基于移动锚节点的加权多维标度节点定位算法

针对无线传感器网络节点定位精度不足等原因,提出了一种基于移动锚节点的加权多维标度度节点定位算法,首先通过对移动锚节点的轨迹进行采样,添加虚拟锚节点,增加拓扑约束关系,将虚拟锚节点收集的信息与实际节点之间的信息构成距离矩阵,然后利用奇异值分解计算节点相异性矩阵的逼近阵,通过加权多维标度对节点进行定位.仿真实验表明:与MDS-MAP和MDS-MAP(P)算法相比,该算法具有良好的定位精度.     

基于虚节点的非度量加权多维标度定位算法*

提出一种基于虚节点的非度量加权多维标度定位算法,它利用矩阵截断奇异值分解计算节点相异性矩阵的逼近阵。仿真实验显示,该算法在网络节点密度较低或拓扑结构不规则时比以往算法有更好的定位精度。     

一种基于非度量多维标度的移动定位算法

稀疏无线传感器网络由于缺乏足够的距离和连通性信息,导致大多数定位算法无法有效工作.提出了一种非度量多维标度移动节点辅助定位算法--NMDS-LRA(M).该算法对移动节点运动轨迹抽样,添加拓扑约束关 系,然后利用奇异值分解计算节点相异性矩阵的逼近阵,从而有效解决了移动辅助定位问题,并且避免了以往移动定位算法中虚拟节点间距离误差较大对定位精度的影响.仿真分析表明,与以往算法相比,提出的算法有更好的定位精度,而且在较低网络连通度和不规则网络分布的条件下表现出更好的可靠性.     

融合奇异值分解和最大间距准则的人脸识别方法

提出了一种融合奇异值分解（SVD）和最大间距准则鉴别分析（MMC）的人脸识别方法。对人脸图像进行奇异值分解,选取较大的一组奇异值构成特征向量,对所有训练样本按照最大间距准则鉴别分析算法计算投影矩阵,把人脸图像矩阵在投影矩阵上投影得到特征矩阵。融合决策阶段,在以上两类特征集中,分别计算待识别样本到所有训练样本的欧氏距离并对得到的两类结果进行加权融合,最后根据最近距离分类器分类。基于ORL人脸数据库上的实验结果表明算法的有效性。     

改进的分布式无线传感器网络多维标度定位算法

为提高无线传感器网络集中式多维标度MDS-MAP算法的定位精度,提出了一种改进的基于MDS的分布式定位算法。该算法在构建距离矩阵时引入Euclidean算法距离估算思想,同时采用一种优化的基于最小二乘逼近的坐标转换方法实现节点由相对坐标到绝对坐标的转换。实验结果显示,与经典MDS-MAP算法相比,改进算法在多种网络拓扑结构下均能有效提高节点的定位精度。     

基于分而治之的多维标度算法

作为一种典型的多元统计分析方法,多维标度法(MDS)广泛应用于降维和可视化研究中.MDS从n个样本间的距离距阵出发,求取它们在低维欧氏空间的坐标.经典MDS算法(CMDS)的时间复杂度为Θ(n3),影响MDS的速度.文中基于分而治之的思想提出一种新的MDS算法.首先将距离矩阵沿对角线分成若干子矩阵,然后对每个子矩阵求解,最后通过正交变换和平移变换整合各子矩阵的解,从而得到原距离矩阵的全局解.该算法的结果与CMDS完全一致.当样本维数远小于样本个数时,其时间复杂度仅为Θ(nlgn).与CMDS算法相比,该算法的速度大大提高,从而使MDS可应用于更大规模数据集.     

基于奇异值分解的大型社交网络差分隐私算法

针对基于随机投影的差分隐私算法中存在直接对降维数据直接添加噪声导致基于欧氏距离数据挖掘中数据可用性较差的问题,提出了一种基于奇异值分解的差分隐私算法。该算法首先对高维社交网络的数据利用随机投影进行降维,然后对降维后的数据进行奇异值分解并对奇异值加入高斯噪声,最后通过奇异值分解逆运算生成待发布矩阵。该算法利用的奇异值矩阵是一个仅有主对角线上有值的矩阵,值的个数为矩阵的秩,与直接对降维后的数据直接添加高斯噪声相比,对奇异值矩阵中的值添加高斯噪声能有效地降低噪声的加入量。理论证明该算法满足差分隐私,并设计了欧氏距离差实验和谱聚类实验用于分析算法的数据可用性,实验结果表明该算法的数据可用性高于基于奇异值分解的差分隐私算法。     

传感器网络中基于多维标度定位算法的改进

针对基于经典多维标度的MDS-MAP算法在定位精度方面的不足,为提高传感器定位精度,提出一种基于Euclidean算法的改进型多维标度定位算法(Euclidean-based MDS-MAP(P,C))。算法与经典多维标度算法的区别在于,Euclidean算法能够算出每个节点与其两跳邻居节点间的欧氏距离,然后用这个欧氏距离来进行多维标度,显然能提高精度。仿真实验表明基于Euclidean算法的改进型多维标度算法与经典多维标度算法相比具有很低的定位误差以及很高的定位精度。     

用于两相流电容层析成像系统中的图像重建算法

图像重建算法研究和增加投影数据是改善图像重建质量的两个重要方面。由于目前在ECT系统中存在着一种基于奇异值分解（SVD）的图像重建算法,此算法中的奇异值将对应图像重建矩阵中很大的对角线元素,从而导致伪逆很不稳定。因而讨论了改进的基于奇异值分解（MSVD）的图像重建算法,该算法是用改进奇异值分解方法求出图像重建矩阵。仿真及实验结果均表明该算法是一种实时的、重建图像质量优于SVD。     

基于多维标度和奇异值分解的视频水印算法

针对于网络中的视频资源的知识产权问题,提出一种基于多维标度(MDS)和奇异值分解( SVD)的视频水印算法。该方法首先利用MDS把原始视频各帧投影到二维平面上,然后利用SVD的方法把水印信息嵌入到视频帧与其在二维平面上投影点之间的差值上。实验证明,该算法对随机噪声干扰和诸如旋转、平移、裁剪等空间同步失真的攻击有较强的鲁棒性;另外,该算法对帧丢弃、帧插入等时间同步失真也具有一定程度的鲁棒性。     

基于加权多维定标的组网定位算法

提出一种视距条件下基于加权多维定标(MDS)技术实现到达时间(TOA)组网定位新算法。利用改进的MDS技术,得到移动台位置的粗估计值。分析基站拓扑结构对定位结果的影响,利用求组合数的方法,分别求出每种基站组合下移动台的位置估计,并与粗估计值进行比较,均方误差小的基站组合对最终定位结果贡献较大,通过加权求得最终结果。与传统MDS算法相比,加权MDS算法对冗余信息的处理能力更强,定位精度更高。     

MDS矩阵和对合MDS矩阵的新构造方法

首先对Lacan等人给出的由Vandermonde矩阵构造MDS码的方法进行了研究, 指出了其中存在的问题, 给出了由两个Vandermonde矩阵构造MDS矩阵的充要条件; 然后利用矩阵乘的方法, 给出了由标量乘Vandermonde矩阵构造MDS矩阵的充要条件; 最后在Sajadieh等人给出的由两个Vandermonde矩阵构造对合MDS矩阵方法的基础之上, 给出了标量乘Vandermonde矩阵构造对合MDS矩阵的方法。对标量乘矩阵来讲, 可以通过调控标量中分量的大小来调整标量乘矩阵元素大小和元素重量大小来满足其软、硬件实现性能, 因此该构造MDS矩阵及对合MDS矩阵的方法具有实用价值。     

基于谱特征嵌入的脑网络状态观测矩阵降维方法

针对基于功能核磁共振（fMRI）重构的脑网络状态观测矩阵维数过高且无特征表现的问题,提出一种基于谱特征嵌入（Spectral Embedding）的降维方法。该方法首先计算样本间相似性度量并构造拉普拉斯矩阵;然后对拉普拉斯矩阵进行特征分解,选取前两个主要的特征向量构建2维特征向量空间以达到数据集由高维向低维映射（降维）的目的。应用该方法对脑网络状态观测矩阵进行降维并可视化在二维空间平面,通过量化类别有效性指标对可视化结果进行评价。实验结果表明,与主成分分析（PCA）、局部线性嵌入（LLE）、等距映射（Isomap）等降维算法相比,使用该方法得到的脑网络状态观测矩阵低维空间的映射点有明显的类别意义表现,且在类别有效性指标上与多维尺度分析（MDS）和t分布随机邻域嵌入（t-SNE）降维算法相比,同一类样本间平均距离Di指数分别降低了87.1%和65.2%,不同类样本间平均距离Do指数分别提高了351.3%和25.5%;在多个样本上的降维可视化结果均有一定的规律性体现,该方法的有效性和普适性得以验证。     

A novel efficient algorithm for mobile robot localization

Being autonomous is one of the most important goals in mobile robots. One of the fundamental works to achieve this goal is giving the ability to a robot for finding its own correct position and orientation. Different methods have been introduced to solve this problem. In this paper, a novel method based on the harmony search (HS) algorithm for robot localization through scan matching is proposed. Simulation results show that the proposed method in comparison with a genetic algorithm-based approach has better accuracy and higher performance. Furthermore a new hybrid algorithm based on harmony search and differential evolution (DE) algorithms is proposed and evaluated on different benchmark functions. Finally the hybrid algorithm has been applied for mobile robot localization and it outperformed the HS-based approach.     

Improved community structure discovery algorithm based on penalised matrix decomposition for complex networks

Complex networks are one of the main research fields in data mining. In this study, a penalised matrix decomposition-based community structure discovery algorithm (PMDCSDA) for complex networks is proposed. The complex network is firstly transformed into an adjacency matrix, which is then processed for dimension reduction via principal component analysis. Numerous clusters are produced on the basis of penalised matrix decomposition. To evaluate the performance of the proposed PMDCSDA, we compare it with several classical algorithms, such as K-means, CPM and GN, using three complex network datasets. Experimental results demonstrate that the proposed algorithm can achieve improved performance in precision, recall, F1 and Sep indicator.     

Seed-based authentication for mobile clients across multiple devices

Authenticating users for mobile cloud apps has been a major security issue in recent years. Traditional passwords ensure the security of mobile applications, but it also requires extra effort from users to memorize complex passwords. Seed-based authentication can simplify the process of authentication for mobile users. In the seed-based authentication, images can be used as credentials for a mobile app. A seed is extracted from an image and used to generate one-time tokens for login. Compared to complex passwords, images are more friendly to mobile users. Previous work had been done in seed-based authentication which focused on providing authentication from a single device. It is common that a mobile user may have two or more mobile devices. Authenticating the same user on different devices is challenging due to several aspects, such as maintaining the same credential for multiple devices and distinguishing different users. In this article, we aimed at developing a solution to address these issues. We proposed multiple-device authentication algorithms to identify users. We adopted a one-time token paradigm to ensure the security of mobile applications. In addition, we tried to minimize the authentication latency for better performance. Our simulation showed that the proposed algorithms can improve the average latency of authentication for 40% at most, compared to single-device solutions.     

Update strategy based on region classification using ELM for mobile object index

Mobile object index should support efficient update operations besides efficient query operations. In this paper, we consider the issue of the efficient updating of mobile object index. Based on a model for the mobile data, we introduce a method of incorporating statistical information of the regions covered by the mobile objects into feature vectors. We then propose a novel architecture of mobile object index, where R-tree is used to index the occupied regions instead of the mobile objects themselves and extreme learning machine (ELM) is used to classify the regions. Further, we describe several related algorithms and the update strategy based on the classification of the regions. The proposed strategy and algorithms are evaluated in a simulated environment. The experiments demonstrate that the proposed update strategy based on region classification using ELM can achieve higher performance with respect to I/O operations. Compared to the strategy without region classification, the proposed method can reduce the number of I/O operations more than 80%.     

An adaptive least squares channel estimation based on conjugate gradient approach for multipath fading CDMA systems

Multiple access interference (MAI) is the main factor affecting the performance of channel estimation techniques for code division multiple access (CDMA) systems. Although, several multi-user channel estimation algorithms have been proposed to mitigate MAI, these algorithms require high computational complexities. In this paper, we address the problem of iterative least squares (LS) mobile channel estimation at high channel efficiency that requires a short training sequence along with the spreading sequences. We employ an efficient iterative method based on conjugate gradient (CG) algorithm to reduce the computational complexity of the estimation method. Computer simulations illustrate that the proposed method performs almost identical to the exact LS estimate for reasonable training lengths.     

Geometrical codification for clustering mixed categorical and numerical databases

This paper presents an alternative to cluster mixed databases. The main idea is to propose a general method to cluster mixed data sets, which is not very complex and still can reach similar levels of performance of some good algorithms. The proposed approach is based on codifying the categorical attributes and use a numerical clustering algorithm on the resulting database. The codification proposed is based on polar or spherical coordinates, it is easy to understand and to apply, the increment in the length of the input matrix is not excessively large, and the codification error can be determined for each case. The proposed codification combined with the well known k-means algorithm showed a very good performance in different benchmarks and has been compared with both, other codifications and other mixed clustering algorithms, showing a better or comparable performance in all cases.