用于光信息处理的WTA电子网络的实现及其特性分析

给出了一种光信号处理用ＷＴＡ电子网络的实现方法，测试了网络的灵敏度，并分析了可能对其产生影响的因素，制作 了３２单元的ＷＴＡ网络器件，网络能在几百微秒的时间内找出输入最大者，分辨精度为１ｍＶ。     

交通运输网络的复杂性研究

依据网络拓扑结构特征划分，人们日常生活中所接触到的实际网络有完全规则网络、完全随机网络、小世界网络和无标度网络，其中，小世界网络或无标度网络通常被认为是交通运运输网络，在各种交通更渠道之中，系统复杂性是交通运输网络发展性的根本原因。现如今，基于统计物理学的交通运输网络的复杂性研究多为拓扑化的理论分析或数据建模，与实际网络结构特征及动力学机理仍存在较大差距。本文笔者阐述了交通网络复杂性研究的实际意义，并结合我国目前的交通运输网状况和国外平均水平，介绍了相关的基本概念，针对相关问题提出了可靠的对策，为交通部门管理交通运输网提供了一定程度上的理论支持。     

网络言论的舆论影响与引导

随着信息技术的进步，日益发展的网络正逐步改变着传统的传播模式和人们的交往方式，网络言论在当今社会中扮演着越来越重要的角色.本文对网络言论的定义进行界定，介绍了网络媒体吉论的传播形态。并预测网络言论的发展趋势，通过分析网络言论对政府、公众舆论、传统媒体所带来的影响、以及网络言论存在的各种问题，探讨了网络言论的舆论引导原则。提出了网络言论管理手段。     

网络中知识流的形成及速率研究分析

知识流理论的普及，网络技术的发展，为网络知识流的深入研究提供了理论与方法支撑。本文从知识的特征出发，探索网络知识流的实质及作用机理，分析网络活动中知识流形成和影响因素。定义了知识流速率，旨在揭示网络知识流的本质，探索网络知识流研究的新思路。     

浅析网络故障的诊断与解决方法

网络故障极为普遍，网络故障的种类也多种多样，要在网络出现故障时及时对出现故障的网络进行维护，以最快的速度恢复网络的正常运行，掌握一套行之有效的网络维护理论、方法和技术是关键。就网络中常见故障进行了分类，并对各种常见网络故障提出了相应的解决方法。     

基于流量和时延的网络性能测量系统的研究

提出了一种间接测量网络吞吐率的新方法，建立了基于流量和时延的网络性能分析模型，基于这个模型对网络性能测量方法进行分析，设计并实现了一个基于流量和时延的网络性能测量系统，对网络性能进行了测量和分析。     

无线通讯网络的质量优化研究

随着移动用户的持续增加和移动业务的层出不穷，我国的GSM无线通讯网络运营与维护必将面临更多的网络优化内容，本文分高话务密度区GSM无线通讯网络优化、高层楼宇GSM无线通讯网络优以及高等院校GSM无线通讯网络优化三种情况，讨论GSM系统无线通讯网络的质量优化，分别剖析了三种不同环境的网络质量影响因素，并针对环境的特点给出了具体的网络优化方案，为移动通信服务的提升起到积极作用。     

基于椭球单元网络的旋转机械多故障同时性诊断

阐述了椭球单元（ＥｌｉｐｓｏｉｄａｌＵｎｉｔ）网络的原理及其结构，研究了网络权重初始化方法和网络的训练算法，借助这种高阶网络泛化的有界性，针对大型旋转机械多故障同时性诊断问题，构造了一种由多个子网络组成的分级诊断网络（ＨＤＡＮＮ）。测试结果表明：用基于椭球单元网络的ＨＤＡＮＮ网络分级诊断策略解决大规模故障诊断问题是合理有效的，且具有较高的诊断精度，可用于旋转机械工况实时监测和诊断场合。     

浅析计算机网络的测量

本文简要概述了测量网络性能的必要性及其主动式测量与被动式测量的基本方法，分析了测量工具的如用场合及其使用方法，根据具体的网络环境问题选择不同的测量工具，查找网络瓶颈，为提高网络性能提供依据。     

探讨如何将基于IP的电路交换网络与软交换核心网的相融合

现阶段有关3g互联网网络的发展方向应当集中表现在：将软交换技术与ip网络结构相融合的网络运行系统。因此，研究两者之间的融合技术以及融合方式是至关重要的。基于此，本文以3g网络的发展为研究对象，提出了一种建立在ip电路交换网络基础之上，实现3g核心网发展的基本方案，同时实现了电路交换网络与软交换核心网之间的充分融合，实践证实能够取得良好的效果。     

A tutorial survey of topics in wireless networking: Part I

In this two part paper, we provide a survey of recent and emerging topics in wireless networking. We view the area of wireless networking as dealing with problems of resource allocation so that the various connections that utilise the network achieve their desired performance objectives. In the first part of the paper, we first survey the area by providing a taxonomy of wireless networks as they have been deployed. Then, we provide a quick tutorial on the main issues in the wireless ‘physical’ layer, which is concerned with transporting bits over the radio frequency spectrum. Then, we proceed to discuss some resource allocation formulations in CDMA(code division multiple access) cellular networks and OFDMA(orthogonal frequency division multiple access) networks. In the second part of the paper, we first analyse random access wireless networks and pay special attention to 802·11 (Wi-Fi) networks.We then survey some topics in ad hoc multihop wireless networks, where we discuss arbitrary networks, as well as some theory of dense random networks. Finally, we provide an overview of the technical issues in the emerging area of wireless sensor networks.     

Networks and Rapid Technological Change: Novel Evidence from the Canadian Biotech Industry

Former studies on inter-organizational relationships have fallen short of properly identifying networks and elucidating factors that cause firms to entertain relationships in one type of network rather than another. This study adopts a methodology that is both empirical and comparative and thus constitutes a methodological departure from these previous studies. It also explicitly accounts for two structural characteristics of networks, namely, interactions and learning, to identify four types of networks, accumulative advantage networks, follow-the-trend networks, homophilies and multiconnectivity networks. It then investigates factors that cause firms to participate in any of these networks rather than another. Results show that even though networking is a common practice among biotech firms, most of them would rather keep this activity to a minimum. In addition, participation in these networks is found to vary according to the firm's size, stage of development and its sector of activity.     

On reaction network implementations of neural networks

This paper is concerned with the utilization of deterministically modelled chemical reaction networks for the implementation of (feed-forward) neural networks. We develop a general mathematical framework and prove that the ordinary differential equations (ODEs) associated with certain reaction network implementations of neural networks have desirable properties including (i) existence of unique positive fixed points that are smooth in the parameters of the model (necessary for gradient descent) and (ii) fast convergence to the fixed point regardless of initial condition (necessary for efficient implementation). We do so by first making a connection between neural networks and fixed points for systems of ODEs, and then by constructing reaction networks with the correct associated set of ODEs. We demonstrate the theory by constructing a reaction network that implements a neural network with a smoothed ReLU activation function, though we also demonstrate how to generalize the construction to allow for other activation functions (each with the desirable properties listed previously). As there are multiple types of ‘networks’ used in this paper, we also give a careful introduction to both reaction networks and neural networks, in order to disambiguate the overlapping vocabulary in the two settings and to clearly highlight the role of each network’s properties.     

A tutorial survey of topics in wireless networking: Part II

This is the second part of the survey of recent and emerging topics in wireless networking. We provide an overview of the area of wireless networking as that of dealing with problems of resource allocation so that the various connections that utilise the network achieve their desired performance objectives. In Part I we provided a taxonomy of wireless networks as they have been deployed. We then provided a quick survey of the main issues in the wireless ‘physical’ layer. We then discussed some resource allocation formulations in CDMA (code division multiple access) cellular networks and OFDMA (orthogonal frequency division multiple access) networks. In this part we begin with a discussion of random access wireless networks. We first provide an overview of the evolution of random access networks from Aloha to the currently popular 802·11 (Wi-Fi) networks. We then analyse the performance of the 802· 11 random access protocol. We briefly discuss the problem of optimal association of nodes to Wi-Fi access points. Next, we consider topics in ad hoc multihop wireless networks. We first discuss topology and cross layer control. For the latter, we describe the important maximum weight link scheduling algorithm. The connectivity and capacity of randomly deployed networks are then analysed. Finally, we provide an overview of the technical issues in the emerging area of wireless sensor networks.     

Topological properties of robust biological and computational networks

Network robustness is an important principle in biology and engineering. Previous studies of global networks have identified both redundancy and sparseness as topological properties used by robust networks. By focusing on molecular subnetworks, or modules, we show that module topology is tightly linked to the level of environmental variability (noise) the module expects to encounter. Modules internal to the cell that are less exposed to environmental noise are more connected and less robust than external modules. A similar design principle is used by several other biological networks. We propose a simple change to the evolutionary gene duplication model which gives rise to the rich range of module topologies observed within real networks. We apply these observations to evaluate and design communication networks that are specifically optimized for noisy or malicious environments. Combined, joint analysis of biological and computational networks leads to novel algorithms and insights benefiting both fields.     

Heterogeneous Hyperedge Convolutional Network

Graph convolutional networks (GCNs) have been developed as a general and powerful tool to handle various tasks related to graph data. However, current methods mainly consider homogeneous networks and ignore the rich semantics and multiple types of objects that are common in heterogeneous information networks (HINs). In this paper, we present a Heterogeneous Hyperedge Convolutional Network (HHCN), a novel graph convolutional network architecture that operates on HINs. Specifically, we extract the rich semantics by different metastructures and adopt hyperedge to model the interactions among metastructure-based neighbors. Due to the powerful information extraction capabilities of metastructure and hyperedge, HHCN has the flexibility to model the complex relationships in HINs by setting different combinations of metastructures and hyperedges. Moreover, a metastructure attention layer is also designed to allow each node to select the metastructures based on their importance and provide potential interpretability for graph analysis. As a result, HHCN can encode node features, metastructure-based semantics and hyperedge information simultaneously by aggregating features from metastructure-based neighbors in a hierarchical manner. We evaluate HHCN by applying it to the semi-supervised node classification task. Experimental results show that HHCN outperforms state-of-the-art graph embedding models and recently proposed graph convolutional network models.     

The diminishing role of hubs in dynamical processes on complex networks

It is notoriously difficult to predict the behaviour of a complex self-organizing system, where the interactions among dynamical units form a heterogeneous topology. Even if the dynamics of each microscopic unit is known, a real understanding of their contributions to the macroscopic system behaviour is still lacking. Here, we develop information-theoretical methods to distinguish the contribution of each individual unit to the collective out-of-equilibrium dynamics. We show that for a system of units connected by a network of interaction potentials with an arbitrary degree distribution, highly connected units have less impact on the system dynamics when compared with intermediately connected units. In an equilibrium setting, the hubs are often found to dictate the long-term behaviour. However, we find both analytically and experimentally that the instantaneous states of these units have a short-lasting effect on the state trajectory of the entire system. We present qualitative evidence of this phenomenon from empirical findings about a social network of product recommendations, a protein–protein interaction network and a neural network, suggesting that it might indeed be a widespread property in nature.     

Spectrum of genetic diversity and networks of clonal organisms.

Clonal reproduction characterizes a wide range of species including clonal plants in terrestrial and aquatic ecosystems, and clonal microbes such as bacteria and parasitic protozoa, with a key role in human health and ecosystem processes. Clonal organisms present a particular challenge in population genetics because, in addition to the possible existence of replicates of the same genotype in a given sample, some of the hypotheses and concepts underlying classical population genetics models are irreconcilable with clonality. The genetic structure and diversity of clonal populations were examined using a combination of new tools to analyse microsatellite data in the marine angiosperm Posidonia oceanica. These tools were based on examination of the frequency distribution of the genetic distance among ramets, termed the spectrum of genetic diversity (GDS), and of networks built on the basis of pairwise genetic distances among genets. Clonal growth and outcrossing are apparently dominant processes, whereas selfing and somatic mutations appear to be marginal, and the contribution of immigration seems to play a small role in adding genetic diversity to populations. The properties and topology of networks based on genetic distances showed a 'small-world' topology, characterized by a high degree of connectivity among nodes, and a substantial amount of substructure, revealing organization in subfamilies of closely related individuals. The combination of GDS and network tools proposed here helped in dissecting the influence of various evolutionary processes in shaping the intra-population genetic structure of the clonal organism investigated; these therefore represent promising analytical tools in population genetics.     

ATM网络中VCC的实时动态路由调度的神经网络新方法

针对神经网络因其强并行处理能力极适用于ＡＴＭ网络实时动态路由调度,提出了一种基于Ｈｏｐｆｉｅｌｄ神经网络的新路由算法,该算法网络拓扑及链路长度参数仅仅与神经元偏置电流有关,使得其硬件实现及逻辑控制非常简单。仿真结果证明了这种新路由算法的自适应性和鲁棒性。     

Influence Diffusion Model in Multiplex Networks

The problem of influence maximizing in social networks refers to obtaining a set of nodes of a specified size under a specific propagation model so that the aggregation of the node-set in the network has the greatest influence. Up to now, most of the research has tended to focus on monolayer network rather than on multiplex networks. But in the real world, most individuals usually exist in multiplex networks. Multiplex networks are substantially different as compared with those of a monolayer network. In this paper, we integrate the multi-relationship of agents in multiplex networks by considering the existing and relevant correlations in each layer of relationships and study the problem of unbalanced distribution between various relationships. Meanwhile, we measure the distribution across the network by the similarity of the links in the different relationship layers and establish a unified propagation model. After that, place on the established multiplex network propagation model, we propose a basic greedy algorithm on it. To reduce complexity, we combine some of the characteristics of triggering model into our algorithm. Then we propose a novel MNStaticGreedy algorithm which is based on the efficiency and scalability of the StaticGreedy algorithm. Our experiments show that the novel model and algorithm are effective, efficient and adaptable.