As a type of collective behavior in social systems, opinion polarization may greatly influence social stability. Thus, this paper systematically sorts out and summarizes the research status of opinion polarization. Based on reviews of the concept and modeling of opinion polarization in social and political fields, the two interaction mechanisms of opinions that lead to opinion polarization are extracted. From the perspective of individuals, the paper focuses on discussion two kinds of social psychological effects that may lead to opinion polarization, viz., biased assimilation and hostile media effect. The key to integration of polarization research in different fields lies in the internal change mechanism of individual opinion. One of the emphasis in future research should focus on the mutual corroboration of models and real data.

Visualization technology can be used to effectively analyze the community structure, help users to understand the network topology, and dig out the hidden information from it, but the traditional network visualization layout algorithm does not consider the overlapping characteristics of nodes in the overlapping communities. Aiming at above problems, firstly, this paper uses the existing overlapping community detection algorithm to divide the community, and then hard partition and determine the node position according to the weighted summation of the membership matrix. Finally, the overlapping nodes are accurately laid out to display the overlapping community structure. The visual results demonstrate that the algorithm can visually display the overlapping community structure, highlight the overlapping nodes and the communities to which the nodes belong. At the same time, the experiment uses indicators such as node deviation, edge length deviation, and point distribution variance to verify that the algorithm can reduce node deviation and point distribution variance. This study can meet the visualization needs of overlapping community structures in complex networks, and can provide certain help for understanding the structure and functions of complex communities.

Cascading failures caused by failed nodes or edges in the network may lead to the paralysis of the whole network. The definition of initial load has a very important impact on the analysis of cascading failure model. In this paper, considering the lack of topological information brought by degree and the huge computation brought by betweenness centrality, we make full use of the topological information as well as neighbors’ information of nodes and firstly propose the initial load definition based on local entropy. Some typical examples about cascading failures in the complex networks demonstrate the effectiveness of proposed definition based on local entropy.

In order to improve the accuracy of complex network model and the comprehensiveness of complexity analysis, the method of modeling undirected weighted complex network of CREFTN in L-space (UWCN-CREFTN), the comprehensive importance evaluation index of the nodes and network robustness analysis method considering node failure based on comprehensive importance index are proposed. Based on the timetable and wagon-flow data, the results of analyzing the topological characteristics of UWCN-CREFTN show that CREFTN is a small-world network which has high heterogeneity, strength-degree positive correlation, point-weighted equality, weighted non-homogeneous matching, strength-strength negative correlation at present. Based on network efficiency and node importance, the results of analyzing the robustness of UWCN-CREFTN contrastively under four situations at two aspects show that the random failure of nodes makes the network more robust than vandalism, maximum-comprehensive-importance vandalism make the network more vulnerable than maximum-strength vandalism and completely collapse faster than maximum-weighted-betweenness vandalism, which indicates that the proposed comprehensive importance evaluation index has the dual characteristics of node strength and node weighted betweenness.

Critical nodes in complex networks can influence the system functionality. Many real networks have a significant number of closed triangle motifs. To explore the influence of these motifs on the importance of nodes, a critical nodes identification method based on closed triangle motifs is proposed. The algorithm measures the importance of each motif and evaluates the node importance through the motif weights and node degrees. Robustness experiments and propagation experiments based on the SIR model are carried out with six real networks. The experimental results show that this method can identify critical nodes of the network more effectively than the DC method, K-shell method, WL method, and ME method.

In order to overcome the deficiency of incomplete importance of nodes evaluated by single attribute and subjective weight selection of indicators, based on the K-shell method in hypernetwork, this paper introduces the influence of neighbor nodes on their own nodes while comprehensively considering the attributes of nodes, combined with the index of betweenness centrality, using the entropy method to determine the contribution weight of each index to node importance. A method to identify important nodes in hypernetworks is proposed from both local and global perspectives. The advantages and disadvantages of different identification methods are compared through the natural connectivity of network and the relative size of the maximum connected subgraph, and the empirical data of Xining city bus hypernetwork is used to further verify the effectiveness a feasibility of the proposed method.

To study the controllability of a class of multi-agent systems, the concept of Input strongly connected component (InSCC) was first proposed, and analyzed using PBH criterion and graph theory. Firstly, the controllability of InSCC structure and the topology structure composed of InSCC and roadmap were analyzed, and a leader′s selection method was provided to achieve system controllability. Secondly, based on the InSCC structure, the influence of adding communication edges between different InSCC structures and in the road map on system controllability was studied. Research has found that for topologies containing InSCC, as well as those composed of InSCC and road maps, increasing communication edges in a certain way does not change the controllability of the system. A method for constructing controllable topologies was proposed. Finally, the necessary and sufficient conditions for the controllability of multi-agent systems containing InSCC structures under switching topology were given.

Terrorist organization network is evolving from traditional pyramid construction to multi-layer network. We analyze multi-layer network of terrorist organization, then construct relevant model.We take ISIS terrorist organization as an example to verify above model. The research terrorist organization is gradually moving towards multi-layer network. And terrorist organization network has different features among multi-layer network.

In order to reduce the energy consumption between industrial sectors, this paper constructs the indirect energy flow network between industrial sectors based on the input-output table, and defines the energy flow situation and dependence relationship between industrial sectors by combining the dependence matrix with other methods. The results show that, the indirect energy supply is more concentrated than the consumption among industrial sectors, and the supply source shifts from the chemical industry to the service industry. Indirect energy flows between the upstream and downstream links of the industrial chain are relatively large and stable. The correlation between indirect energy flows and inter-sector dependence is gradually increasing, but it still needs to be improved. It is necessary to further optimize the industrial structure, improve the integrity of the domestic industrial chain and reduce the energy consumption among industrial sectors.

The user behavior of short video (such as viewing comments, likes, clicking on avatars, and forwarding) is predicted by considering the change of user interests. In this paper, the sorted user historical behavior sequence is introduced into word2vec as a corpus to train the word embedding model, learn the dynamic interests of users, and effectively capture the changes in user interests. The statistical features constructed by feature engineering and the user dynamic interest features constructed by the word embedding model are input into the multi task learning with multi gate mixture of experts (MMOE), and a new evaluation index W-uAUCis proposed to evaluate the prediction accuracy of the model. The experimental results show that compared with shared bottom, wide & deep and deepfm, the proposed MMOE model considering the change of user interest has the best prediction accuracy.

In order to find ways to improve the effectiveness of security check, based on the mechanism of passengers violating civil aviation security check regulations, an evolutionary game model of passengers, airport police and security inspectors was constructed, and the influence mechanism of security check personnel, airport police and passengers in the process of civil aviation security check was obtained. The results show that properly increasing the punishment of passengers who violate security regulations can avoid the occurrence of stable state of passengers who violate security regulations; The key method to improve the effectiveness of security check is to make good use of emerging technologies and innovate security check management methods to improve the accuracy of security check and increase the cost of passengers' speculative behavior to avoid security check.

Inorder to study how online shopping platforms can effectively use recommendation agents to stimulate consumers′purchase intention,for the first time, this paper discusses the impact of consumer characteristics, recommendation agent characteristics and platform characteristics of recommendation agents on consumers' trust, and the impact of trust on consumers' purchase intention. This paper used the questionnaire survey and the structural equation model analysis verify the hypothesis. The research shows that the accuracy of recommendation agents has a positive impact on consumers' cognitive trust, emotional trust and purchase intention; The diversity of recommendation agents positively affects consumers' emotional trust; The credibility of online shopping platforms positively affects consumers' emotional trust.

Traditional loop closure detection algorithms mostly utilize handcrafted features to represent images. The robustness of dealing environmental changes such as illumination and viewpoint changes is vulnerable, and the features extraction is time-consuming, which cannot meet the real-time requirements. To address these problems, we propose an improved algorithm which uses deep neural network to extract more robust image features. Specifically, the atrous spatial pyramid pooling (ASPP) module is introduced into the classic NetVLAD model to characterize the image. By the fusion of multi-scale features, the feature maps have fewer dimension and higher resolution, and thus, more accurate and compact image features are obtained. Experiments on public datasets show that the proposed algorithm has higher precision and recall rate. It can deal with the changes of illumination and viewpoint to a certain extent, and has less time cost in extracting image features.

In order to explore the process of residents’ emotion dissemination in community built environment renovation, a learning rule that integrates residents’ personality preferences and historical information is designed based on evolutionary game and multi-agent simulation, and the inner mechanism of residents’ emotional dynamic evolution is analyzed. The results demonstrate that enhancing the willingness of neutral players to interact with positive ones can promote the spread of positive emotion and system stability. Besides, residents’ support cost, synergistic benefits, government compensation, and the difference of information diffusion cost between negative and positive, are the determinants of macro-evolution of residents’ emotional state.