Optimal Estimation of High-Dimensional Covariance Matrices with Missing and Noisy Data

The estimation of covariance matrices is very important in many fields, such as statistics. In real applications, data are frequently influenced by high dimensions and noise. However, most relevant studies are based on complete data. This paper studies the optimal estimation of high-dimensional covariance matrices based on missing and noisy sample under the norm. First, the model with sub-Gaussian additive noise is presented. The generalized sample covariance is then modified to define a hard thresholding estimator , and the minimax upper bound is derived. After that, the minimax lower bound is derived, and it is concluded that the estimator presented in this article is rate-optimal. Finally, numerical simulation analysis is performed. The result shows that for missing samples with sub-Gaussian noise, if the true covariance matrix is sparse, the hard thresholding estimator outperforms the traditional estimate method.

Evaluating the Vulnerability of Integrated Electricity-heat-gas Systems Based on the High-dimensional Random Matrix Theory

Faced with the tight coupling of multi energy sources,the interaction between different energy supply systems makes it difficult for integrated energy systems(IES)to identify weak nodes.Based on the analysis of the data generated by the actual operation of IES,this paper proposes a weak node identification method based on random matrix theory(RMT).First,establish a unified power flow model for IES.Secondly.introduce RMT and the characteristics of weak nodes,without considering the detailed physical model of the system,using historical data and real-time data to construct the random matrix.Thirdly,the two limit spectrum distribution functions(Marchenko-Pastur law and ring law)are used to qualitatively analyze the system’s operating status,calculate linear eigenvalue statistics such as mean spectral radius(MSR),and establish the weak node identification model based on entropy theory.Finally,the simulation of IES verifies the effectiveness of the proposed method and provides a new approach for the identification of weak nodes in IES.

Randomized Latent Factor Model for High-dimensional and Sparse Matrices from Industrial Applications

Latent factor(LF) models are highly effective in extracting useful knowledge from High-Dimensional and Sparse(HiDS) matrices which are commonly seen in various industrial applications. An LF model usually adopts iterative optimizers,which may consume many iterations to achieve a local optima,resulting in considerable time cost. Hence, determining how to accelerate the training process for LF models has become a significant issue. To address this, this work proposes a randomized latent factor(RLF) model. It incorporates the principle of randomized learning techniques from neural networks into the LF analysis of HiDS matrices, thereby greatly alleviating computational burden. It also extends a standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix correctly.Experimental results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models, RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data.I provides an important alternative approach to LF analysis of HiDS matrices, which is especially desired for industrial applications demanding highly efficient models.

Random Subspace Learning Approach to High-Dimensional Outliers Detection

We introduce and develop a novel approach to outlier detection based on adaptation of random subspace learning. Our proposed method handles both high-dimension low-sample size and traditional low-dimensional high-sample size datasets. Essentially, we avoid the computational bottleneck of techniques like Minimum Covariance Determinant (MCD) by computing the needed determinants and associated measures in much lower dimensional subspaces. Both theoretical and computational development of our approach reveal that it is computationally more efficient than the regularized methods in high-dimensional low-sample size, and often competes favorably with existing methods as far as the percentage of correct outlier detection are concerned.

Robust Latent Factor Analysis for Precise Representation of High-Dimensional and Sparse Data

High-dimensional and sparse(HiDS)matrices commonly arise in various industrial applications,e.g.,recommender systems(RSs),social networks,and wireless sensor networks.Since they contain rich information,how to accurately represent them is of great significance.A latent factor(LF)model is one of the most popular and successful ways to address this issue.Current LF models mostly adopt L2-norm-oriented Loss to represent an HiDS matrix,i.e.,they sum the errors between observed data and predicted ones with L2-norm.Yet L2-norm is sensitive to outlier data.Unfortunately,outlier data usually exist in such matrices.For example,an HiDS matrix from RSs commonly contains many outlier ratings due to some heedless/malicious users.To address this issue,this work proposes a smooth L1-norm-oriented latent factor(SL-LF)model.Its main idea is to adopt smooth L1-norm rather than L2-norm to form its Loss,making it have both strong robustness and high accuracy in predicting the missing data of an HiDS matrix.Experimental results on eight HiDS matrices generated by industrial applications verify that the proposed SL-LF model not only is robust to the outlier data but also has significantly higher prediction accuracy than state-of-the-art models when they are used to predict the missing data of HiDS matrices.

Accelerated Matrix Recovery via Random Projection Based on Inexact Augmented Lagrange Multiplier Method

In this paper, a unified matrix recovery model was proposed for diverse corrupted matrices. Resulting from the separable structure of the proposed model, the convex optimization problem can be solved efficiently by adopting an inexact augmented Lagrange multiplier (IALM) method. Additionally, a random projection accelerated technique (IALM+RP) was adopted to improve the success rate. From the preliminary numerical comparisons, it was indicated that for the standard robust principal component analysis (PCA) problem, IALM+RP was at least two to six times faster than IALM with an insignificant reduction in accuracy; and for the outlier pursuit (OP) problem, IALM+RP was at least 6.9 times faster, even up to 8.3 times faster when the size of matrix was 2 000×2 000.

MATRIX ALGEBRA ALGORITHM OF STRUCTURE RANDOM RESPONSE NUMERICAL CHARACTERISTICS

A new algorithm of structure random response numerical characteristics, namedas matrix algebra algorithm of structure analysis is presented. Using the algorithm, structurerandom response numerical characteristics can easily be got by directly solving linear matrixequations rather than structure motion differential equations. Moreover, in order to solve thecorresponding linear matrix equations, the numerical integration fast algorithm is presented. Thenaccording to the results, dynamic design and life-span estimation can be done. Besides, the newalgorithm can solve non-proportion damp structure response.

COOPERATIVE MIMO SPECTRUM SENSING BASED ON RANDOM MATRIX THEORY

Random Matrix Theory (RMT) is a valuable tool for describing the asymptotic behavior of multiple systems,especially for large matrices. In this paper,using asymptotic random matrix theory,a new cooperative Multiple-Input Multiple-Output (MIMO) scheme for spectrum sensing is proposed,which shows how asymptotic free property of random matrices and the property of Wishart distribution can be used to assist spectrum sensing for Cognitive Radios (CRs). Simulations over Rayleigh fading and AWGN channels demonstrate the proposed scheme has better detection performance compared with the energy detection techniques even in the case of a small sample of observations.

RUAP:Random Rearrangement Block Matrix-Based Ultra-Lightweight RFID Authentication Protocol for End-Edge-Cloud Collaborative Environment

Cloud computing provides powerful processing capabilities for large-scale intelligent Internet of things(IoT)terminals.However,the massive realtime data processing requirements challenge the existing cloud computing model.The edge server is closer to the data source.The end-edge-cloud collaboration offloads the cloud computing tasks to the edge environment,which solves the shortcomings of the cloud in resource storage,computing performance,and energy consumption.IoT terminals and sensors have caused security and privacy challenges due to resource constraints and exponential growth.As the key technology of IoT,Radio-Frequency Identification(RFID)authentication protocol tremendously strengthens privacy protection and improves IoT security.However,it inevitably increases system overhead while improving security,which is a major blow to low-cost RFID tags.The existing RFID authentication protocols are difficult to balance overhead and security.This paper designs an ultra-lightweight encryption function and proposes an RFID authentication scheme based on this function for the end-edge-cloud collaborative environment.The BAN logic proof and protocol verification tools AVISPA formally verify the protocol’s security.We use VIVADO to implement the encryption function and tag’s overhead on the FPGA platform.Performance evaluation indicates that the proposed protocol balances low computing costs and high-security requirements.

Cross Correlation of Intra-day Stock Prices in Comparison to Random Matrix Theory

We propose and apply a new algorithm of principal component analysis which is suitable for a large sized, highly random time series data, such as a set of stock prices in a stock market. This algorithm utilizes the fact that the major part of the time series is random, and compare the eigenvalue spectrum of cross correlation matrix of a large set of random time series, to the spectrum derived by the random matrix theory (RMT) at the limit of large dimension (the number of independent time series) and long enough length of time series. We test this algorithm on the real tick data of American stocks at different years between 1994 and 2002 and show that the extracted principal components indeed reflects the change of leading stock sectors during this period.

Compressive Wideband Spectrum Sensing Based on Random Matrix Theory

Spectrum sensing in a wideband regime for cognitive radio network(CRN) faces considerably technical challenge due to the constraints on analog-to-digital converters(ADCs).To solve this problem,an eigenvalue-based compressive wideband spectrum sensing(ECWSS) scheme using random matrix theory(RMT) was proposed in this paper.The ECWSS directly utilized the compressive measurements based on compressive sampling(CS) theory to perform wideband spectrum sensing without requiring signal recovery,which could greatly reduce computational complexity and data acquisition burden.In the ECWSS,to alleviate the communication overhead of secondary user(SU),the sensors around SU carried out compressive sampling at the sub-Nyquist rate instead of SU.Furthermore,the exact probability density function of extreme eigenvalues was used to set the threshold.Theoretical analyses and simulation results show that compared with the existing eigenvalue-based sensing schemes,the ECWSS has much lower computational complexity and cost with no significant detection performance degradation.

Verification of the Validity of the NPT Treatment in Hereditary Spastic Paraplegia: An Investigation Performed by Application of Random Matrix Theory

We have applied the Random Matrix Theory in order to examine the validity of the NPT treatment in HSP. We have investigated the pathology examining the sEMG recorded signal for about eight minutes. We have performed standard electromyographic investigations as well as we have applied the RMT method of analysis. We have investigated the sEMG signals before and after the NPT treatment. The application of a so robust method as the RMT evidences that the NPT treatment was able to induce a net improvement of the disease respect to the pathological status before NPT.

Research on Power Quality Disturbance Signal Classification Based on Random Matrix Theory

In this paper, a method of power quality disturbance classification based on random matrix theory (RMT) is proposed. The method utilizes the power quality disturbance signal to construct a random matrix. By analyzing the mean spectral radius (MSR) variation of the random matrix, the type and time of occurrence of power quality disturbance are classified. In this paper, the random matrix theory is used to analyze the voltage sag, swell and interrupt perturbation signals to classify the occurrence time, duration of the disturbance signal and thedepth of voltage sag or swell. Examples show that the method has strong anti-noise ability.

随机矩阵理论在高速路关键路径辨识中的应用

高速公路网络是我国各地区相互连接的重要纽带,高速公路网络关键路径辨识对确保高速网络的可靠运行具有重要意义。传统的关键路径分析方法基于拓扑结构,未考虑交通网络的运输量特性;而现有的基于运输量数据的分析方法只考虑部分路径的运输量特性,难以反映交通网络的实际运行情况。利用路径运输量数据,搭建运输量随机矩阵模型,针对高速公路网络异常后的运输量变化特性,定义关键路径评估指数,实现异常影响程度的量化评估,在此基础上提出一种基于数据驱动的高速公路网络关键路径辨识方法。最后,采用辽宁省高速公路网络进行分析,验证了所提方法的合理性和有效性,并将该方法应用于城市路网案例中,进一步证明该方法具有普适性。

基于特征值的动态数字信道化子带检测算法

动态数字信道化接收结构通过检测所有子带,判断信号是否存在,为综合滤波器组处理提供依据,因此子带检测在接收结构中起着关键作用。针对传统检测算法存在低信噪比(signal-to-noise ratio,SNR)下检测性能不高的问题,依据随机矩阵理论,提出了基于最大最小特征值之差与平均特征值之比的检测算法,利用平均特征值和最小特征值的极限分布规律来推导算法的检测门限。其次,根据所有子带数据获取的特征值信息对所提算法进行了优化。最后,在动态数字信道化接收结构中,分析不同因素下算法的性能,表明了所提算法能够克服低SNR的影响,子带检测的性能更好。

基于生成对抗网络的电缆局部放电异常自动监测设计

电力设备运行过程中,电缆绝缘损伤、内部缺陷、外部环境等因素容易造成电缆局部放电异常,进而引发电力事故和断电故障。为了及时、有效地监测电缆局部放电异常,在生成对抗网络环境下完成电缆局部放电异常自动监测。根据电缆内部结构分析电缆局部放电原因,利用生成对抗网络重构插补缺失数据,获取完整电缆运行数据。建立随机矩阵,获取电缆运行数据的概率密度函数,提取特征向量,构建特征指标矩阵对特征向量实施奇异值分解,辨识电缆局部放电状态,实现电缆局部放电异常的自动监测。实验结果表明:所提方法在提取电缆局部放电信号脉冲时波形振动幅度小且波形完整;电缆局部放电位置定位与实际位置一致;电缆局部放电位置的相对误差低于1%。

基于RMT-CNN的电网短路故障定位研究

随着我国智能电网的快速发展,电网监测数据呈现多元化、高速化、海量化的趋势.为了充分挖掘电力大数据的潜在价值,实现电网内异常区域的自动识别与定位,本文研究了基于随机矩阵理论(random matrix theory,RMT)和卷积神经网络(convolutional neural networks,CNN)的电网异常事件定位方法.首先根据电网内部联系将电网划分为若干子系统,分区构建监测矩阵;然后采用RMT作为数据挖掘的特征提取方法,提取分区矩阵特征向量作为输入,根据电网监测数据和异常识别需求的特点搭建CNN模型;最后基于分区矩阵特征向量构建数据集,训练获得有效的异常事件自动定位CNN模型.以IEEE39节点电网模型三相短路故障为例,分析表明通过RMT提取特征向量的预处理方法能有效降低数据维度,提高CNN模型的故障定位准确率,分区RMT-CNN模型能有效定位电网内异常事件的发生地点,定位精度可达97.96%,精确率可达98.65%.

执行器随机失效系统鲁棒预测容错切换控制

针对一类具有执行器随机失效问题的离散线性系统,提出一种基于故障概率情况下的鲁棒预测容错切换控制方法。首先,将工业过程建立成新型多自由度状态空间模型,设计含有故障概率的容错控制器;其次,引入系统故障和其恢复时的随机概率,利用李雅普诺夫判据给出基于线性矩阵不等式形式的稳定性条件,再通过指数稳定的相关证明求解出不同执行器切换时的稳定条件,以保证系统故障时容错控制与无故障时常规控制间的切换;然后,控制器设计时还充分考虑了设定值变化时所产生的跟踪误差带来的影响。最后,通过仿真结果验证了所提方法的可行性。

基于矩阵填充的随机步进频雷达高分辨距离-多普勒谱稀疏恢复方法

随机步进频雷达通过合成大带宽,能在较低硬件复杂度下获得距离高分辨效果,同时由于其每个脉冲的载频随机捷变,因而具有强的抗干扰、电磁兼容能力,在复杂电磁环境高精度探测领域具有重要的应用价值。然而,由于其波形在时频域稀疏的感知形式,造成回波相参信息有所缺失,因而传统匹配滤波方法在估计高分辨距离-多普勒时会演化为欠定估计,导致估计谱中产生起伏高旁瓣,严重影响探测性能。为此,该文提出一种基于Hankel重构矩阵填充的随机步进频雷达高分辨距离-多普勒谱低旁瓣稀疏恢复方法。该方法采用低秩矩阵填充思想补全波形在时频域稀疏感知时造成的缺失采样,恢复目标连续相参信息,可以有效解决欠定估计问题。文章首先构建了随机步进频雷达的慢时间-载频(时-频)回波欠采样数据矩阵;然后,重构待恢复数据矩阵为双重Hankel型,并分析证明了矩阵满足低秩先验特性;最后,利用ADMM算法补全未采样时频数据,恢复相参信息,保证了高分辨距离-多普勒谱低旁瓣稀疏恢复。仿真和实测试验证明了该文所提方法的有效性和优越性。

便笺式存储器中一种新颖的交错映射数据布局

现代计算机一直沿用传统的线性数据布局模式,该模式允许对使用行主序模式存储的二维矩阵进行高效的行优先数据访问,但是增加了高效执行列优先数据访问的复杂性,造成列优先访问的空间局部性较差。改善列优先数据访存效率的常见解决方案是对原始矩阵进行预先转置操作,将列优先访问的复杂性集中在一次矩阵转置运算中,然而矩阵转置不仅会引入额外的数据传输操作,而且会消耗额外的存储空间用于存储转置后的矩阵。为了在不引入额外开销的情况下使行优先与列优先数据访问具有同样高效的访存效率,提出一种新颖的交错映射(IM)数据布局,同时在不改变便笺式存储器(SPM)内部结构的基础上,在SPM的输入和输出(I/O)接口处添加循环移位单元和译码单元2个新组件,实现交错映射数据布局并定制访存指令,使程序员可通过定制的访存指令充分利用该数据布局。实验结果表明,应用交错映射数据布局的SPM在仅额外增加了1.73%面积开销的情况下获得了1.4倍的加速。