Tensor Train Random Projection

This work proposes a Tensor Train Random Projection(TTRP)method for dimension reduction,where pairwise distances can be approximately preserved.Our TTRP is systematically constructed through a Tensor Train(TT)representation with TT-ranks equal to one.Based on the tensor train format,this random projection method can speed up the dimension reduction procedure for high-dimensional datasets and requires fewer storage costs with little loss in accuracy,comparedwith existingmethods.We provide a theoretical analysis of the bias and the variance of TTRP,which shows that this approach is an expected isometric projectionwith bounded variance,and we show that the scaling Rademacher variable is an optimal choice for generating the corresponding TT-cores.Detailed numerical experiments with synthetic datasets and theMNIST dataset are conducted to demonstrate the efficiency of TTRP.

Face Templates Encryption Technique Based on Random Projection and Deep Learning

Cancellable biometrics is the solution for the trade-off between two concepts:Biometrics for Security and Security for Biometrics.The cancelable template is stored in the authentication system’s database rather than the original biometric data.In case of the database is compromised,it is easy for the template to be canceled and regenerated from the same biometric data.Recoverability of the cancelable template comes from the diversity of the cancelable transformation parameters(cancelable key).Therefore,the cancelable key must be secret to be used in the system authentication process as a second authentication factor in con-junction with the biometric data.The main contribution of this paper is to tackle the risks of stolen/lost/shared cancelable keys by using biometric trait(in different feature domains)as the only authentication factor,in addition to achieving good performance with high security.The standard Generative Adversarial Network(GAN)is proposed as an encryption tool that needs the cancelable key during the training phase,and the testing phase depends only on the biometric trait.Additionally,random projection transformation is employed to increase the proposed system’s security and performance.The proposed transformation system is tested using the standard ORL face database,and the experiments are done by applying different features domains.Moreover,a security analysis for the proposed transformation system is presented.

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.

Quasi-cyclic Random Projection Code and Hardware Implementation

Random Projection Code (RPC) is a mechanism that combines channel coding and modulation together and realizes rate adaptation in the receiving end. Random projection code’s mapping matrix has significant influences on decoding performance as well as hardware implementation complexity. To reduce hardware implementation complexity, we design a quasi-cyclic mapping matrix for RPC codes. Compared with other construction approaches, our design gets rid of data filter component, thus reducing chip area 7284.95 um2, and power consumption 331.46 uW in 0.13 um fabrication. Our simulation results show that our method does not cause any performance loss and even gets 0.2 dB to 0.5 dB gain at BER 10-4.

Rate Adaptation for Decoding-and-Forward Relay Channel by Random Projections Codes

This paper investigates rate adaptation schemes for decoding-and-forward (DF) relay system based on random projections codes (RPC). We consider a classic three node relay system model, where relay node performs on half-duplex mode. Then, we give out receiving diversity relay scheme and coding diversity relay scheme, and present their jointly decoding methods. Furthermore, we discuss the performance of the two schemes with different power allocation coefficients. Simulations show that our relay schemes can achieve different gain with the help of relay node. And, we should allocate power to source node to just guarantee relay node can decode successfully, and allocate remain power to relay node as far as possible. In this way, this DF relay system not only achieves diversity gain, but also achieves higher and smooth spectrum efficiency.

Statistics of Projected Motion in One Dimension of a D-Dimensional Random Walker

We are studying the motion of a random walker in generalised d-dimensional continuum with unit step length (up to 10 dimensions) and its projected one dimensional motion numerically. The motion of a random walker in lattice or continuum is well studied in statistical physics but what will be the statistics of projected one dimensional motion of higher dimensional random walker is yet to be explored. Here in this paper, by addressing this particular type of problem, it shows that the projected motion is diffusive irrespective of any dimension;however, the diffusion rate is changing inversely with dimensions. As a consequence, it can be predicted that for the one dimensional projected motion of infinite dimensional random walk, the diffusion rate will be zero. This is an interesting result, at least pedagogically, which implies that though in infinite dimensions there is diffusion, its one dimensional projection is motionless. At the end of the discussion we are able to make a good comparison between projected one dimensional motion of generalised d-dimensional random walk with unit step length and pure one dimensional random walk with random step length varying uniformly between -h to h where h is a “step length renormalizing factor”.

考虑随机返工与紧急插单的可抢占设计项目群调度

鉴于多项目并行以及因随机返工和紧急插单而导致的任务抢占特征,使设计项目群调度问题难以求解,而传统随机动态规划方法因维数灾难只能获得小规模问题的最优策略,为构造面向大规模问题的高效近似方法,提出将原随机调度问题近似分解为各个状态下的确定性调度子问题,从而获得原问题的次优策略。建立了确定性调度子问题的混合整数规划模型,并提出基于元启发式算法和优先规则的求解方法。基于标准测试集PSPLIB设计了多组计算实验,在不同调度环境下验证了所构建模型和算法的有效性。实验结果表明,元启发式算法不但在单项目平均拖期比目标下较最优规则提升了12%以上,而且具有较高的计算效率,能够满足实际决策需求。

公共政策评估中的随机控制实验:实施困境与突破策略

采用随机控制实验方法来进行政策评估,已成为公共政策或项目评估的“黄金标准”。但是,随机控制实验方法在中国政策评估过程中还运用较少,评估者缺乏对其实施困境与突破策略的深入认识。本研究在深入分析随机控制实验方法及其适用范围的基础上,对随机控制实验的实施困境与突破策略进行了系统的考察与总结。研究发现,采用随机控制实验开展政策评估主要面临着实验方法本身的复杂性、实验方法引发的公共价值分歧以及随机控制实验融入中国政策场域的挑战三个层面的困境。

多源多特征集成的南水北调工程丹江库区湿地时空格局演变

丹江口水库是中国南水北调工程的关键水源区。随着城镇化发展以及大坝二次建设,库区湿地生态系统变化显著,亟需湿地生态科学监测。以丹江库区为例,依托Google Earth Engine(GEE)平台,首先采用已有土地覆盖数据集生成湿地样本集,其次整合Landsat影像、DEM等数据构建多源特征集合,并基于Jeffries-Matusita(JM)距离进行特征优选,使用随机森林(RF)算法实现了1985~2023年丹江库区湿地制图。结果表明:①本文提出的样本采集流程可有效提高样本质量,为长时序分类样本采集提供参考;②湿地分类特征优选后特征数由37个减为27个,分类总体精度变化不大,优选后的特征应用于丹江库区湿地分类的平均总体精度(OA)以及平均数量和分配分歧指数(QADI)分别为89.53%和0.0802,说明特征优选有效减少信息冗余,提高影像分类效率;③1985~2023年,丹江库区湿地面积呈波动增加趋势,从1985年的17839.85 ha扩大到2023年的28872.48 ha,面积增长38.12%。总体来说,丹江库区湿地生态系统呈现出逐步恢复和优化的良好态势。

基于随机活动工期的装配式项目鲁棒性调度优化

将装配式项目的生产阶段、运输阶段和装配阶段作为一个整体进行研究,考虑了各阶段的调度性质及相互牵制特性,提出了分种类分批次的调度策略。针对随机活动工期的装配式项目调度问题,采用鲁棒性调度方法,建立了以项目鲁棒值和成本值为优化目标的生产-运输-装配一体化建造鲁棒性调度模型。依据调度性质设计了集成精英策略的非支配性遗传算法(Non-dominated Sorting Genetic Algorithms-II,NSGA-II)并对其进行了求解。最后选取装配式项目实际案例,验证了算法的有效性并对实验结果进行了分析。研究结果表明,通过改变活动时差的不同分布状态,可在提高项目鲁棒性的同时保证项目成本最低。

核酸检测的重排算法及其数值模拟

2022年春季上海遭受到奥密克戎变异株的侵袭,核酸检测是筛查新冠阳性病例的重要手段之一。目前社区常用核酸检测方式是10人/20人混合检测,重点人群单人单管复测。考虑到检测数量的庞大,二次复核易对非阳性人员造成恐慌,仿照CT成像原理,设计一种核酸检测重排方法,每人检测后将检测液分别随机置于多组不同试管中,根据不同组试管中的检测结果(投影数据),利用反投影方法,确定进入二次检测人员。计算机仿真结果表明,上述所设计的重排算法能够实现减少总检测数量和提高进入二次检测人员精度的目的。因此以上重排方法有望进一步应用到智能化的核酸采样机器人上,达到高效检测的目的。

基于可见光谱特征波长提取和分类算法的柑橘黄龙病快检研究

柑橘黄龙病(HLB)是由亚洲韧皮杆菌引起的一种严重病害,目前无法根治。其防控具有重要意义和经济价值。当前利用健康和患病叶片的光谱差异对其进行诊断显示了良好的应用前景。因患病叶片在叶绿素反射区及O—H伸缩振动区的可见光谱与健康叶片存在显著差异,而可见光谱检测在采集和数据处理方面具有成本低、简便的优势,研究可见光谱的黄龙病快速检测方法具有可行性和重要意义。为了减少光谱数据冗余和计算量,实现精准的黄龙病的早期鉴别以及降低黄龙病相似病症的误诊率,采集了黄龙病患病地区共160个叶片样本。经qPCR测定分别将其分类标定为健康、轻度疾病、重度疾病和缺镁症四类。根据叶片样本在可见光波段450~800 nm的反射光谱特征,通过S-G平滑以及降采样等预处理光谱数据后,为了优选出尽可能囊括光谱特征信息的特征波长,分别使用遗传算法(GA)、连续投影算法(SPA)以及竞争自适应重加权采样法(CARS)对采集到的可见光谱数据进行特征波长提取和降维优选出特征波长,进一步降低模型复杂度,提高预测精度。综合泛化能力及检测速度的考量,在定性判别分析模型的选择中采用训练速度快,分析准确率高的最小二乘支持向量机(LS-SVM)以及随机森林(RF)对两种变量筛选算法降维后的数据进行分类判别。通过对不同的模型的验证优选,筛选出最佳的快检方案。对比发现,在建立的模型中,SPA-RF模型与其他模型比较,对于训练集和测试集的判别准确率分别达到了100%和97.5%。结果表明,连续投影算法以及随机森林的组合分类模型可以很好地实现黄龙病早期的病理鉴别,同时也能够很好地识别出黄龙病病叶与其他相似病症的差异,为柑橘黄龙病快速检测及防治提供了一种方法依据。

基于MRP的可撤销模板设计及其分析

针对基于生物特征认证系统中的存储及传输安全问题,并且考虑到基于VQ(Vector Quantization)算法声纹认证系统训练数据少,存储空间和训练时间也比较小的优点,在基于VQ算法声纹认证系统的基础上,采用MRP(Multispace Random Projection)提出一种可撤销声纹模板.通过特征点与特征点,特征点与码字之间的距离变换前后保持不变,说明平均量化误差不变,从而证明该方法满足可撤销模板的性能保持性.通过随机矩阵和不定方程的分析证明该方法满足不可逆性,即是安全的.初步实验结果的认证率达96%,说明该方法的有效性.

深度线索增强的全息视网膜投影显示

全息视网膜投影显示(retinal projection display,RPD)具有大景深的特征,是能够缓解辐辏聚焦冲突(vergence accommodation conflict,VAC)的近眼显示技术之一。但是,景深过大会导致聚焦模糊的深度线索丢失。因此,提出了一种基于带限随机相位的RPD全息图计算方法,其通过在目标图像面引入带限随机相位控制进入瞳孔的光束宽度,从而达到控制景深范围并增强深度线索的目的。计算全息图并再现过程可分为3步:首先,根据目标图像所在深度及进入瞳孔时限制的光束宽度计算得到带限随机相位。第二步,目标图像乘以球面波相位及带限随机相位后通过一步菲涅尔衍射获得全息图。最后,准直的激光光源照射于加载全息图的空间光调制器,再现的物光汇聚于人眼瞳孔处实现深度线索增强的全息RPD。实验结果表明,基于带限随机相位的全息RPD不仅具有低散斑、高再现质量等优势,而且能够灵活控制目标图像的景深,为观察者提供聚焦模糊的深度线索。

基于VSRP与β-GWO-SVM的变压器故障辨识方法

针对变压器故障诊断准确率低的问题,提出一种基于VSRP与β-GWO-SVM的变压器故障诊断方法。首先,采用非常稀疏随机投影(very sparse random projection,VSRP)对原始数据进行维数约减,消除变量信息之间的冗余特征;其次,用β-混沌序列优化的灰狼算法(β-chaotic map enabled grey wolf optimizer,β-GWO)动态寻优支持向量机(support vector machine,SVM)的核参数与惩罚因子,获取VSRP与β-GWO-SVM相结合的综合故障诊断模型;最后,将实际变压器故障数据输入诊断模型,并与传统灰狼优化支持向量机模型(GWO-SVM)、粒子群优化支持向量机模型(particle swarm optimization-SVM,PSO-SVM)进行对比验证,诊断精度分别为91.87%、82.13%、75.10%,结果表明该文所提方法能够有效地提升变压器故障诊断性能。

基于变量筛选与机器学习算法的渭-库绿洲土壤有机质含量估测研究

选择合适的变量筛选方法和模型可有效提升土壤有机质含量的估测精度。本研究以新疆渭干河-库车河绿洲为研究区,基于哨兵2号(Sentinel-2)卫星影像和实测土壤有机质,通过对土壤有机质与遥感影像波段及多种光谱指数进行相关分析,结合Boruta算法和连续投影算法(Successive Projections Algorithm,SPA)进行变量筛选,构建随机森林(Random Forest,RF)模型和BP神经网络(Back Propagation Neural Network,BPNN)模型进行表层土壤有机质含量的估测。结果表明:(1)波段B3、B4、B5、B7和B8A以及转换植被指数(Transformed Vegetation Index,TVI)、颜色指数(Color Index,CI)对土壤有机质含量的估测具有重要作用;(2)单独使用Boruta算法和SPA算法筛选的变量集建模效果要优于全变量集以及结合算法筛选的变量集,Boruta算法优于SPA算法;(3)RF模型的估测能力优于BPNN模型,最优估测模型训练集和验证集的决定系数(R^(2))均大于0.74,模型拟合效果较好,均方根误差(RMSE)小于2.0 g/kg,相对分析误差(RPD)大于1.6,能够较好地进行土壤有机质含量的估测。采用Boruta算法结合随机森林模型可较好地反演绿洲表层土壤有机质的空间分布,为该区域土壤养分评价提供参考。

Fine-grained grid computing model for Wi-Fi indoor localization in complex environments

The fingerprinting-based approach using the wireless local area network(WLAN)is widely used for indoor localization.However,the construction of the fingerprint database is quite time-consuming.Especially when the position of the access point(AP)or wall changes,updating the fingerprint database in real-time is difficult.An appropriate indoor localization approach,which has a low implementation cost,excellent real-time performance,and high localization accuracy and fully considers complex indoor environment factors,is preferred in location-based services(LBSs)applications.In this paper,we proposed a fine-grained grid computing(FGGC)model to achieve decimeter-level localization accuracy.Reference points(RPs)are generated in the grid by the FGGC model.Then,the received signal strength(RSS)values at each RP are calculated with the attenuation factors,such as the frequency band,three-dimensional propagation distance,and walls in complex environments.As a result,the fingerprint database can be established automatically without manual measurement,and the efficiency and cost that the FGGC model takes for the fingerprint database are superior to previous methods.The proposed indoor localization approach,which estimates the position step by step from the approximate grid location to the fine-grained location,can achieve higher real-time performance and localization accuracy simultaneously.The mean error of the proposed model is 0.36 m,far lower than that of previous approaches.Thus,the proposed model is feasible to improve the efficiency and accuracy of Wi-Fi indoor localization.It also shows high-accuracy performance with a fast running speed even under a large-size grid.The results indicate that the proposed method can also be suitable for precise marketing,indoor navigation,and emergency rescue.

海上风电施工中海缆敷设张力影响因素权重分析

为分析挖掘海缆敷设监测数据中对施工质量的有益成果,研究影响海缆敷设张力因素权重量化问题,本文基于某海缆敷设工程施工数据,利用随机森林方法,分析研究海缆敷设施工对海缆张力的有关影响因素。以张力作为因变量,根据地理位置信息和作业时间计算得出实际航行速度,以航行速度、水深、侧向力和埋深作为自变量,在对施工数据进行清洗挖掘的基础上,利用随机森林方法分析各因素对张力的影响权重,得出特征重要性排序。结果表明:海缆张力的影响,航行速度在所有特征中的特征重要性最高,权重占比0.57,其次是埋深和水深,权重分别占比为0.23和0.18。研究所得结果与已有文献分析进行了对比,体现了所得结果的有效性和优势,为海上风电工程施工和海缆敷设施工质量安全提供帮助和参考。

基于随机部署RP的位置指纹定位算法

随着人们对位置信息需求的不断增加,室内定位技术迎来了前所未有的研究热潮.在分析影响基于位置指纹定位算法性能主要因素的基础上,提出了基于随机部署参考点(RP)的位置指纹定位算法.该方法首先将目标环境划分成多个子区域,在每个子区域中采用随机方式部署RP,从而减少定位成本、提高灵活性;为了在保证定位性能的前提下缩短定位时间,给出了两种数据剔除方法.仿真结果表明,该方法能够获得良好的定位性能,具有实际的应用价值.

基于Fourier-TOuNN的鲁棒性拓扑优化设计

为推广拓扑优化设计方法的工程应用,需要在设计过程中考虑结构鲁棒性以应对实际工程荷载的随机性。本文基于神经网络提出了鲁棒性结构拓扑优化设计的高效方法。该方法通过优化Fourier-TOuNN神经网络的权值更新描述结构拓扑的密度变量,并引入随机荷载下结构柔顺度平均值和标准差的加权总和作为目标函数,从而定义了随机荷载下的结构鲁棒性优化问题。利用神经网络的自动反向微分功能,实现了优化过程中灵敏度的直接求解。借助Fourier-TOuNN细部尺寸可控特性,可在结构中生成细小支撑以抵抗随机荷载。数值算例表明,采用本文提出的方法可以高效地获得鲁棒性稳健的优化设计结果。