To improve the ability to predict the evolution trend of public opinion, a public opinion evolution trend prediction model based on an improved wolf pack algorithm and optimized long-short term memory neural network is proposed. Use Halton Sequence to initialization to improve population diversity. Design step factor to perform Gauss-Sine perturbation transformation to improve wolf group exploration and development capabilities. Combine with the spiral in the whale optimization algorithm to improve the siege mechanism to enhance the local search ability of wolves. The bidirectional memory population is used to increase the cooperative ability of the wolf pack. The improved wolf pack algorithm (IWPA) is applied to the hyperparameter prediction of the LSTM neural network. Using keywords such as “COVID-19” and “Food Safety”, the experiment proves that the IWPA-LSTM neural network public opinion evolution prediction model has good accuracy and generality. The model is suitable for the prediction of various public opinion evolution trends.

In order to study the influence of higher-order structures on the evolution of cooperative behavior on scale-free networks, a network game model based on the Prisoner's Dilemma game is constructed. A second-order higher-order structure is introduced on the scale-free network, a triangular face game containing pairwise games is defined, and the higher-order structure parameters are used to link the pairwise game payoffs with the face game payoffs, and the influence of the higher-order structure on the evolution of cooperative behavior is analyzed through simulation experiments. The results show that when individuals with high connectivity prioritize cooperation and obtain high payoffs, other individuals with high connectivity will be prompted to choose cooperation, and once a stable "all-cooperative" triangular strategy structure is formed among individuals, the payoffs of each cooperator can be significantly increased, which in turn promotes the emergence of cooperative behaviors.

In order to identify important nodes in temporal networks, a node importance evaluation method is proposed in based on inter-layer neighborhood information entropy. Inspired by the directed flows model of temporal networks, the method introduces the parameter ω to fuse the inter-layer neighborhood topology information of node at adjacent snapshots, uses information entropy to describe the complexity of network structure, and also takes into account the global topological information. The effectiveness and applicability of the method is proved by using the SIR propagation model, Kendall correlation coefficient, Top-k metrics, and the proposed method is compared with six evaluation methods on six real datasets. The experimental results demonstrate that the method can more effectively identify the important nodes in the temporal network. Meanwhile, the identification of the nodes of with high importance is more accurate. In addition, the parameter ω can be adjusted to improve the evaluation effect of this method according to the topology of the temporal network. Last but not least, the time complexity of this method is O(mn), which is suitable for large-scale temporal networks.

This paper studies the selection of grid access location for distributed wind power stations in a two-layer grid with a communication control layer. The power grid layer adopts the second-order Kuramoto-like model for modeling, and the communication control layer collects the information of the generators and their neighbor nodes to form control signals and adjusts the frequencies of the generator nodes. According to the average distance from each load node to the generator nodes of the original grid, three access models of the distributed power stations are defined, and the optimal grid access locations for distributed wind power stations with intermittent power fluctuations is studied. Study shows that the synchronization performance and anti-interference ability of the power grid can be effectively improved by adding the frequency control of the two-layer network. In addition, the distributed wind power stations can improve grid stability by selecting load nodes with a small average distance from the generator nodes of the original grid to be connected to the grid.

In order to reduce the transmission risk of closed systems in densely populated areas during outbreaks of infectious diseases, this study focuses on the first cafeteria of the Shahe Campus of Beihang University as the research scene, and proposes 12 evacuation strategies for school cafeterias where disease transmission occurs. By conducting cellular automaton simulations, the effectiveness of these control strategies is evaluated. The simulation results indicate that implementing measures such as disinfection of entrances and exits, and isolating patients before evacuation can reduce the overall infection risk by approximately 40%. These control measures not only address the issue of evacuating individuals suspected of having COVID-19 in places of congregation, but also have practical value in handling sudden situations in specific scenarios and guiding epidemic prevention efforts.

In order to explore the impact of the Covid-19 epidemic on China's stock market, the Granger causality test is used to construct a complex network model of three stages before the outbreak, the outbreak period and the normalized control of the epidemic. The comparative analysis is made from the network topology, survivability and node importance. It is found that the impact of the epidemic has significantly changed the structural relationship of the Shanghai Stock Exchange industry sectors, and the linkage effect between industry indices has weakened; the network attack simulation experiment shows that in the face of more destructive deliberate attacks, the third stage has a more durable resistance, followed by the first, second-stage network. Before and after the epidemic, the ranking of the importance of industry stocks has changed significantly. The electronics, social services, comprehensive and commercial retail industries have gradually taken an important position in the stock market; the computer, household appliances and communication industries have become important control nodes for information transmission efficiency in the stock market network. During the attack of the epidemic, the positive impact of medical biology was obvious, and it became a buffer for risk contagion in the market.

Conducting research on the local structure of satellite networks is an important means to understand the nature of networks. Considering the visibility constraints of inter-satellite link antennas, a satellite network motif counts method based on temporal network data is proposed, and a motif counts process is established from TLE file input to substructure identification output; taking the three-node three-edge motif counts of GPS satellite network as an example, we found that in a short period of time maximum scanning range of the satellite antenna was positively correlated with the concentration of the triangular M₄ subgraph with special structural significance.

Technology convergence can significantly improve the innovation ability of enterprises. In-depth exploration of technology convergence mechanism is helpful to select suitable innovation partners and integrated technologies. This paper constructs a dependent network analysis model, explores the relationship between technical characteristics and organizational characteristics of technical attachment and technical convergence, and makes an empirical study on artificial intelligence industry. The research shows that, the technology with strong absorption or diffusion ability is easy to absorb or flow to other technologies; Two technologies with high technology maturity and strong technology proximity are prone to two-way flow. Common technologies owned by multiple organizations are not easy to absorb other technologies, but easy to flow to other technologies; The technology owned by a single organization is prone to two-way flow.

In order to analyze the competitive pattern and factors influencing the competitive advantage of China's major domestic passenger airlines during the epidemic period, we use the TOPSIS-Entropy method and a modified Huff model to quantify the competitive advantage strength of airlines on routes, construct a weighted bipartite network of airlines-routes empowerment based on advantage strength, and study the market segmentation of airlines' competitive advantage and its static characteristics from the perspective of network. The Tobit regression model is used to analyze the factors influencing competitive advantage. The study shows that during the epidemic period, the airlines have a low degree of multi-market exposure, and the three major airlines have obvious competitive advantages, which vary greatly in city distribution and are mainly concentrated in their base cities; HU, 3U and other airlines have less obvious advantages in market competition and are more competitive and mainly around the second-tier coastal cities. The competitive advantage of airlines is constrained by a combination of factors, and the revenue during the epidemic period is more indicative of the ability to control cost.

In order to get more complex dynamical properties, a chaotic system with cubic polynomial taking absolute value function is designed. The theoretical model of the chaotic system is described by a set of nonlinear equations with three state variables. The basic properties and the dynamic characteristics of the system like phase diagram, time domain waveform, Lyapunov exponent, Poincaré map and bifurcation diagram are analyzed. Under certain parameter conditions, the system has periodic and chaotic properties, and there are coexistence attractors or aggregation attractors when the initial values are symmetrical. In addition, when some system parameters change, the system has constant dynamic characteristics, when the initial value of the state variable changes, the dynamic characteristics of the system also remain unchanged. The correctness of the theory is verified by circuit simulation. Based on the newly designed chaotic system, an encryption scheme is designed, and the encryption performance is analyzed, which shows the effectiveness of the encryption scheme.

Based on the perspective of bounded rationality, this paper first constructed a dynamic game model of dynamic cooperative behavior to explore this problem. Secondly, it discussed the impact of contract fines, government incentives, cooperation costs, and cooperation revenues on the evolution of top-management team behavior. Finally, it carried out numerical simulation and correlation analysis on its evolution process. The research shows that the final strategy of the two sides in the cooperation of the senior management team of mixed ownership enterprises will be stable in the cooperation and non-cooperation strategy, and will not be stable in the cooperation and non-cooperation strategy of one party. Among them, within a certain range, increasing the penalty of contract, increasing government incentives, reducing cooperation costs, and increasing the coefficient of cooperation revenue can promote the transformation from non-cooperation to cooperation. We hope that this study can provide some reference significance for the smooth progress of the mixed reform of state-owned enterprises and form efficient institutional arrangements.

In order to realize the scientific design of motor bus transferring scheme in the commuter corridor, the resilience recovery process of commuting corridor is regarded as a bi-level programming in which the resilience is improved through continuous exploration and iteration of ground bus transferring scheme in complex environment. The deep reinforcement learning algorithm is introduced to form the upper level planning, and the value function neural network is used to fit the response function of emergencies and travelers' cluster behavior to the adjustment of ground bus transferring scheme. The decision-making objective is achieved by training the transferring schemes. In the lower level planning, the cellular neural network model is introduced to simulate the cluster travel choice behavior under the background of data intelligence. The case study shows that this method can effectively improve the resilience of the commuter corridor, and the cluster behavior will have a negative impact on the resilience recovery.

Scientific and reasonable cold chain logistics mode is the key to ensure the price and freshness competitiveness of agricultural products e-commerce. For the supply chain involving two agricultural products e-commerce, e-commerce self-run cold chain logistics and third party cold chain logistics provider, the Stackelberg game model that takes into account the competition between two agricultural products e-commerce, and the dominance of third-party cold chain logistics provider, as well as the evolutionary game model for the choice of two agricultural e-commerce cold chain logistics modes is constructed. The influence of cross price elasticity, freshness demand elasticity, and preservation input cost coefficient of self-run and third-party on the evolution path is revealed through the simulation. The results show that: if the cross price elasticity, freshness demand elasticity and the third-party preservation input cost coefficient increase respectively, self-run cold chain logistics is the stable evolutionary strategy, e-commerce tends to self-run cold chain logistics. If the self-run preservation input cost coefficient increases, the third-party cold chain logistics is the stable strategy, the e-commerce tends to cooperate with the third-party cold chain logistics provider.

In order to overcome the shortages of the particle swarm optimization algorithm, such as low accuracy, slow convergence and falling into local optima, a particle swarm optimization algorithm based on labor division and fuzzy control is proposed, which improves the algorithm by using the division of labor, parameter adaptive adjustment and simulated annealing with distance factors. Particles are divided into scout and rearguard ones, the former searches randomly and the latter learns from the best individual solutions as well as the best global solution to ensure the diversity of population and to accelerate the search. A sigmoid function is used to adjust the inertial weight and fuzzy logic is applied to balance exploration and exploitation capability of the algorithm. The best global particle is updated according to simulated annealing with distance factors taken into account, which improves the ability of the algorithms to jump out of the local optima. Simulation experiments on 25 standard test functions show that the improved algorithm has better performance in terms of convergence accuracy, speed and stability.

In order to evaluate the risk of unsafe behavior of wind power operation and maintenance personnel and reduce the occurrence of behavioral safety accidents. On the basis of determining the set of risk factors of unsafe behavior, the risk evaluation index system of unsafe behavior is constructed. The weight and threshold of BP neural network were adjusted by fruit fly optimization algorithm, and an unsafe behavior risk assessment model based on FOA-BP was established. Taking a wind farm as an example to collect data, test the model, realize the risk evaluation of unsafe behavior, and calculate the weight of risk evaluation index. This model has good predictive performance and can evaluate the risk of unsafe behavior. Enterprises can develop targeted prevention and control measures according to the evaluation index, index weight value and risk level.

In a mixed intersection composed of autonomous and manual vehicles, the traditional traffic strategy leads to slow traffic, long waiting time, and low efficiency. To solve the problem, in this paper, platoons of vehicles are formed based on the distance between vehicles. The platoons with autonomous and manual vehicles are controlled by different traffic strategies and priorities, which effectively prevents the traffic efficiency reduction of autonomous vehicles and ensures the fairness of traffic at intersections. Simulations show that with the increase of penetration rate, the proposed strategy is superior to the traditional strategies in terms of the average speed, the average waiting time, and the average fuel consumption.

In order to study the property of self-oscillating gels, dissipative structure theory is applied to analyze the oscillating dynamics of the Belousov-Zhabotinsky (BZ) reaction, and Andronov-Hopf bifurcation is adopted for the BZ reaction model to study the occurrence and energy status and periodic change between chemical and mechanical potential; and its complex nonlinear characteristics are the key to the force-chemical coupling behavior of self-oscillating gels. From this study, we find that BZ reaction a typical system that is far from thermodynamic equilibrium, and the extra potential provided from the inputs might cause the system to destabilize, and with the onset of fluctuations, periodic deformation between swelling and deswelling takes place. The study of BZ rection dynamically could aid exploration on adjusting smart/ soft material that exhibits heartbeat-like behaviors

This paper analyzes the influence of seasonality of infection rate and floating population on measles dynamics in Henan province, compares and analyzes the seasonal variation pattern of measles infection rate, and provides theoretical support for the future prevention and control of measles in China. In this paper, a SIR model including the seasonal ladder model of migrant population and infection rate was established, and the parameters in the model were estimated using the Markov Monte Carlo method, the infection rate of local mobile population and the migrant population outside the province was compared, and the influence of different infection rate models on transmission dynamics was analyzed. In the measles transmission dynamics in Henan, the influence of migrant population outside the province on measles transmission dynamics was greater than that of the local population, and the seasonal change pattern of infection rate in Henan was more in line with the step change, and the influence of migrant population on measles transmission dynamics in Henan was higher than that of seasonal infection rate. In the future measles prevention and control work, we should strengthen the monitoring of the migrant population and reasonably choose the time and population of immunization.

In order to explore the key factors affecting small catering merchants' access to the food safety traceability system and the choices behavior of the food regulatory sector and the social public, an evolutionary game model among small catering merchants, food regulatory sector and the social public is conducted by using the evolutionary game theory. The impacts of different parameters on the choice of the three-party strategy are analyzed under the assumption of bounded rationality. The results of the study show that, in order to further maintain the food safety environment and prompt small catering merchants to be positive in accessing to the food safety traceability system, a scientific and reasonable reward and compensation mechanism should be established to motivate the social public's enthusiasm to participate in the regulation, reduce the costs of small catering merchants using information technology and achieve a safety supervision on the quality of the whole food chain.

The coal mill group is one of the important equipment in thermal power plants. To ensure the safety and stability of the production process, a fault diagnosis method named clustering coarsening graph convolution neural network (CC-GCN) is proposed in this paper. Firstly, the graph structure is established between the original fault samples by KNN algorithm and converted into graph samples. Then, spectral clustering is used to compress the graph samples into multi-level coarsening graphs, and convolution operations and feature fusion are performed for each level of coarsening graph respectively. Finally, fault diagnosis is performed on the fault samples based on the graph classification method. Simulation experiments are carried out on two sets of data sets with different operation conditions of the coal mill group, and the results show that this method can not only effectively improve the accuracy of fault diagnosis, but also significantly reduce the running time of the model.