Design and Implementation of a New Local Alignment Algorithm for Multilayer Networks

Network alignment (NA) is a popular research field that aims to develop algorithms for comparing networks. Applications of network alignment span many fields, from biology to social network analysis. NA comes in two forms: global network alignment (GNA), which aims to find a global similarity, and LNA, which aims to find local regions of similarity. Recently, there has been an increasing interest in introducing complex network models such as multilayer networks. Multilayer networks are common in many application scenarios, such as modelling of relations among people in a social network or representing the interplay of different molecules in a cell or different cells in the brain. Consequently, the need to introduce algorithms for the comparison of such multilayer networks, i.e., local network alignment, arises. Existing algorithms for LNA do not perform well on multilayer networks since they cannot consider inter-layer edges. Thus, we propose local alignment of multilayer networks (MultiLoAl), a novel algorithm for the local alignment of multilayer networks. We define the local alignment of multilayer networks and propose a heuristic for solving it. We present an extensive assessment indicating the strength of the algorithm. Furthermore, we implemented a synthetic multilayer network generator to build the data for the algorithm’s evaluation.     

Evolution of a protein domain interaction network

In this paper, we attempt to understand complex network evolution from the underlying evolutionary relationship between biological organisms. Firstly, we construct a Pfam domain interaction network for each of the 470 completely sequenced organisms, and therefore each organism is correlated with a specific Pfam domain interaction network; secondly, we infer the evolutionary relationship of these organisms with the nearest neighbour joining method; thirdly, we use the evolutionary relationship between organisms constructed in the second step as the evolutionary course of the Pfam domain interaction network constructed in the first step. This analysis of the evolutionary course shows: (i) there is a conserved sub-network structure in network evolution; in this sub-network, nodes with lower degree prefer to maintain their connectivity invariant, and hubs tend to maintain their role as a hub is attached preferentially to new added nodes; (ii) few nodes are conserved as hubs; most of the other nodes are conserved as one with very low degree; (iii) in the course of network evolution, new nodes are added to the network either individually in most cases or as clusters with relative high clustering coefficients in a very few cases.     

CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling

Heterogeneous information network (HIN) embedding is an important tool for tasks such as node classification, community detection, and recommendation. It aims to find the representations of nodes that preserve the proximity between entities of different nature. A family of approaches that are widely adopted applies random walk to generate a sequence of heterogeneous contexts, from which, the embedding is learned. However, due to the multipartite graph structure of HIN, hub nodes tend to be over-represented to their context in the sampled sequence, giving rise to imbalanced samples of the network. Here, we propose a new embedding method: CoarSAS2hvec. The self-avoiding short sequence sampling with the HIN coarsening procedure (CoarSAS) is utilized to better collect the rich information in HIN. An optimized loss function is used to improve the performance of the HIN structure embedding. CoarSAS2hvec outperforms nine other methods in node classification and community detection on four real-world data sets. Using entropy as a measure of the amount of information, we confirm that CoarSAS catches richer information of the network compared with that through other methods. Hence, the traditional loss function applied to samples by CoarSAS can also yield improved results. Our work addresses a limitation of the random-walk-based HIN embedding that has not been emphasized before, which can shed light on a range of problems in HIN analyses.     

基于K-阶结构熵的网络异构性研究

结构熵可以考察复杂网络的异构性.为了弥补传统结构熵在综合刻画网络全局以及局部特性能力上的不足,本文依据网络节点在K步内可达的节点总数定义了K-阶结构熵,可从结构熵随K值的变化规律、最大K值下的结构熵以及网络能够达到的最小结构熵三个方面来评价网络的异构性.利用K-阶结构熵对规则网络、随机网络、Watts-Strogatz小世界网络、Barabási_-Albert无标度网络以及星型网络进行了理论研究与仿真实验,结果表明上述网络的异构性依次增强.其中K-阶结构熵能够较好地依据小世界属性来刻画小世界网络的异构性,且对星型网络异构性随其规模演化规律的解释也更为合理.此外, K-阶结构熵认为在规则结构外新增孤立节点的网络的异构性弱于未添加孤立节点的规则结构,但强于同节点数的规则网络.本文利用美国西部电网进一步论证了K-阶结构熵的有效性.     

基于粒子群优化算法的测光红移回归预测

星系的红移在天文研究中极其重要,星系测光红移的预测对研究宇宙大尺度结构及演变有着重要的研究意义。利用斯隆巡天项目发布的SDSS DR13的150 000个星系的测光及光谱数据进行分析,首先根据颜色特征并基于聚类的方法对星系进行分类,由分类结果可知早型星系的占比较大。对比了三种不同的机器学习算法对早型星系进行测光红移回归预测实验,并找出最优的方法。实验中将星系样本中u, g, r, i, z五个波段的测光值以及两两做差得到的10个颜色特征作为输入数据,首先构建BP网络,使用BP算法对星系的测光红移进行回归预测;然后利用遗传算法（GA）优化BP网络各层参数,将优化后的GA-BP算法应用于早型星系的回归预测试验中。考虑到GA算法的复杂操作会影响预测效率,并且粒子群算法（PSO）不仅稳定性高且操作简单,因此将粒子群算法应用到星系样本中早型星系的测光红移回归预测实验中,进而采用粒子群算法优化BP网络（PSO-BP）。实验中将光谱红移作为期望值,采用均方差（MSE）作为误差分析指标来评判三种算法的精度,将PSO-BP回归预测结果与BP网络模型、GA-BP网络模型进行比较。由实验结果可知,BP网络的MSE值为0.001 92,GA-BP网络的MSE值0.001 728,PSO-BP网络的MSE值为0.001 708。实验结果表明,所用到的PSO-BP优化模型在精度上优于BP神经网络模型和GA-BP神经网络模型,分别提高了11.1%和1.2%;在效率上优于传统的K近邻（KNN）测光红移估计算法, 克服了KNN算法中遍历所有数据样本进行训练的缺点并且其泛化性能优于其它BP网络优化模型。     

Efficient Network Dismantling via Node Explosive Percolation

The network dismantling problem asks the minimum separate node set of a graph whose removal will break the graph into connected components with the size not larger than the one percentage of the original graph.This problem has attracted much attention recently and a lot of algorithms have been proposed. However, most of the network dismantling algorithms mainly focus on which nodes are included in the minimum separate set but overlook how to order them for removal, which will lead to low general efficiency during the dismantling process. In this paper,we reformulate the network dismantling problem by taking the order of nodes' removal into consideration. An efficient dismantling sequence will break the network quickly during the dismantling processes. We take the belief-propagation guided decimation(BPD) dismantling algorithm, a state-of-the-art algorithm, as an example, and employ the node explosive percolation(NEP) algorithm to reorder the early part of the dismantling sequence given by the BPD. The proposed method is denoted as the NEP-BPD algorithm(NBA) here. The numerical results on Erd¨os-R′enyi graphs,random-regular graphs, scale-free graphs, and some real networks show the high general efficiency of NBA during the entire dismantling process. In addition, numerical computations on random graph ensembles with the size from 2~(10) to2~(19) exhibit that the NBA is in the same complexity class with the BPD algorithm. It is clear that the NEP method we used to improve the general efficiency could also be applied to other dismantling algorithms, such as Min-Sum algorithm,equal graph partitioning algorithm and so on.     

多种确定性广义Farey组织的网络金字塔

提出复杂网络的另一类家族的确定性金字塔,它是由确定性的不同连接方式构造的广义Farey组织的网络金字塔(GFONP),理论推导了该类金字塔网络的拓扑性质及其转变特点,发现三种GFONP网络的度分布都服从指数分布形式,随着时间t的不断演化网络金字塔群聚系数不断减小并趋于一个常数,同时网络金字塔从异配向同配转变,度-度相关系数也趋于一个正的常数.结果显示这类型网络的新特性具有应用潜力.     

Enhancing network lifespan in wireless sensor networks using deep learning based Graph Neural Network

Inadequate energy of sensors is one of the most significant challenges in the development of a reliable wireless sensor network (WSN) that can withstand the demands of growing WSN applications. Implementing a sleep-wake scheduling scheme while assigning data collection and sensing chores to a dominant group of awake sensors while all other nodes are in a sleep state seems to be a potential way for preserving the energy of these sensor nodes. When the starting energy of the nodes changes from one node to another, this issue becomes more difficult to solve. The notion of a dominant set-in graph has been used in a variety of situations. The search for the smallest dominant set in a big graph might be time-consuming. Specifically, we address two issues: first, identifying the smallest possible dominant set, and second, extending the network lifespan by saving the energy of the sensors. To overcome the first problem, we design and develop a deep learning-based Graph Neural Network (DL-GNN). The GNN training method and back-propagation approach were used to train a GNN consisting of three networks such as transition network, bias network, and output network, to determine the minimal dominant set in the created graph. As a second step, we proposed a hybrid fixed-variant search (HFVS) method that considers minimal dominant sets as input and improves overall network lifespan by swapping nodes of minimal dominating sets. We prepared simulated networks with various network configurations and modeled different WSNs as undirected graphs. To get better convergence, the different values of state vector dimensions of the input vectors are investigated. When the state vector dimension is 3 or 4, minimum dominant set is recognized with high accuracy. The paper also presents comparative analyses between the proposed HFVS algorithm and other existing algorithms for extending network lifespan and discusses the trade-offs that exist between them. Lifespan of wireless sensor network, which is based on the dominant set method, is greatly increased by the techniques we have proposed.     

Elman回归神经网络同时定量测定三种酚类化合物

应用Elman回归神经网络(ERNN)对光谱严重重叠的对-硝基苯酚,邻-硝基苯酚和2,4-二硝基苯酚体系的同时定量测定进行了研究,并与多变量线性回归(MLR)法作了比较。编制了PERNN和PMLR程序执行有关计算。通过最佳化确定了Elman回归网络的结构和参数。ERNN和MLR法所有组分的相对预测标准偏差(RSEP)分别为3.1%和2 027.3%,实验结果显示对于分辨严重重叠光谱本法是成功的。ERNN法是解决局部最小和提高收敛速度的一种有价值的工具,亦可用于分析全光谱而不只限于选取少数特征值。本法为不经预先分离同时测定严重重叠的分子光谱体系提供了新的途径。     

An Improved Residual Network for Pork Freshness Detection Using Near-Infrared Spectroscopy

Effective and rapid assessment of pork freshness is significant for monitoring pork quality. However, a traditional sensory evaluation method is subjective and physicochemical analysis is time-consuming. In this study, the near-infrared spectroscopy (NIRS) technique, a fast and non-destructive analysis method, is employed to determine pork freshness. Considering that commonly used statistical modeling methods require preprocessing data for satisfactory performance, this paper presents a one-dimensional squeeze-and-excitation residual network (1D-SE-ResNet) to construct the complex relationship between pork freshness and NIRS. The developed model enhances the one-dimensional residual network (1D-ResNet) with squeeze-and-excitation (SE) blocks. As a deep learning model, the proposed method is capable of extracting features from the input spectra automatically and can be used as an end-to-end model to simplify the modeling process. A comparison between the proposed method and five popular classification models indicates that the 1D-SE-ResNet achieves the best performance, with a classification accuracy of 93.72%. The research demonstrates that the NIRS analysis technique based on deep learning provides a promising tool for pork freshness detection and therefore is helpful for ensuring food safety.     

Tomography of functional organization in protein-protein interaction network

In recent years, after high throughput PPI data was available, studies have focused on unraveling how proteins organize their functionality from architecture of the PPI network. We examine the functional organization of a PPI network by dividing the network into layered structure around a protein according to shortest path length. We proposed an index, functional correlation, to assess the functional closeness of a specific protein with its l layer neighbors, i.e. proteins having l shortest path length from the center protein. Our results showed that functional correlation decays exponentially with the number of layers within a characteristic length l_c, and it becomes uncorrelated outside such a characteristic length. A simple model based on functional unit structure was proposed to explain this exponential decay of functional correlation.     

Nonlinear signal transduction network with multistate

Signal transduction is an important and basic mechanism to cell life activities. The stochastic state transition of receptor induces the release of signaling molecular, which triggers the state transition of other receptors. It constructs a nonlinear sigaling network, and leads to robust switchlike properties which are critical to biological function. Network architectures and state transitions of receptor affect the performance of this biological network. In this work, we perform a study of nonlinear signaling on biological polymorphic network by analyzing network dynamics of the Ca²⁺-induced Ca²⁺ release (CICR) mechanism, where fast and slow processes are involved and the receptor has four conformational states. Three types of networks, Erdös-Rényi (ER) network, Watts-Strogatz (WS) network, and BaraBási-Albert (BA) network, are considered with different parameters. The dynamics of the biological networks exhibit different patterns at different time scales. At short time scale, the second open state is essential to reproduce the quasi-bistable regime, which emerges at a critical strength of connection for all three states involved in the fast processes and disappears at another critical point. The pattern at short time scale is not sensitive to the network architecture. At long time scale, only monostable regime is observed, and difference of network architectures affects the results more seriously. Our finding identifies features of nonlinear signaling networks with multistate that may underlie their biological function.     

An enhanced non-uniformity correction algorithm for IRFPA based on neural network

Influenced by detector materials’ non-uniformity, growth and etching techniques, etc., every detector’s responsivity of infrared focal plane arrays (IRFPA) is different, which results in non-uniformity of IRFPA. And non-uniformity of IRFPA generates fixed pattern noises (FPN) that are superposed on infrared image. And it may degrade the infrared image quality, which greatly limits the application of IRFPA. Non-uniformity correction (NUC) is an important technique for IRFPA. The traditional non-uniformity correction algorithm based on neural network and its modified algorithms are analyzed in this paper. And a new improved non-uniformity correction algorithm based on neural network is proposed in this paper. In this algorithm, the desired image is estimated by using three successive images in an infrared sequence. And blurring effect caused by motion is avoided by applying implicit motion detection and edge detection. So the estimation image is closer to real image than the estimation image estimated by other algorithms, which results in fast convergence speed of correction parameters. A comparison is made to these algorithms in this paper. And experimental results show that the algorithm proposed in this paper can correct the non-uniformity of IRFPA effectively and it prevails over other algorithms based on neural network.     

A Path-Based Distribution Measure for Network Comparison

As network data increases, it is more common than ever for researchers to analyze a set of networks rather than a single network and measure the difference between networks by developing a number of network comparison methods. Network comparison is able to quantify dissimilarity between networks by comparing the structural topological difference of networks. Here, we propose a kind of measures for network comparison based on the shortest path distribution combined with node centrality, capturing the global topological difference with local features. Based on the characterized path distributions, we define and compare network distance between networks to measure how dissimilar the two networks are, and the network entropy to characterize a typical network system. We find that the network distance is able to discriminate networks generated by different models. Combining more information on end nodes along a path can further amplify the dissimilarity of networks. The network entropy is able to detect tipping points in the evolution of synthetic networks. Extensive numerical simulations reveal the effectivity of the proposed measure in network reduction of multilayer networks, and identification of typical system states in temporal networks as well.     

How to Effectively Collect and Process Network Data for Intrusion Detection?

The number of security breaches in the cyberspace is on the rise. This threat is met with intensive work in the intrusion detection research community. To keep the defensive mechanisms up to date and relevant, realistic network traffic datasets are needed. The use of flow-based data for machine-learning-based network intrusion detection is a promising direction for intrusion detection systems. However, many contemporary benchmark datasets do not contain features that are usable in the wild. The main contribution of this work is to cover the research gap related to identifying and investigating valuable features in the NetFlow schema that allow for effective, machine-learning-based network intrusion detection in the real world. To achieve this goal, several feature selection techniques have been applied on five flow-based network intrusion detection datasets, establishing an informative flow-based feature set. The authors’ experience with the deployment of this kind of system shows that to close the research-to-market gap, and to perform actual real-world application of machine-learning-based intrusion detection, a set of labeled data from the end-user has to be collected. This research aims at establishing the appropriate, minimal amount of data that is sufficient to effectively train machine learning algorithms in intrusion detection. The results show that a set of 10 features and a small amount of data is enough for the final model to perform very well.     

小波软阈值径向基神经网络同时测定多组分混合物

建立了一种小波软阈值径向基函数神经网络 (STWRBFN)方法 ,同时定量分析了多组分混合物。结合小波软阈值法和径向基函数神经网络改进了回归质量。通过最佳化 ,选择了小波函数、小波分解水平(L)、阈值法类型和网络的伸展参数 (σ)。两个程序PSTWRBFN和PRBFN被设计执行STWRBFN和径向基函数神经网络 (RBFN)计算。实验结果表明STWRBFN是成功的且优于RBFN法 ,和经典的多变量线性回归(MLR)方法相比较 ,这两个方法更为有效     

Costs of Fiber-to-the-Home Passive Optical Network Unbundling

Abstract

This work considers different unbundling options for local loop unbundling in order to provide multi-operator access and consider the economical impact for the fiber-to-the-home next-generation access entrants to deploy such alternatives. It is shown that deploying wavelength division multiplexing networks is an efficient strategy to perform local loop unbundling while upgrading the gigabit passive optical network for the new era where high bandwidths are necessary for satisfying customer demand. In areas with a high population density, wavelength division multiplexing techniques are the most suitable for entrant operators to access the incumbent's network and provide service.     

Measurements of ultrasonic phase velocities and attenuation of slow waves in cellular aluminum foams as cancellous bone-mimicking phantoms

The water-saturated aluminum foams with an open network of interconnected ligaments were investigated by ultrasonic transmission technique for the suitability as cancellous bone-mimicking phantoms. The phase velocities and attenuation of nine samples covering three pores per inch (5, 10, and 20 PPI) and three aluminum volume fractions (5, 8, and 12% AVF) were measured over a frequency range of 0.7-1.3 MHz. The ligament thickness and pore sizes of the phantoms and low-density human cancellous bones are similar. A strong slow wave and a weak fast wave are observed for all samples while the latter is not visible without significant amplification (100x). This study reports the characteristics of slow wave, whose speeds are less than the sound speed of the saturating water and decrease mildly with AVF and PPI with an average 1469 m/s. Seven out of nine samples show positive dispersion and the rest show minor negative dispersion. Attenuation increases with AVF, PPI, and frequency except for the 20 PPI samples, which exhibit non-increasing attenuation level with fluctuations due to scattering. The phase velocities agree with Biot's porous medium theory. The RMSE is 16.0 m/s (1%) at n = 1.5. Below and above this value, the RMSE decreases mildly and rises sharply, respectively.     

基于深度递归级联卷积神经网络的并行磁共振成像方法

快速磁共振成像是磁共振研究领域重要的课题之一.随着大数据和深度学习的兴起,神经网络成为快速磁共振技术的重要方法.然而网络性能表现和网络参数量之间较难取得平衡,且对于多通道数据重建的并行成像问题,相关研究较少.本文构建了一种深度递归级联卷积神经网络结构,用于处理并行成像问题.这种网络结构在减少网络参数量的同时,能够尽可能地提高网络的表达能力,提高网络重建的精确度.实验结果表明,相较于传统并行成像方法,通过训练好的神经网络对欠采样磁共振数据进行重建,可以得到更准确的重建结果,且重建时间大大缩短.