基于卡尔曼滤波的压缩感知弱匹配去噪重构

现有的贪婪迭代类压缩感知重构算法均基于最小二乘对信号进行波形估计,未考虑到可能将量测噪声引入信号估计的情况.针对以上不足,提出了一种基于线性Kalman滤波的压缩感知弱匹配去噪重构算法.该算法不需已知稀疏度先验,通过引入Kalman滤波,在最小均方误差准则下,每次迭代都获得最佳信号估计;并以弱匹配的方式同时筛选出有效的原子,并剔除冗余原子进而重构原信号.新算法继承了现有贪婪迭代类算法的有效性,同时避免了因噪声干扰或稀疏度未知导致的重构失败.理论分析和实验表明,新算法在同等条件下,重构性能优于现有典型贪婪迭代类算法,且其运算时间低于BPDN算法和同类的KFCS算法.     

基于Monte Carlo采样的压缩感知弱匹配去噪重构

最小二乘是现有贪婪迭代类压缩感知重构算法中通用的信号估计方法,其未考虑到可能将量测噪声引入信号估计的情况.针对以上不足,提出一种基于Monte Carlo采样的压缩感知弱匹配去噪重构算法.该算法在未知信号稀疏度先验的条件下,通过引入递推Bayesian估计减小量测噪声的干扰;同时,以弱匹配的方式筛选出有效的原子,并剔除冗余原子进而重构原信号.新算法继承了现有贪婪迭代类算法的有效性,同时避免了因噪声干扰或稀疏度未知导致的重构失败.理论分析和实验表明,新算法在同等条件,尤其是非高斯噪声情况下,重构性能优于现有典型贪婪迭代类算法,且其运算时间低于BPDN算法和同类的KF-SAMP算法.     

基于F范数的二维主成分分析算法及焊缝表面缺陷识别研究

针对传统二维主成分分析(two-dimensional principal component analysis, 2DPCA)算法应用于焊缝表面缺陷识别中存在重构性能及鲁棒性较弱等问题,本文将最大化投影距离和最小化重构误差引入到目标函数中,提出了一种基于F范数的非贪婪二维主成分分析算法(non-greedy 2DPCA with F-norm, NG-2DPCA-F),该算法具有良好的鲁棒性和较低的重构误差。为了进一步提取图像的结构信息和求解出维数更小的特征矩阵,进而提出一种基于F范数的非贪婪双向二维主成分分析算法(non-greedy bilateral 2DPCA with F-norm, NG-B2DPCA-F)。最后,以含有不同噪声块的焊缝表面图像数据集进行实验,结果表明,本文所提算法在平均重构误差、重构图像与分类识别实验中均表现出良好的鲁棒性能。     

基于贝叶斯假设检验的压缩感知重构

为提高贪婪类算法的重构精度,该文提出一种贝叶斯假设检验匹配追踪算法。该算法首先建立了贝叶斯假设检验模型,用于在噪声污染下识别稀疏信号非零元素的下标;其次利用追踪算法的输出下标集作为该模型的候选集,并对候选集中的每个元素进行假设检验以剔除冗余下标;最后根据剔冗后的真实下标集,采用最小二乘法重构原始信号。仿真结果表明:在相同的实验条件下,与传统贪婪类算法相比,该算法不存在冗余下标,具有更强的抗干扰能力和更高的重构精度。     

原子稀疏结合块结构稀疏的联合表示图像识别算法

针对结构稀疏表示识别算法中稀疏准则的选择以及字典内块的划分两个重要问题,提出两种改进的结构稀疏表示识别算法。首先,针对结构稀疏准则会出现较多系数不为零的情况,提出将结构稀疏准则与原子稀疏准则相结合的思路,包括并行和串行两种结合方式。并行结合是将两者以加权求和的方式同时作为稀疏表示的判别准则进行分类,串行结合则是在结构稀疏表示后,通过重组字典,再对测试样本进行原子稀疏表示实现分类。然后,针对字典中类内样本的块划分问题,提出基于MLP的结构稀疏表示识别算法,先将类内样本经过MLP的划分,保证各个分块分别位于低维的线性子空间中,再进行结构稀疏表示的分类。实验结果证明两种改进的结构稀疏表示识别算法的有效性。      

压缩感知中一种改进的迭代硬阈值算法

研究了压缩感知理论中一种改进的迭代硬阈值稀疏信号重构算法。针对现有IHT算法类最优秀的BIHT算法中回溯操作无法保证稀疏信号重构误差递减的问题,对稀疏重构误差及其差值进行了简单介绍和分析,提出了一种能够保证重构误差随迭代进行单调减小的重构算法,在每次迭代的回溯操作中选择能够保证重构误差逐渐减小的原子,并将其指标与估计支撑集合并,最后基于最小二乘法进行伪逆运算获取稀疏信号估计。对高斯稀疏信号和0-1稀疏信号进行了仿真,证明了优于IHT、NIHT以及BIHT算法的稀疏信号重构性能。     

基于杂波聚类与贪婪策略的电离层杂波智能处理方法

在高频地波超视距雷达系统中,电离层杂波作为一种时变、非均匀、非高斯的复杂杂波,其抑制方法一直是困扰国内外的研究难点。针对传统杂波抑制方法对电离层杂波的处理能力单一、普适性差的问题,该文开展了杂波智能分类抑制处理方法的研究,通过对电离层杂波的成因与特性分析,提出了一种基于杂波聚类与贪婪策略的电离层杂波智能处理方法,对电离层杂波进行分类分情况处理。实验分析表明该方法对电离层杂波的抑制性能优于典型传统算法。      

一种自适应阈值选择的宽带压缩频谱感知重构算法

针对宽带压缩频谱感知算法在未知稀疏度条件下重构频谱效果不理想的问题,提出一种自适应阈值选择的改进型分段正交匹配追踪(Adaptive Threshold Option-Improved Stagewise Orthogonal Matching Pursuit, ATO-IStOMP)算法,该算法根据迭代残差的分布特性自适应地调整原子选择判决门限,使其每次迭代能够高效选择多个原子作为候选集,同时该算法利用残差比阈值对迭代终止条件进行修正,能够实现重构算法的盲停止,增强算法在低信噪比环境下的鲁棒特性。仿真结果表明,ATO-IStOMP算法能够实现对原始信号的盲重构,且在低信噪比环境下的重构性能良好。      

基于改进遗传算法的多无人机搜索航路规划

针对多无人机对特定区域内的目标搜索问题,提出了一种基于贪婪算法改进变异操作的自适应遗传算法。依据先验情报对搜索区域进行栅格化处理,并结合无人机性能约束建立基于状态更新周期的协同搜索模型;引入类0-1编码将无人机航向控制序列与搜索概率进行关联;考虑到机载雷达对某一区域的重复探测会在一定程度上提高搜索概率,提出加入贪婪算子的贪婪变异策略,并引入策略选择阈值实现依据搜索概率变化对变异策略的动态调整,提高算法后期的局部搜索能力。仿真结果表明,改进的自适应遗传算法整体性能较好,具有较强的搜索能力和鲁棒性。     

一种面向信号分类的匹配追踪新方法

匹配追踪(MP)的主要策略是通过每次迭代时选择一个局部最优解,从而逐步逼近原始信号。然而传统的MP系列算法进行原子匹配时,各类原子集间存在交集,从而影响了原子的表示能力以及相应的分类效果。基于此,该文提出一种适用于信号监督分类的匹配追踪新算法。其原子挑选的准则为:同类信号采用相同的原子集匹配,获取相同的类内表示结构;异类信号选择不同的原子集匹配,从而增强信号的类间差异。示例分析表明,使原子集间相互独立,能够减少异类信号间的共性因素,强化信号间的区分度,从而有利于提升分类识别效果。通过在标准图像库和实测雷达辐射源信号集上的实验表明,较之传统的MP系列方法,所提算法对噪声和遮挡具有更强的鲁棒性。     

Stagewise Weak Gradient Pursuits

Finding sparse solutions to underdetermined inverse problems is a fundamental challenge encountered in a wide range of signal processing applications, from signal acquisition to source separation. This paper looks at greedy algorithms that are applicable to very large problems. The main contribution is the development of a new selection strategy (called stagewise weak selection) that effectively selects several elements in each iteration. The new selection strategy is based on the realization that many classical proofs for recovery of sparse signals can be trivially extended to the new setting. What is more, simulation studies show the computational benefits and good performance of the approach. This strategy can be used in several greedy algorithms, and we argue for the use within the gradient pursuit framework in which selected coefficients are updated using a conjugate update direction. For this update, we present a fast implementation and novel convergence result.     

Relay Subset Selection in Wireless Networks Using Partial Decode-and-Forward Transmission

This paper considers the problem of selecting a subset of nodes in a two-hop wireless network to act as relays in aiding the communication between the source–destination pair. Optimal relay subset selection with the objective of maximizing the overall throughput is a difficult problem that depends on multiple factors, including node locations, queue lengths, and power consumption. A partial decode-and-forward strategy is applied in this paper to improve the tractability of the relay selection problem and the performance of the overall network. Note that the number of relays that are selected ultimately determines the performance of the network. This paper benchmarks this performance by determining the net diversity that is achieved using the relays that are selected and the partial decode-and-forward strategy. This framework is subsequently used to further transform relay selection into a simpler relay placement problem, and two proximity-based approximation algorithms are developed to determine the appropriate set of relays to be selected in the network. Other selection strategies, such as random relay selection and a greedy algorithm that relies on channel state information, are also presented. This paper concludes by showing that the proposed proximity-based relay selection strategies yield near-optimal expected rates for a small number of selected relays.      

Application of Rollout Strategy to Test Points Selection for Integer-Coded Fault Wise Table

Test points selection for integer-coded fault wise table is a discrete optimization problem. The global minimum set of test points can only be guaranteed by an exhaustive search which is eompurationally expensive. In this paper, this problem is formulated as a heuristic depth-first graph search problem at first. The graph node expanding method and rules are given. Then, rollout strategies are applied, which can be combined with the heuristic graph search algorithms, in a computationally more efficient manner than the optimal strategies, to obtain solutions superior to those using the greedy heuristic algorithms. The proposed rollout-based test points selection algorithm is illustrated and tested using an analog circuit and a set of simulated integer-coded fault wise tables. Computa- tional results are shown, which suggest that the rollout strategy policies are significantly better than other strategies.     

动作识别算法的评估策略探讨

以时空兴趣点特征和支持向量机(SVM)分类器识别方法为基本算法,在广泛使用的公开动作数据集KTH上,从不同角度考察评估策略对动作识别算法性能的影响。实验表明,当采用不同的交叉实验方法时,算法性能的波动最大达到10.5%,而不同数据集划分方法对算法性能的影响则达到11.87%。因此,通过量化分析得出的结论,可以充分地比较现有算法的真实差异,并为设计合理的评估策略提供参考。     

无标度网络的局部搜索策略

基于最小聚类系数搜索和贪婪算法在搜索中的优点,根据BA无标度网络的结构特性,以最小聚类系数和度量距离两个影响搜索性能的参数,设计出最小聚类系数最小距离搜索策略。并通过仿真实验对最小聚类系数最小距离搜索策略、最小聚类系数搜索策略、贪婪算法和随机游走搜索策略的性能进行对比。理论分析与仿真结果均表明,最小聚类系数最小距离搜索策略在BA无标度网络模型上能取得较好地搜索效果。     

Minimizing Recovery State in Geographic Ad Hoc Routing

Geographic ad hoc networks use position information for routing. They often utilize stateless greedy forwarding and require the use of recovery algorithms when the greedy approach fails. We propose a novel idea based on virtual repositioning of nodes that allows to increase the efficiency of greedy routing and significantly increase the success of the recovery algorithm based on local information alone. We explain the problem of predicting dead ends which the greedy algorithm may reach and bypassing voids in the network, and introduce NEAR, node elevation ad-hoc routing, a solution that incorporates both virtual positioning and routing algorithms that improve performance in ad-hoc networks containing voids. We demonstrate by simulations the advantages of our algorithm over other geographic ad-hoc routing solutions.     

GMD V-BLAST系统天线选择

基于最大容量和最小差错率准则,研究了在GMD V-BLAST系统中的天线选择问题。选用以信道矩阵非零奇异值的几何均值最大化为目标函数,可以避免容量与差错率性能之间的矛盾。在所有可用天线中进行选择的全搜索算法虽有最佳性能,但复杂度太高。基于贪婪算法,对发射天线采用快速的逐增选择策略,对接收天线采用快速的逐减选择策略,可以显著降低计算的复杂性。计算机仿真结果表明,所采用的快速天线选择算法可以较低的复杂度获得接近全搜索法的容量和分集增益。     

Planar graph routing on geographical clusters

Geographic routing protocols base their forwarding decisions on the location of the current device, its neighbors, and the packets destination. Early proposed heuristic greedy routing algorithms might fail even if there is a path from source to destination. In recent years several recovery strategies have been proposed in order to overcome such greedy routing failures. Planar graph traversal was the first of those strategies that does not require packet duplication and memorizing past routing tasks. This article introduces a novel recovery strategy based on the idea of planar graph traversal but performing routing tasks along geographical clusters instead of individual nodes. The planar graph construction method discovered so far needs one-hop neighbor information only, but may produce disconnection even if there is a path from source to destination. However, simulation results show that the proposed algorithm is a good choice from a practical point of view, since disconnection does only concern sparse networks, while in dense network the proposed algorithm competes with existing solutions and even outperforms planar graph routing methods based on one-hop neighbor information. This paper finally gives an outline of further research directions which show that geographical clusters may be the key to solve some problems that come along with planar graph routing in wireless networks.     

水下无线传感器网络目标跟踪低复杂度节点行径策略

针对水下无线传感器网络节点选择“组合爆炸冶的问题,研究了低计算复杂度节点选择问题。首先,在量化量测的条件下推导了后验克拉美罗下界(PCRLB)与节点位置的关系,为节点选择提供了准则;然后,将GBFOS 算法、贪心算法和随机算法与推导的PCRLB 相结合,设计了低计算复杂度的节点选择策略。实验结果表明,GBFOS 算法和贪心算法可以在保持跟踪性能不退化的情况下,大幅度降低计算复杂度,非常适合解决密集水下网络节点选择问题。此外,还将GBFOS 算法应用到非理想信道条件下节点选择问题,实验结果显示考虑非理想信道的影响可以大幅提高跟踪性能。