There is growing evidence that the current worldwide epidemic of COVID-19 has many asymptomatic infections. This raises new questions for the study of medical researchers, and it is also new challenge for non-medical interventions. Based on the SEIR model with periodic boundary, this study simulates the actual spread of pathogens and the interventions by multi-agent simulation. The simulations show that epidemic prevention and control can be feasible only with the joint intervention of the two measures when there are asymptomatic infections, one cannot leave without. Our results are of guiding importance for the prevention and control of epidemic situation in the world.

User traits can be effectively predicted by singular value decomposition and Logistic Regression through online user’s ‘Like’ information. However, this method cannot predict new users’ traits. To slove the problem, this paper proposes an online user traits predicting method based on LDA topic model. Firstly, the method extracted the Weibo user’s ‘Like’ text topic through LDA model. Then it predicted new user traits based on topic. Finally, the result is compared to the traditional method based on singular value decomposition. The results showed that the F1 value of this method was up to 0.15, and the calculation time was shortened by 69.09% in average. Research inproves the defect that the inherent tags of the ‘Like’ informations cannot accurately reflect user preference, avoiding the disadvantage of recalculating new users and their ‘like’information in the predicting process of traditional methods, providing another feasible way for user traits analysis.

In order to reveal the characteristics of multilayer complex networks, three kinds of evolution models of three-layer complex networks are proposed, and a probability is defined to quantitatively describe the interlayer dependence of multilayer networks. The experimental results show that different random probabilities represent the degree distribution of three-layer networks with the characteristics of single peak, double peak and three peak. When the probabilities tends to 10^-3, the three-layer scale free networks show the characteristics of power law and single peak co-occurrence; the influence of probability on the clustering coefficient and average path length of three-layer networks is relatively small.

To solve the problem of poor generalization of existing autonomous driving systems, this paper designs a visual feature based autonomous driving system trained by reinforcement learning. The environment noise could be removed by lane lines extraction. Then the variational autoencoder is used to reduce the dimension of features and only maintain the key information of the original visual data, which could speed up the training process. Experiments on simulation platform show that the proposed autonomous driving system could perform the task of lane following. Moreover, the system has good generalization ability, and could still work in new traffic environments.

This study is devoted to the complex network analysis of China pharmaceutical manufacturing industry-university-research cooperative innovation network, to explore the evolution of the network and the impact of small world on the innovation performance of cooperative innovation network. Firstly, through complex network analysis, this study concludes that China′s pharmaceutical manufacturing industry-university-research cooperative innovation network has scale-free network characteristics, and the openness and communication frequency between the six cohesive subgroups of Shanghai pharmaceutical manufacturing industry are conducive to the formation of innovation and Communication; Secondly, using QAP regression analysis, this paper concludes that the small world has a certain adverse impact on the innovation performance of the Shanghai Industry-University-Research Cooperation Innovation Network. Finally, corresponding countermeasures and suggestions are put forward according to above analysis results.

Resource bricolage has become an important means for precision-targeted and entrepreneurship poverty alleviation. In this paper, the bricolage of economic resources and social resources in the process of precision-targeted and entrepreneurship poverty alleviation is taken as the research object, and the influence of different preferential connection mechanisms on the resource bricolage of precision-targeted and entrepreneurship poverty alleviation is explored from the perspective of dynamic evolution. The main conclusions are as followings: 1.the number of entrepreneurial poverty alleviation objects has little significant impact on the topological characteristics of precision-targeted and entrepreneurship poverty alleviation resources bricolage super-network; 2.different numbers of poverty alleviation targets get the maximum value by adopting different decision preferences.

COVID-19 is a highly contagious disease, which is mainly caused by infected persons with symptoms and thus needs to be prevented from spreading by a large number of control measures. The study on the COVID-19 outbreak in Wuhan will help to understand the transmission characteristics of COVID-19 and help to design and evaluate appropriate prevention and control measures. Based on the data of COVID-19 cases reported in Wuhan from January 20 to March 29, a SEAIC model including asymptomatic infected persons was established. The initial stage of the epidemic was divided into three stages of transmission. The least square method was used to estimate the corresponding characteristic parameters. The results showed that the R₀ of the three transmission stages was 5.53, 4.023 and 0.016 respectively. The true proportion of asymptomatic infected is about 7.4%. With the use of the quarantine hospital, R0 quickly dropped below 1 and the epidemic was gradually brought under control.

In the application of artificial intelligence, the cooperation of multi robots can solve complex problems in practical engineering and become the research hotspot. In this paper, an input-constrained finite-time consistency algorithm is proposed to solve the formation control problem of nonholonomic mobile robots. By using the analysis tools such as algebraic graph theory, modern control theory and matrix theory, the formation problem of multi-robot system is transformed into the path tracking problem by introducing the virtual navigator. It is proved that the multi-robot system can realize the finite time convergence under the condition of input saturation. And the sufficient condition is obtained in finite time. Finally, the effectiveness of the proposed algorithm is verified by computer simulation.

With requirements of continuous improvements to customers’ service, Vehicle Routing Problems with Time Windows (VRPTW) attracted more and more attention. Aiming to minimize the total cost and to maximize customers’ satisfaction, a bi-objective integer programming model is established. A Hybrid Ant Colony Optimization (HACO) is designed to solve it. An elitist-ant strategy is set up to explore the bi-objective functions respectively and to get better non-dominant solutions. The evaporation factors are redefined to balance local and global search capabilities of the algorithm and to avoid premature convergence. NSGA-Ⅱ is used to guide the bi-objective optimizing process, a variable neighborhood search algorithm is used to expand the search space, in order to obtain the better Pareto solution set. The optimal parameter combination was determined by an orthogonal experiment, and the Solomon standard instances are used to test the performance of the algorithm. The simulation results show that the HACO can effectively solve the vehicle routing problem with time windows, and the performance of HACO has a significant improvement.

This article aims to conduct a systematic search and analysis of its technical composition, technological activity, distribution of patent rights and key patents through patent search on rice noodle cutting and packaging technology, and obtain rice noodle processing technology with the help of patent databases and patent navigation comparative analysis methods. The chart display of patent status in the field provides reference for decision-making for technology research and development, product operation and government departments for technology management, innovation layout and market development, and provides scientific reference for the industry’s intellectual property management, patent strategy formulation and patent protection early warning.