干态和压缩真空态输入为例,数值分析了高估QFI随损耗系数或分束比的变化,发现这时出现的高估QFI的消失和恢复现象是和分束比,增益因子以及压缩振幅具有一定的关系.通过调整分束比和损耗系数,可获得最佳的灵敏度,有利于在有损环境下进行量子精密测量.

基于先验信息的压缩感知重建温度场技术

针对利用压缩感知方法重建微处理器芯片温度场存在错失真实热点、从而影响重建精度的问题,提出了一种基于先验信息的压缩感知重建温度场方法。通过对温度场先验信息的处理,结合主成分分析和模拟退火算法有针对性地设计观测矩阵,优化温度传感器的布置,提高重建精度。实验结果表明:与基于特征图的重建方法、基于模拟退火算法布置传感器的方法和基于随机采样的压缩感知重建温度场方法相比,该方法在平均温度误差、最大温度误差和均方误差方面至少分别提升了29.9%、46.6%和53.7%,有更优越的温度场重建性能。