The Immense Impact of Reverse Edges on Large Hierarchical Networks

Hierarchical networks are frequently encountered in animal groups,gene networks,and artificial engineering systems such as multiple robots,unmanned vehicle systems,smart grids,wind farm networks,and so forth.The structure of a large directed hierarchical network is often strongly influenced by reverse edges from lower-to higher-level nodes,such as lagging birds’howl in a flock or the opinions of lowerlevel individuals feeding back to higher-level ones in a social group.This study reveals that,for most large-scale real hierarchical networks,the majority of the reverse edges do not affect the synchronization process of the entire network;the synchronization process is influenced only by a small part of these reverse edges along specific paths.More surprisingly,a single effective reverse edge can slow down the synchronization of a huge hierarchical network by over 60%.The effect of such edges depends not on the network size but only on the average in-degree of the involved subnetwork.The overwhelming majority of active reverse edges turn out to have some kind of“bunching”effect on the information flows of hierarchical networks,which slows down synchronization processes.This finding refines the current understanding of the role of reverse edges in many natural,social,and engineering hierarchical networks,which might be beneficial for precisely tuning the synchronization rhythms of these networks.Our study also proposes an effective way to attack a hierarchical network by adding a malicious reverse edge to it and provides some guidance for protecting a network by screening out the specific small proportion of vulnerable nodes.

Research on the Processing Methods of the Computer Format Information Flow in the Network English Translation System

The development o f the network technology, and especially the web search engine, has brought great changes to the field of the English translation. Translators can acquire the background information of the translated texts by using the web search engine correctly, inquire about the correct translation methods of the rare professional terms, apply the fixed sentence patterns, and check the correctness of the translation, so as to improve the translation speed and quality.

DuFNet:Dual Flow Network of Real-Time Semantic Segmentation for Unmanned Driving Application of Internet of Things

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.

Evolving a Bayesian network model with information flow for time series interpolation of multiple ocean variables

Based on Bayesian network (BN) and information flow (IF),a new machine learning-based model named IFBN is put forward to interpolate missing time series of multiple ocean variables. An improved BN structural learning algorithm with IF is designed to mine causal relationships among ocean variables to build network structure. Nondirectional inference mechanism of BN is applied to achieve the synchronous interpolation of multiple missing time series. With the IFBN,all ocean variables are placed in a causal network visually,making full use of information about related variables to fill missing data. More importantly,the synchronous interpolation of multiple variables can avoid model retraining when interpolative objects change. Interpolation experiments show that IFBN has even better interpolation accuracy,effectiveness and stability than existing methods.

A time sequence analysis on the informal information flow mechanism of microblogging

Microblog is a new Internet featured product, which has seen a rapid development in recent years. Researchers from different countries are making various technical analyses on microblogging applications. In this study, through using the natural language processing(NLP) and data mining, we analyzed the information content transmitted via a microblog, users' social networks and their interactions, and carried out an empirical analysis on the dissemination process of one particular piece of information via Sina Weibo.Based on the result of these analyses, we attempt to develop a better understanding about the rule and mechanism of the informal information flow in microblogging.

Distributed Information Flow Verification for Secure Service Composition in Smart Sensor Network

Accelerate processor, efficient software and pervasive connections provide sensor nodes with more powerful computation and storage ability, which can offer various services to user. Based on these atomic services, different sensor nodes can cooperate and compose with each other to complete more complicated tasks for user. However, because of the regional characteristic of sensor nodes, merging data with different sensitivities become a primary requirement to the composite services, and information flow security should be intensively considered during service composition. In order to mitigate the great cost caused by the complexity of modeling and the heavy load of single-node verification to the energy-limited sensor node, in this paper, we propose a new distributed verification framework to enforce information flow security on composite services of smart sensor network. We analyze the information flows in composite services and specify security constraints for each service participant. Then we propose an algorithm over the distributed verification framework involving each sensor node to participate in the composite service verification based on the security constraints. The experimental results indicate that our approach can reduce the cost of verification and provide a better load balance.

Measuring the Evolution and Influence in Society’s Information Networks

We develop a series of mathematical models to describe flow of information in different periods of time and the relationship between flow of information and inherent value. We optimize the diffusion mechanism of information based on model SEIR and improve the diffusion mechanism. In order to explore how inherent value of the information affects the flow of information, we simulate the model by using Matalab. We also use the data that the number of people is connected to Internet in Canada from the year 2009 to 2014 to analysis the model’s reliability. Then we use the model to predict the communication networks’ relationships and capacities around the year 2050. Last we do sensitivity analysis by making small changes in parameters of simulation experiment. The result of the experiment is helpful to model how public interest and opinion can be changed in complex network.

Multi-faceted spatio-temporal network for weather-aware air traffic flow prediction in multi-airport system

As one of the core modules for air traffic flow management,Air Traffic Flow Prediction(ATFP)in the Multi-Airport System(MAS)is a prerequisite for demand and capacity balance in the complex meteorological environment.Due to the challenge of implicit interaction mechanism among traffic flow,airspace capacity and weather impact,the Weather-aware ATFP(Wa-ATFP)is still a nontrivial issue.In this paper,a novel Multi-faceted Spatio-Temporal Graph Convolutional Network(MSTGCN)is proposed to address the Wa-ATFP within the complex operations of MAS.Firstly,a spatio-temporal graph is constructed with three different nodes,including airport,route,and fix to describe the topology structure of MAS.Secondly,a weather-aware multi-faceted fusion module is proposed to integrate the feature of air traffic flow and the auxiliary features of capacity and weather,which can effectively address the complex impact of severe weather,e.g.,thunderstorms.Thirdly,to capture the latent connections of nodes,an adaptive graph connection constructor is designed.The experimental results with the real-world operational dataset in Guangdong-Hong Kong-Macao Greater Bay Area,China,validate that the proposed approach outperforms the state-of-the-art machine-learning and deep-learning based baseline approaches in performance.

The prediction of external flow field and hydrodynamic force with limited data using deep neural network

Predicting the external flow field with limited data or limited measurements has attracted long-time interests of researchers in many industrial applications.Physics informed neural network(PINN)provides a seamless framework for combining the measured data with the deep neural network,making the neural network capable of executing certain physical constraints.Unlike the data-driven model to learn the end-to-end mapping between the sensor data and high-dimensional flow field,PINN need no prior high-dimensional field as the training dataset and can construct the mapping from sensor data to high dimensional flow field directly.However,the extrapolation of the flow field in the temporal direction is limited due to the lack of training data.Therefore,we apply the long short-term memory(LSTM)network and physics-informed neural network(PINN)to predict the flow field and hydrodynamic force in the future temporal domain with limited data measured in the spatial domain.The physical constraints(conservation laws of fluid flow,e.g.,Navier-Stokes equations)are embedded into the loss function to enforce the trained neural network to capture some latent physical relation between the output fluid parameters and input tempo-spatial parameters.The sparsely measured points in this work are obtained from computational fluid dynamics(CFD)solver based on the local radial basis function(RBF)method.Different numbers of spatial measured points(4–35)downstream the cylinder are trained with/without the prior knowledge of Reynolds number to validate the availability and accuracy of the proposed approach.More practical applications of flow field prediction can compute the drag and lift force along with the cylinder,while different geometry shapes are taken into account.By comparing the flow field reconstruction and force prediction with CFD results,the proposed approach produces a comparable level of accuracy while significantly fewer data in the spatial domain is needed.The numerical results demonstrate that the proposed approach with a specific deep neural network configuration is of great potential for emerging cases where the measured data are often limited.

电力信息物理系统中信息系统物理化的建模及分析方法

该文基于信息系统物理化的设想提出电力信息物理系统(cyber-physical power system,CPPS)中的信息流建模和计算分析方法。采用连续时间函数来刻画信息流的特征,并定义信息网络运行参数为流量累积函数、信息流速和时延。首先,基于遍历法搜索出信息流路径,建立信息流速矩阵的范式;然后利用改进的网络演算(network calculus,NC)特性赋值流速矩阵的元素;进一步采用流量累积函数表征信源数据发送规律,从而显式求解时延上界。最后将提出的信息流建模方法应用于智能变电站自动化系统的时延计算,通过与OPNET的仿真结果相比较,验证所提出模型的有效性,而且该方法可以提供定量分析指标以优化变电站组网方案设计中的信息流分布。

多用户复杂网络信息流短时预测方法

当前的多用户复杂网络信息流短时预测模型多为单一结构,预测的范围较小,为此提出多用户复杂网络信息流短时预测方法。根据实时的信息流预测需求及标准的变化,设定最大预测误差范围,采用多阶的方式构建多阶短时预测模型,建立短时模糊预测流程,构建多用户复杂网络信息流短时预测模型,采用自适应修正处理,实现信息流预测。测试结果表明,设计方法的信息流的短时预测F值均可以达到0.95以上,表明该方法的泛化能力与针对性均得到增强,可以大范围地精准预测信息流。

数字化公交为导向的常州公交客流提升策略研究

受社会和经济等因素的影响,目前地面公交客流出现不同层次的下降,如何深入挖掘制约客流的影响因素,针对不同的具体问题提出相对应的客流提升措施,是提高地面公交的行业竞争力,提升地面公交在居民出行中比例的重要策略。本文通过对居民出行调查和公交满意度调查,深入分析客流下降的原因,并结合公交乘客交通需求调查数据,以数字化公交为导向,从智能化采集数据、灵活化公交线路、数字化线网布局和信息化定制服务等方面提出改善措施。

Modeling and simulation of network traffic flow evolution based on incomplete information feedback strategies in the ATIS environment

Considering both the high complexity of urban traffic flow systems and the bounded rationality of travelers,providing traffic information to all travelers is an effective method to induce each individual to make a more rational route-choice decision.Within Advanced Traveler Information System(ATIS)working environment,temporal and spatial evolution processes of traffic flow in urban road networks are closely related to strategies of providing traffic information and contents of information.In view of the day-to-day route-choice situations,this study constructs original updating models of the cognitive travel time of travelers under four conditions,including not providing any route travel time,only providing the most rapid route travel time,only providing the most congested route travel time,and providing all the routes travel times.The disaggregate route-choice approach is adopted for simulation to reveal the relationship between the evolution process of network traffic flow and the strategy of providing traffic information.The simulation shows that providing traffic information to all travelers cannot improve the operational efficiency of road networks.It is noteworthy that an inappropriate information feedback strategy would lead to intense variation in various routes traffic flow.Compared with incomplete information feedback strategies,it is inefficient and superfluous to provide complete traffic information to all travelers.

融合三维人脸动态信息和光流信息的人脸表情识别

人脸表情识别在静态图像上取得了卓越的成效,但这些方法应用于视频或图像序列时,准确度和鲁棒性往往会受到影响。传统的方法通常无法基于空间信息和光流信息进行人脸表情的识别,然而这些辅助识别信息都是二维信息,没有考虑到人脸的表情变化是一种三维的变化过程。为充分挖掘人脸表情识别的深层语义信息,提出了一种基于三维人脸动态信息和光流信息相结合的融合表情识别方法。该方法构建基于人脸深度图像、光流图像和RGB图像的多流卷积神经网络,通过融合3种模态的信息进行人脸表情识别。所提方法在CAER,RAVDESS数据集上进行了充分验证,实验结果表明,其在表情识别性能上优于目前的主流方法,证明了其有效性。

基于PINNs算法的一维潜水流方程的渗流参数反演

在地下水领域中,渗流参数反演有助于了解地下水流动的性质,帮助确定地下水资源的分布、移动和质量,这对于地下水资源管理、水文模型开发和地下水补给的可持续性非常重要.近年来,神经网络方法快速发展,然而其针对潜水流渗流参数反演的研究较少.基于此,首次将物理信息神经网络(Physics-Informed Neural Networks,PINNs)方法结合软硬约束设置来解决潜水含水层渗透系数反演问题,以一维稳态非均质潜水流以及非稳态均质潜水流(含溶质运移)的渗透系数反演为例,对比了不同问题中PINNs软约束方法(PINNs-S)和硬约束方法(PINNs-H)反演渗透系数的表现.PINNs算例结果表明,PINNs算法反演渗透系数具有较高的计算精度.此外,PINNs硬约束算法和软约束算法各有优劣,在实际应用中应根据具体问题和实验效果来合理选择.

基于物理信息自适应深度学习的交通状态估计

物理信息深度学习(physics-informed deep learning, PIDL)是一种将深度学习与物理学先验知识相结合的新兴范式,该范式在智能交通领域,尤其在交通状态估计应用中,展现出了巨大潜力。为进一步优化物理信息深度学习模型在交通状态估计问题上的准确度与收敛速度,构建了一个结合Aw-Rascle宏观交通流模型的物理信息自适应深度学习模型(physics-informed adaptive deep learning with Aw-Rascle, PIAdapDL-AR),依据有限与局部的交通检测数据,实时准确估计全局交通流状态。主要的改进包括两部分,一是在PIDL框架中的物理部分引入高阶Aw-Rascle交通流模型作为物理约束条件,引导并规范神经网络的训练过程;二是在神经网络部分融合自适应激活函数,替代固定的非线性激活函数,以动态优化神经网络性能。基于NGSIM数据集生成模拟的固定检测器数据和移动检测器数据,进行实验以验证模型有效性。实验结果表明:在不同覆盖率的固定检测数据场景下,PIAdapDL-AR的相对误差相比于基线模型PIDL-LWR降低了34.38%~45.24%;在不同渗透率的移动检测数据场景下,PIAdapDL-AR的相对误差相比于PIDL-LWR降低了18.33%~34.95%;融合自适应激活函数的PIAdapDL-AR的收敛速度优于配置固定激活函数的PIDL-AR,且收敛速度和估计精度均随着自适应激活函数中比例因子的增大而提升。

山东半岛城市群旅游信息流网络结构及其影响因素分析

信息与通讯技术的发展降低了旅游信息获取的难度,促成了旅游信息在地域范围内的流动,在城市之间形成了旅游信息流网络。文章基于百度指数,借助场强模型、社会网络分析和QAP分析,以山东半岛城市群为例,探究城市群内部旅游信息流特征与规律,并解释影响旅游信息流网络结构的驱动机制。研究发现:旅游信息流场强时间分布上,山东半岛城市群旅游信息流总场强,集聚场强和扩散场强演变过程基本一致,呈先上升后下降的趋势;空间分布上,山东半岛城市群总场强呈现多核心的特点,集聚场强由多核心场强特征向双核心方向演变,扩散场强呈现东西方向边缘地区高于中部地区,且由南向北减弱的结构特点。山东半岛城市群旅游信息流网络具有核心—次级核心—边缘地区的结构特点,核心地区较为稳定,次级核心区域变化较大,边缘地区变化不大,旅游信息流网络结构向双核心方向发展。旅游信息流网络结构影响因素上,推力和拉力因素与山东半岛旅游信息流网络结构具有较强的相关性而阻力因素相关性不明显,推力和拉力因素中的人口因素、信息化程度和公共服务水平的影响最为突出。

一种多状态空间信息网络拓扑生成算法的优化

空间信息网络是一种具有节点运转高速性、周期性的网络。随着近地轨道卫星日益增多,空间信息网络拓扑动态性极强,网络拓扑抗毁优化问题将具有研究意义。在考虑卫星组网的可视性、卫星节点的连接度、以及整个网络通信链路数等多种状态情况下,以最小化网络中卫星节点间的端到端时延为优化目标,构建一个满足多种约束条件的网络拓扑优化模型,提出一种优化后的模拟退火算法对模型进行求解,在模拟退火过程中创新性的提出了网络流算法进行邻域求解。实验表明,模拟退火混合求邻域算法显著优于模拟退火随机求邻域算法。

Network Coding理论的研究进展

Network Coding是一种新的信息传输方式。与传统的路由相比,Network Coding可以提高网络的性能。从理论和应用两方面总结了Network Coding研究的进展,同时,分析了将Network Coding应用到实际网络中所面临的一些问题,最后提出了进一步的研究方向。