A self‐adaptive algorithm for super‐peer selection considering the mobility of peers in cognitive mobile peer‐to‐peer networks

Cognitive peer‐to‐peer networks are obtained from a combination of cognitive networking concepts and peer‐to‐peer networks. These networks are able to improve their performance while operating under dynamic and unknown environments. A cognitive peer‐to‐peer network tries to learn an appropriate configuration for itself considering the unknown physical properties of peers. Cognitive mobile peer‐to‐peer networks refer to cognitive peer‐to‐peer networks which are built over mobile ad hoc networks. In these networks, heterogeneity of the mobility of peers and resource limitation in wireless networks create challenges for network management algorithms. Because of the dynamicity of these networks, the management algorithms should be designated in self‐adaptive manner. In one type of these networks, some peers, called super‐peers, undertake to perform network managerial tasks. The mobility of peers leads to connection failure among peers and reselection of new super‐peers. Therefore, the selection of super‐peers, due to their influential role, requires an algorithm that considers the peers' mobility. Up to now, no self‐adaptive algorithm has been designated for super‐peer selection considering the mobility of peers in a self‐adaptive manner. This paper proposes M‐SSBLA, a self‐adaptive algorithm for super‐peer selection considering the mobility of peers based on learning automata. The proposed algorithm is obtained from cooperation between a learning automata‐based cognitive engine and MIS. MIS is a well‐known super‐peer selection algorithm in mobile peer‐to‐peer networks. We compared the proposed algorithm with recently reported algorithms, especially for a network with high mobility. Simulation results show that the proposed algorithm can cover maximum ordinary‐peer with a few super‐peer and improve robustness against super‐peer failures while decreasing maintenance overhead.     

基于自适应多字典学习的单幅图像超分辨率算法

自适应字典学习利用图像结构自相似性,将图像自身作为训练样本,通过字典学习使图像中的相似块在字典下具有稀疏表示形式.本文将全局字典学习中利用图像库获取附加信息的思想融入到自适应字典学习的过程中,提出了一种基于自适应多字典学习的单幅图像超分辨率算法,从低分辨率图像自身与图像库同时获取附加信息.该算法对低分辨率图像金字塔结构中的图像块进行聚类,在聚类结果的引导下将图像库中的图像块进行分类,利用各类中的样本分别构建针对各类的多个字典,从而确定表达重建图像块的最优字典.实验表明,与ScSR、SISR、NLIBP、CSSS以及mSSIM等算法相比,本文算法具有更好的超分重建效果.     

A distributed adaptive landmark clustering algorithm based on mOverlay and learning automata for topology mismatch problem in unstructured peer‐to‐peer networks

Peer‐to‐peer networks are overlay networks that are built on top of communication networks that are called underlay networks. In these networks, peers are unaware of the underlying networks, so the peers choose their neighbors without considering the underlay positions, and therefore, the resultant overlay network may have mismatches with its underlying network, causing redundant end‐to‐end delay. Landmark clustering algorithms, such as mOverlay , are used to solve topology mismatch problem. In the mOverlay algorithm, the overlay network is formed by clusters in which each cluster has a landmark peer. One of the drawbacks of mOverlay is that the selected landmark peer for each cluster is fixed during the operation of the network. Because of the dynamic nature of peer‐to‐peer networks, using a non‐adaptive landmark selection algorithm may not be appropriate. In this paper, an adaptive landmark clustering algorithm obtained from the combination of mOverlay and learning automata is proposed. Learning automata are used to adaptively select appropriate landmark peers for the clusters in such a way that the total communication delay will be minimized. Simulation results have shown that the proposed algorithm outperforms the existing algorithms with respect to communication delay and average round‐trip time between peers within clusters. Copyright © 2015 John Wiley & Sons, Ltd.     

An optimal energy‐efficient clustering method in wireless sensor networks using multi‐objective genetic algorithm

In this study, an optimal method of clustering homogeneous wireless sensor networks using a multi‐objective two‐nested genetic algorithm is presented. The top level algorithm is a multi‐objective genetic algorithm (GA) whose goal is to obtain clustering schemes in which the network lifetime is optimized for different delay values. The low level GA is used in each cluster in order to get the most efficient topology for data transmission from sensor nodes to the cluster head. The presented clustering method is not restrictive, whereas existing intelligent clustering methods impose certain conditions such as performing two‐tiered clustering. A random deployed model is used to demonstrate the efficiency of the proposed algorithm. In addition, a comparison is made between the presented algorithm other GA‐based clustering methods and the Low Energy Adaptive Clustering Hierarchy protocol. The results obtained indicate that using the proposed method, the network's lifetime would be extended much more than it would be when using the other methods. Copyright © 2011 John Wiley & Sons, Ltd.     

自适应稀疏约束图像超分辨力重建方法

简要介绍了基于稀疏字典约束的超分辨力重建算法,提出了具有低复杂度的基于K均值聚类的自适应稀疏约束图像超分辨力重建算法。所提算法从两个方面降低其计算复杂度:分类训练字典,对图像块归类重建,降低每个图像块所用字典的大小;对图像块的特征进行分析,自适应地选择重建方法。实验结果表明,提出的快速重建方法在重建质量与原算法相当的前提下,可以较大程度地降低重建时间。     

An efficient actor‐critic reinforcement learning for device‐to‐device communication underlaying sectored cellular network

In this paper, a novel reinforcement learning (RL) approach with cell sectoring is proposed to solve the channel and power allocation issue for a device‐to‐device (D2D)‐enabled cellular network when the prior traffic information is not known to the base station (BS). Further, this paper explores an optimal policy for resource and power allocation between users intending to maximize the sum‐rate of the overall system. Since the behavior of wireless channel and traffic request of users in the system is stochastic in nature, the dynamic property of the environment allows us to employ an actor‐critic RL technique to learn the best policy through continuous interaction with the surrounding. The proposed work comprises of four phases: cell splitting, clustering, queuing model, and channel allocation and power allocation simultaneously using an actor‐critic RL. The implementation of cell splitting with novel clustering technique increases the network coverage, reduces co‐channel cell interference, and minimizes the transmission power of nodes, whereas the queuing model solves the issue of waiting time for users in a priority‐based data transmission. With the help of continuous state‐action space, the actor‐critic RL algorithm based on policy gradient improves the overall system sum‐rate as well as the D2D throughput. The actor adopts a parameter‐based stochastic policy for giving continuous action while the critic estimates the policy and criticizes the actor for the action. This reduces the high variance of the policy gradient. Through numerical simulations, the benefit of our resource sharing scheme over other existing traditional scheme is verified.     

Affinity propagation‐based interference‐free clustering for wireless sensor networks

Wireless sensor networks (WSNs), eg, industrial WSNs, require reliability and real‐time communication. Clustering technique together with schedule‐based access can provide the benefits, such as energy saving, reliability, and timeliness. However, integrating above two technologies into WSNs requires sophistical time slot allocation mechanism. To simplify the time slot allocation, the paper proposes a distributed interference‐free clustering algorithm for WSNs. The algorithm is inspired by affinity propagation (AP) clustering algorithm. By adapting and improving the original AP algorithm, the proposed clustering algorithm aims to jointly optimize energy saving and coverage issues while providing interference free between clusters. The performance analysis demonstrates that it can achieve high receiving rate (reliability), low delay (real time), and low‐energy consumption.     

Nonparametric Bayesian dictionary learning algorithm based on structural similarity

Though nonparametric Bayesian methods possesses significant superiority with respect to traditional comprehensive dictionary learning methods,there is room for improvement of this method as it needs more consideration over the structural similarity and variability of images.To solve this problem,a nonparametric Bayesian dictionary learning algorithm based on structural similarity was proposed.The algorithm improved the structural representing ability of dictionaries by clustering images according to their non-local structural similarity and introducing block structure into sparse representing of images.Denoising and compressed sensing experiments showed that the proposed algorithm performs better than several current popular unsupervised dictionary learning algorithms.     

基于耦合特征空间下改进字典学习的图像超分辨率重建

针对目前基于字典学习的图像超分辨率重建效果欠佳或字典训练时间过长的问题,本文提出了一种耦合特征空间下改进字典学习的图像超分辨率重建算法.该算法首先利用高斯混合模型聚类算法对训练图像块进行聚类,然后使用更改字典更新方式的改进KSVD字典学习算法来快速获得高、低分辨率特征空间下字典对和映射矩阵.重建时根据测试样本与各个类别的似然概率自适应地选择最匹配的字典对和映射矩阵进行高分辨率重建.最后利用图像非局部相似性,将其与迭代反向投影算法相结合对重建后的图像进行后处理获得最佳重建效果.实验结果表明了本文方法的有效性.     

Frequency resource allocation strategy with QoS support in hybrid cellular and Device‐to‐Device networks

Hybrid networks, comprising a conventional cellular network overlaid with Device‐to‐Device (D2D), offer efficient way to improve system throughput. In this paper, a novel orthogonal frequency‐division multiple access channel‐assignment method is proposed for hybrid network. The proposed approach is optimal in terms of throughput and is subjected to a sensible QoS requirement, which guarantees that macrocell and D2D achieve a prescribed data rate and outage probability, respectively. Our solution consists of two phases. In the first phase, the minimum sub‐channels are allocated to the macrocell to satisfy their data rate requirements. This problem is mapped to the 0‐1 Knapsack Problem and solved by integer programming based Lagrange dual approach. In the second phase, the redundant sub‐channels are allocated to D2D pairs to maximize the throughput of D2D networks. An interference management scheme is proposed to guarantee the outage probability of D2D communications. A cluster is taken as the unit for frequency reuse among D2D pairs. The problem of clustering is mapped to the MAX k‐CUT problem in graph theory and is solved by graph‐based heuristic algorithm. Extensive simulations demonstrate the superior performance of the proposed solution compared with the existing scheme. Copyright © 2014 John Wiley & Sons, Ltd.     

Energy‐efficient resource allocation for lifetime maximization in M2M networks

Machine‐to‐machine (M2M) communications is one of the major enabling technologies for the realization of the Internet of Things (IoT). Most machine‐type communication devices (MTCDs) are battery powered, and the battery lifetime of these devices significantly affects the overall performance of the network and the quality of service (QoS) of the M2M applications. This paper proposes a lifetime‐aware resource allocation algorithm as a convex optimization problem for M2M communications in the uplink of a single carrier frequency division multiple access (SC‐FDMA)‐based heterogeneous network. A K‐means clustering is introduced to reduce energy consumption in the network and mitigate interference from MTCDs in neighbouring clusters. The maximum number of clusters is determined using the elbow method. The lifetime maximization problem is formulated as a joint power and resource block maximization problem, which is then solved using Lagrangian dual method. Finally, numerical simulations in MATLAB are performed to evaluate the performance of the proposed algorithm, and the results are compared to existing heuristic algorithm and inbuilt MATLAB optimal algorithm. The simulation results show that the proposed algorithm outperforms the heuristic algorithm and closely model the optimal algorithm with an acceptable level of complexity. The proposed algorithm offers significant improvements in the energy efficiency and network lifetime, as well as a faster convergence and lower computational complexity.     

Nelder‐Mead–based power optimization for secrecy enhancement in amplify‐and‐forward cooperative relay networks

Cooperative communication based on relaying nodes has been considered as a promising technique to increase the physical layer security (PLS) performance in wireless communications. In this paper, an optimal power allocation (OPA) scheme based on Nelder‐Mead (NM) algorithm is proposed for improving the secrecy rate of amplify‐and‐forward (AF) cooperative relay networks employing cooperative jamming (CJ) scheme. The proposed hybrid jamming scheme allows the source and selected relay to transmit the jamming signal along with the information to confound the eavesdropper. The path selection probability of ant colony optimization (ACO) algorithm is used for selecting the relay for transmission. The performance based on secrecy rate is evaluated for “n” trusted relays distributed dispersedly between the source and destination. Gradient‐based optimization and three‐dimensional exhaustive search methods are used as benchmark schemes for comparison of the proposed power optimization algorithm. The secrecy performance is also compared with conventional AF scheme and CJ scheme without power optimization (EPA). The impact of single and multiple relays on secrecy performance is also evaluated. Numerical results reveal that, compared with the gradient method and exhaustive search algorithm, the proposed power allocation strategy achieves optimal performance. Also, the derived OPA results show a significantly higher secrecy rate than the EPA strategy for both CJ and AF schemes.     

Online CQI‐based optimization using k‐means and machine learning approach under sparse system knowledge

Modern cellular mobile networks are becoming more complicated and too expensive in terms of deployment, operation, and maintenance. Traffic demand in cellular networks typically experiences spatio‐temporal variations because of users' mobility and usage behaviour, which lead some of the cells to get overloaded without fully utilizing network capacity. To tackle these challenges, nowadays, self‐organizing networks (SONs) become an essential feature. This paper offers the development of an optimization framework for SONs based on channel quality indicator (CQI) and loading condition without detail knowledge of the network environment. Since the electrical tilt plays a key role in optimizing both coverage and capacity, the main motive is to ensure efficient network operation by electrical tilt‐based radio frequency (RF) performance optimization using a machine learning approach. This novel methodology shows two‐step optimization algorithms: (a) cluster formation based on handover success rate using k‐means algorithm and (b) reinforcement learning‐based optimization. Simulation and field trial shows that the proposed approach provides better results than the conventional method of prediction using genetic algorithm (GA) and other online approaches.     

Clustering‐based resource discovery on Internet‐of‐Things

Resource discovery on Internet‐of‐Things paradigm is an eminent challenge due to data‐specific activities with respect to foraging and sense‐making loops. The prerequisite to deal with the challenge is to process and analyze the data that require resources to be indexed, ranked, and stored in an efficient manner. A novel clustering technique is proposed to resolve the specified challenge. The technique, namely, iterative k‐means clustering algorithm, targets concrete cluster formation using similarity coefficients of vector space model and performs efficient search against matching criteria with respect to complexity. It is simulated on MATLAB, and the obtained results are compared with fuzzy k‐means and fuzzy c‐means clustering algorithm with similarity coefficients of vector space model against exponential increase in the number of resources.     

An adjusted K‐medoids clustering algorithm for effective stability in vehicular ad hoc networks

Recently, the routing problem in vehicular ad hoc networks is one of the most vital research. Despite the variety of the proposed approaches and the development of communications technologies, the routing problem in VANET suffers from the high speed of vehicles and the repetitive failures in communications. In this paper, we adjusted the well‐known K‐medoids clustering algorithm to improve the network stability and to increase the lifetime of all established links. First, the number of clusters and the initial cluster heads will not be selected randomly as usual, but based on mathematical formula considering the environment size and the available transmission ranges. Then the assignment of nodes to clusters in both k‐medoids phases will be carried out according to several metrics including direction, relative speed, and proximity. To the best of our knowledge, our proposed model is the first that introduces the new metric named “node disconnection frequency.” This metric prevents nodes with volatile and suspicious behavior to be elected as a new CH. This screening ensures that the new CH retains its property as long as possible and thus increases the network stability. Empirical results confirm that in addition to the convergence speed that characterizes our adjusted K‐medoids clustering algorithm (AKCA), the proposed model achieves more stability and robustness when compared with most recent approaches designed for the same objective.     

基于压缩感知与结构自相似性的遥感图像超分辨率方法

本文提出了一种基于压缩感知、结构自相似性和字典学习的遥感图像超分辨率方法,其基本思路是建立能够稀疏表示原始高分辨率图像块的字典。实现超分辨率所必需的附加信息来源于遥感图像中广泛存在的自相似结构,该信息可在压缩感知框架下通过字典学习而得到。这里,本文采用K-SVD方法构建字典、并采用OMP方法获取用于稀疏表达的相关系数。与现有基于样本的超分辨率方法的最大不同在于,本文方法仅使用了低分辨率图像及其插值图像,而不需要使用其它高分辨率图像。另外,为了评价方法的效果,本文还引入了一个衡量图像结构自相似性程度的新型指标SSSIM。对比实验结果表明,本文方法具有更好的超分辨率重构效果和运算效率,并且SSSIM指标与超分辨率重构效果具有较强的相关性。      

Golden codeword–based modulation schemes for single‐input multiple‐output systems

The Golden code has full rate and full diversity. The Golden codeword matrix contains two pairs of super symbols. Based on one pair of super symbols, two modulation schemes, Golden codeword–based M‐ary quadrature amplitude modulation (GC‐MQAM) and component‐interleaved GC‐MQAM (CI‐GC‐MQAM), are proposed for single‐input multiple‐output (SIMO) systems. Since the complexities of the maximum likelihood detection for the proposed GC‐MQAM and CI‐GC‐MQAM are proportional to O(M²) and O(M⁴), respectively, low complexity detection schemes for the proposed GC‐MQAM and CI‐GC‐MQAM are further proposed. In addition, the theoretical average bit error probabilities (ABEPs) for the proposed GC‐MQAM and CI‐GC‐MQAM are derived. The derived ABEPs are validated through Monte Carlo simulations. Simulation and theoretical results show that the proposed GC‐MQAM can achieve the error performance of signal space diversity. Simulation and theoretical results further show that the proposed CI‐GC‐16QAM, ‐64QAM, and ‐256QAM with three receive antennas can achieve approximately 2.2, 2.0, and 2.1 dB gain at a bit error rate of 4 × 10^?6 compared with GC‐16QAM, ‐64QAM, and ‐256QAM, respectively.     

Power allocation scheme based on sum capacity maximization for signal‐to‐leakage‐and‐noise ratio precoded multiuser multiple‐input single‐output downlink

This paper proposes a power allocation scheme to maximize the sum capacity of all users for signal‐to‐leakage‐and‐noise ratio (SLNR) precoded multiuser multiple‐input single‐output downlink. The designed scheme tries to explore the effect of the power allocation for the SLNR precoded multiuser multiple‐input single‐output system on sum capacity performance. This power allocation problem can be formulated as an optimization problem. With high signal‐to‐interference‐plus‐noise ratio assumption, it can be converted into a convex optimization problem through the geometric programming and hence can be solved efficiently. Because the assumption of high signal‐to‐interference‐plus‐noise ratio cannot be always satisfied in practice, we design a globally optimal solution algorithm based on a combination of branch and bound framework and convex relaxation techniques. Theoretically, the proposed scheme can provide optimal power allocation in sum capacity maximization. Then, we further propose a judgement‐decision algorithm to achieve a trade‐off between the optimality and computational complexity. The simulation results also show that, with the proposed scheme, the sum capacity of all the users can be improved compared with three existing power allocation schemes. Meanwhile, some meaningful conclusions about the effect of the further power allocation based on the SLNR precoding have been also acquired. The performance improvement of the maximum sum capacity power allocation scheme relates to the transmit antenna number and embodies different variation trends in allusion to the different equipped transmit antenna number as the signal‐to‐noise ratio (SNR) changes.Copyright © 2013 John Wiley & Sons, Ltd.     

自适应聚类的全耦合稀疏学习算法

在图像处理领域,基于稀疏表示理论的图像超分辨力算法、高低分辨力字典与稀疏编码之间的映射关系是其中的2个关键环节。由于丰富多样的图像类型,单一字典并不能很好地表示图像。而在稀疏编码之间的映射关系上,严格相等的约束关系也限制了图像重建的效果。针对上述两个方面,采用包容性更强的多个字典与约束条件更为宽松的全耦合稀疏关系进行图像的超分辨力重建。在图像非局部自相似性的基础上,进行多次自适应聚类;挑选出最优的聚类,通过全耦合稀疏学习的图像超分辨力算法,得到多个字典;最后,对输入的低分辨力图像进行分类重建,得到高分辨力图片。实验结果表明,在图像Leaves,Barbara,Room上,本文的聚类算法比原全耦合稀疏学习算法在峰值信噪比(PSNR)上分别提升了0.51 dB,0.21 dB,0.15 dB。     

特征聚类的局部敏感稀疏图像修复

针对图像修复过程中单一的字典迭代时间长、适应性差、修复效果不理想的缺点,提出了一种结合图像特征聚类与字典学习的改进的图像修复方式。首先破损的图像被分割成小块,并产生索引矩阵。然后使用控制核回归权值算法,对其进行图像聚类。通过对图像内在结构与未破损区域信息的挖掘,分割的图像块根据SKRW的相似性进行了分类。之后针对不同类型结构的图像,通过自适应局部明感字典学习的方式,获取每类字典的过完备字典。然后,通过构建自适应局部配适器,提高字典更新的收敛速度与稀疏字典的适应性。因为是通过多个字典匹配不同结构的图像,因此图像的稀疏表示更为准确。各个字典在达到收敛之前不断进行更新,而图像的稀疏因子也会随着改变。在对破损区域进行补丁更换之后,实现了对破损图像的修复。实验结果表明,该算法相较于目前的修复算法,视觉效果和客观评价上更好,且所需的修复时间更短。