Cluster anti-consensus in directed networks of multi-agents based on the Q-theory

In this paper, we investigate the cluster anti-consensus problem for multi-agent systems with directed information exchange. The algebra graph theory is reviewed and the properties of signless Laplacian matrix of a directed graph are derived. Then a new control protocol is designed to achieve cluster anti-consensus of multi-agent systems based on the Q-theory. Sufficient conditions are given to guarantee the cluster anti-consensus of multi-agent systems by using the properties of signless Laplacian matrix. Numerical simulations show the effectiveness of our theoretical results.     

新浪微博信息传播效果评价及实证研究——基于DEA方法的分析

为了衡量新浪微博信息传播效果,本文在10个不同话题领域分别选择公众微用户、意见领袖（加“V”）用户以及普通用户共30个决策单元,利用模糊数据包络分析模型进行实证分析,研究结果表明,用户属性、内容属性、媒介属性都对新浪微博信息传播具有影响,而在不同的话题领域影响具有异质性。     

赖志杰,杨玉兰广东省科技创新监测研究中心,暨南大学

重复建设、发展模式单一、协同作用弱等问题严重阻碍着广东省专业镇中小微企业服务平台的发展.在调研的基础上将目前广东省专业镇中小微企业服务平台的建设模式归纳为自有团队模式、外包模式、合作模式、提供信息交流平台模式和混合型模式五大类,综合考虑影响平台建设模式选择的相关因素,得出多功能综合服务平台是未来服务平台发展方向的结论,并针对5个典型服务平台建设模式,提出创新发展意见.     

企业微博质量对用户行为意向的影响机理研究

以新浪微博为背景,本文在界定企业微博质量的定义及其构成维度的基础上,提出了企业微博质量的测量指标,构建了企业微博质量影响用户行为意向的概念模型。通过应用SmartPLS2.0对337份有效问卷进行分析,对模型进行了验证。研究结果表明,企业微博质量可以划分为信息质量和交互质量两个维度,它们通过用户满意和信任这两个中间变量正向影响用户行为意向。最后,本文对改善企业微博质量,企业有效利用微博培养用户粘性提出了一些建议。     

基于符号有向图的故障诊断系统及其软件平台

基于符号有向图(SDG)的故障诊断系统不依赖精确数学模型和在线数据,适用于外场通用故障诊断设备实施现场诊断。建立图形化SDG模型开发平台是实现其通用性的关键。基于Visio的软件实现通过模具设计和功能扩展降低了平台开发成本,提高了平台运行的可靠性,也使得现场维护人员可以方便地利用其扩展诊断设备功能。     

基于UTAUT模型的旅游信息服务平台用户使用意愿研究

【目的/意义】旅游信息服务平台是现代旅游发展的关键支撑,研究旅游信息服务平台用户使用意愿与行为 及其影响因素,有助于平台运营商不断优化功能、提升服务水平。【方法/过程】基于UTAUT模型,综合考虑信任程 度、感知风险、产品或服务权威性等,构建旅游信息服务平台用户使用意愿影响因素的结构方程模型,并以“掌上高 铁”为例,设计了用户使用意愿影响因素测量量表,通过发放问卷方式收集数据,利用软件 R4.1.0对结构方程模型 进行了分析。【结果/结论】数据分析结论显示：付出期望、社会影响、便利条件、信任程度、产品或服务权威性对使用 意愿有显著的正向影响,感知风险对使用意愿有显著负向影响,绩效期望和使用意愿对使用行为有显著正向影响。 【创新/局限】本文新增了“产品或服务权威性”变量,构建了铁路旅游信息服务平台即“掌上高铁”软件用户使用行 为影响因素模型。     

新型社交网络信息传播特点和模型分析

新型社交网络开放平台近年来得到了迅速的发展,正在改变着人们的沟通与交往模式,并深刻影响着经济和社会的发展。本文主要研究社交网络中信息传播问题,就其传播方式、传播行为、传播路径和传播特点进行了研究,同时以新浪微博为例,在分析大量实例的基础上,提出关于社交网络开放平台中信息传播的几种主要模型及特点。     

Global information-aware argument mining based on a top-down multi-turn QA model

Argument mining (AM) aims to automatically generate a graph that represents the argument structure of a document. Most previous AM models only pay attention to a single argument component (AC) to classify the type of the AC or a pair of ACs to identify and classify the argumentative relation (AR) between the two ACs. These models ignore the impact of global argument structure of the documents, which is important, especially in some highly structured genres such as scientific papers, where the process of argumentation is relatively fixed. Inspired by this, we propose a novel two-stage model which leverages global structure information to support AM. The first stage uses a multi-turn question-answering model to incrementally generate an initial argumentative graph that identifies relations among ACs. At each turn, all ACs related to the query AC are generated simultaneously, such that the sibling global information between the answer ACs is considered. In addition, the partially constructed graph is used as global structure information to support the extension of the graph with additional ACs. After the whole initial graph structure has been determined, the second stage assigns semantic types to both the ACs and ARs among them, leveraging information from this initial graph as global structure information. We test the proposed methods on two scientific datasets (one is the AbstRCT dataset including 659 abstracts about cancer research and the other is the SciARG dataset that consists of 225 computer linguistic abstracts and 285 biomedical abstracts) and a student essay dataset PE with 402 essays. Our experiments show that our model improves the state-of-the-art performance on two scientific datasets for different AM subtasks, with average improvements of 1%, 2.41%, 1.1% for the ACC, ARI and ARC task respectively on the AbstRCT dataset, and 2.36%, 1.84%, 8.87% for the ACC, ARI and ARC task on the SciARG dataset. Our model also achieves comparative results on the PE datasets: 87.7% of F1 scores for the ACC task, 81.4% for the ARI task and 78.8% for the ARC task.     

Spectral clustering with physical intuition on spring–mass dynamics

In this paper, we provide a new insight into clustering with a spring–mass dynamics, and propose a resulting hierarchical clustering algorithm. To realize the spectral graph partitioning as clustering, we model a weighted graph of a data set as a mass–spring dynamical system, where we regard a cluster as an oscillating single entity of a data set with similar properties. And then, we describe how oscillation modes are related with eigenvectors of a graph Laplacian matrix of the data set. In each step of the clustering, we select a group of clusters, which has the biggest number of constituent clusters. This group is divided into sub-clusters by examining an eigenvector minimizing a cost function, which is formed in such a way that subdivided clusters will be balanced with large size. To find k clusters out of non-spherical or complex data, we first transform the data into spherical clusters located on the unit sphere positioned in the (k−1)-dimensional space. In the sequel, we use the previous procedure to these transformed data. The computational experiments demonstrate that the proposed method works quite well on a variety of data sets, although its performance degrades with the degree of overlapping of data sets.     

Research of Chinese intangible cultural heritage knowledge graph construction and attribute value extraction with graph attention network

The development of digital technology promotes the construction of the Intangible cultural heritage (ICH) database but the data is still unorganized and not linked well, which makes the public hard to master the overall knowledge of the ICH. An ICH knowledge graph (KG) can help the public to understand the ICH and facilitate the protection of the ICH. However, a general framework of ICH KG construction is lacking now. In this study, we take the Chinese ICH (nation-level) as an example and propose a framework to build a Chinese ICH KG combining multiple data sources from Baike and the official website, which can extend the scale of the KG. Besides, the data of ICH grows daily, requiring us to design an efficient model to extract the knowledge from the data to update the KG in time. The built KG is based on the triple 〈entity, attribute, attribute value〉 and we introduce the attribute value extraction (AVE) task. However, the public Chinese ICH annotated AVE corpus is lacking. To solve that, we construct a Chinese ICH AVE corpus based on the Distant Supervision (DS) automatically rather than employing traditional manual annotation. Currently, AVE is usually seen as the sequence tagging task. In this paper, we take the ICH AVE as a node classification task and propose an AVE model BGC, combining the BiLSTM and graph attention network, which can fuse and utilize the word-level and character-level information by means of the ICH lexicon generated from the KG. We conduct extensive experiments and compare the proposed model with other state-of-the-art models. Experimental results show that the proposed model is of superiority.     

MTGCN: A multi-task approach for node classification and link prediction in graph data

Both node classification and link prediction are popular topics of supervised learning on the graph data, but previous works seldom integrate them together to capture their complementary information. In this paper, we propose a Multi-Task and Multi-Graph Convolutional Network (MTGCN) to jointly conduct node classification and link prediction in a unified framework. Specifically, MTGCN consists of multiple multi-task learning so that each multi-task learning learns the complementary information between node classification and link prediction. In particular, each multi-task learning uses different inputs to output representations of the graph data. Moreover, the parameters of one multi-task learning initialize the parameters of the other multi-task learning, so that the useful information in the former multi-task learning can be propagated to the other multi-task learning. As a result, the information is augmented to guarantee the quality of representations by exploring the complex constructure inherent in the graph data. Experimental results on six datasets show that our MTGCN outperforms the comparison methods in terms of both node classification and link prediction.     

Distributed cruise control of high-speed trains

In this work, the cruise control problem of high-speed trains’ movements is investigated. Both cases of a single high-speed train and multiple high-speed trains are under consideration. Different with most existing studies where the centralized control or the decentralized control methods are adopted based on a single point mass model of the train, in this paper, a distributed control mechanism is proposed by virtue of the graph theory, and the high-speed train’s model is built as a cascade of point masses connected by flexible couplers. For a single high-speed train, the neighboring cars interact through the coupling force with each other, which can be described by a connected topological graph by regarding each car as a node. Besides, the speed information communication among the cars is considered to be described by another directed topological graph. A distributed control strategy is then developed, with which all the cars of a train track a desired speed asymptotically and the neighboring cars keep a safety distance from each other. For the multiple high-speed trains running on a railway line, the in-train force interaction topology and the speed information communication topology of all the trains are more complex than those of a single train. A new cluster consensus technique is developed, by which a distributed control law is designed. Under the control law, the trains can track the desired speeds asymptotically, the headway distance between adjacent trains and the distance between the neighboring cars of a train can be kept in appropriate ranges. Finally, simulations are provided to illustrate the effectiveness of the obtained theoretical results.     

CD/CV: Blockchain-based schemes for continuous verifiability and traceability of IoT data for edge–fog–cloud

This paper presents a continuous delivery/continuous verifiability (CD/CV) method for IoT dataflows in edge–fog–cloud. A CD model based on extraction, transformation, and load (ETL) mechanism as well as a directed acyclic graph (DAG) construction, enable end-users to create efficient schemes for the continuous verification and validation of the execution of applications in edge–fog–cloud infrastructures. This scheme also verifies and validates established execution sequences and the integrity of digital assets. CV model converts ETL and DAG into business model, smart contracts in a private blockchain for the automatic and transparent registration of transactions performed by each application in workflows/pipelines created by CD model without altering applications nor edge–fog–cloud workflows. This model ensures that IoT dataflows delivers verifiable information for organizations to conduct critical decision-making processes with certainty. A containerized parallelism model solves portability issues and reduces/compensates the overhead produced by CD/CV operations. We developed and implemented a prototype to create CD/CV schemes, which were evaluated in a case study where user mobility information is used to identify interest points, patterns, and maps. The experimental evaluation revealed the efficiency of CD/CV to register the transactions performed in IoT dataflows through edge–fog–cloud in a private blockchain network in comparison with state-of-art solutions.     

Global consensus of multiple integrator agents via saturated controls

This paper investigates the problem of global leader-following consensus of multiple integrator agents subject to control input saturation. A weighted and saturated consensus algorithm is proposed to solve this problem. Both the case of an undirected communication topology and the case of a directed communication topology are considered. It is shown that global consensus of the multiple integrator agents can be reached under a general undirected graph or a detailed balanced directed graph provided that its generated graph contains a directed spanning tree. Numerical examples are provided to demonstrate the theoretical results.     

基于医学知识图谱的慢性病在线医疗社区分面检索研究

[目的/意义]基于知识图谱与分面检索能够实现健康信息的有效组织,解决其多源异构、专业知识门槛高、语义歧义等方面的问题,从而帮助用户降低专业性医疗知识的使用门槛,引导用户更快获取资源。[方法/过程]将知识图谱与分面检索相结合,构建基于医学知识图谱的慢性病在线医疗社区分面检索模型,主要包括分面体系构建、分面与焦点排序以及分面展现控制3个步骤,并以百度贴吧自闭症吧为数据来源对分面检索原型予以实现。[结果/结论]所构建的自闭症分面检索原型系统应用效果较好,提高了用户检索的效率与质量。提出的分面检索模型对完善健康信息服务等相关理论和方法具有一定推动作用。     

Model-based deep reinforcement learning for data-driven motion control of an under-actuated unmanned surface vehicle: Path following and trajectory tracking

Unmanned surface vehicles (USVs) are a promising marine robotic platform for numerous potential applications in ocean space due to their small size, low cost, and high autonomy. Modelling and control of USVs is a challenging task due to their intrinsic nonlinearities, strong couplings, high uncertainty, under-actuation, and multiple constraints. Well designed motion controllers may not be effective when exposed in the complex and dynamic sea environment. The paper presents a fully data-driven learning-based motion control method for an USV based on model-based deep reinforcement learning. Specifically, we first train a data-driven prediction model based on a deep network for the USV by using recorded input and output data. Based on the learned prediction model, model predictive motion controllers are presented for achieving trajectory tracking and path following tasks. It is shown that after learning with random data collected from the USV, the proposed data-driven motion controller is able to follow trajectories or parameterized paths accurately with excellent sample efficiency. Simulation results are given to illustrate the proposed deep reinforcement learning scheme for fully data-driven motion control without any a priori model information of the USV.     

Group event recommendation based on graph multi-head attention network combining explicit and implicit information

In event-based social networks (EBSN), group event recommendation has become an important task for groups to quickly find events that they are interested in. Existing methods on group event recommendation either consider just one type of information, explicit or implicit, or separately model the explicit and implicit information. However, these methods often generate a problem of data sparsity or of model vector redundancy. In this paper, we present a Graph Multi-head Attention Network (GMAN) model for group event recommendation that integrates the explicit and implicit information in EBSN. Specifically, we first construct a user-explicit graph based on the user's explicit information, such as gender, age, occupation and the interactions between users and events. Then we build a user-implicit graph based on the user's implicit information, such as friend relationships. The incorporated both explicit and implicit information can effectively describe the user's interests and alleviate the data sparsity problem. Considering that there may be a correlation between the user's explicit and implicit information in EBSN, we take the user's explicit vector representation as the input of the implicit information aggregation when modeling with graph neural networks. This unified user modeling can solve the aforementioned problem of user model vector redundancy and is also suitable for event modeling. Furthermore, we utilize a multi-head attention network to learn richer implicit information vectors of users and events from multiple perspectives. Finally, in order to get a higher level of group vector representation, we use a vanilla attention mechanism to fuse different user vectors in the group. Through experimenting on two real-world Meetup datasets, we demonstrate that GMAN model consistently outperforms state-of-the-art methods on group event recommendation.     

Building a K-Pop knowledge graph using an entertainment ontology

Recently, the Korean popular (K-Pop) music industry has grown into a popular subculture among teenagers and young adults worldwide, which resulted in widespread interest in the fashion and style of idolised Korean singers and groups. Although English social media websites provide some content related to K-Pop, these websites lack diversity and rapid updating of information compared to local Korean websites. This study introduces a K-Pop knowledge graph, which is the basis for describing various objects and their relationships. All contents of the knowledge graph can be distributed and shared across various applications. To do so, this study proposes a semantic data model to represent a comprehensive profile for singers and groups, their activities, organisations and entertainment content. The knowledge graph is created by aggregating a set of relevant datasets from various data sources. In addition, Gnosis, which is a news application, demonstrates how this knowledge graph can be used in a real-world service.     

基于知识图谱和DSM的研发项目多领域集成管理

   研发项目是涉及顾客需求、产品功能和部件、团队等多知识领域的复杂系统,与大数据技术相关的知识图谱方法可以更加客观全面地展示、分析不同领域间的关联,为此,本文提出新产品开发(NPD)知识图谱,并将其与依赖结构矩阵(DSM)等方法相结合,以识别研发项目中多领域间的相互依赖关系。首先,本文建立依据NPD知识图谱测度顾客需求优先序的模型,并采用DSM和质量功能展开(QFD)方法,建立由“需求-功能”QFD关联推导功能间依赖关系强度的模型。然后,采用“功能-产品”多领域矩阵(MDM)推导部件间的依赖关系强度。最后,对DSM进行聚类,为提高聚类算法的稳定性,采用改进的信息熵,建立了改进的基于信息熵的两阶段DSM聚类模型,算例分析表明,该方法可明显降低类间的协调复杂性并提高算法的稳定性。     

Informed Patch Enhanced HyperGCN for skeleton-based action recognition

Human skeleton, as a compact representation of action, has attracted numerous research attentions in recent years. However, skeletal data is too sparse to fully characterize fine-grained human motions, especially for hand/finger motions with subtle local movements. Besides, without containing any information of interacted objects, skeleton is hard to identify human–object interaction actions accurately. Hence, many action recognition approaches that purely rely on skeletal data have met a bottleneck in identifying such kind of actions. In this paper, we propose an Informed Patch Enhanced HyperGraph Convolutional Network that jointly employs human pose skeleton and informed visual patches for multi-modal feature learning. Specifically, we extract five informed visual patches around head, left hand, right hand, left foot and right foot joints as the complementary visual graph vertices. These patches often exhibit many action-related semantic information, like facial expressions, hand gestures, and interacted objects with hands or feet, which can compensate the deficiency of skeletal data. This hybrid scheme can boost the performance while keeping the computation and memory load low since only five extra vertices are appended to the original graph. Evaluation on two widely used large-scale datasets for skeleton-based action recognition demonstrates the effectiveness of the proposed method compared to the state-of-the-art methods. Significant accuracy improvements are reported using X-Sub protocol on NTU RGB+D 120 dataset.