Jiaying Zhang

Bio: Jiaying Zhang is an academic researcher from Tianjin University of Technology. The author has contributed to research in topics: Support vector machine & Data mining. The author has an hindex of 1, co-authored 1 publications receiving 4 citations.

Situation prediction of large-scale Internet of Things network security

Abstract: The Internet of Things (IoT) is a new technology rapidly developed in various fields in recent years. With the continuous application of the IoT technology in production and life, the network security problem of IoT is increasingly prominent. In order to meet the challenges brought by the development of IoT technology, this paper focuses on network security situational awareness. The network security situation awareness is basic of IoT network security. Situation prediction of network security is a kind of time series forecasting problem in essence. So it is necessary to construct a modification function that is suitable for time series data to revise the kernel function of traditional support vector machine (SVM). An improved network security situation awareness model for IoT is proposed in this paper. The sequence kernel support vector machine is obtained and the particle swarm optimization (PSO) method is used to optimize related parameters. It proves that the method is feasible by collecting the boundary data of a university campus IoT network. Finally, a comparison with the PSO-SVM is made to prove the effectiveness of this method in improving the accuracy of network security situation prediction of IoT. The experimental results show that PSO-time series kernel support vector machine is better than the PSO-Gauss kernel support vector machine in network security situation prediction. The application of the Hadoop platform also enhances the efficiency of data processing.

The wind power prediction based on hierarchical clustering method

Abstract: An empirical mode decomposition-extreme learning machine (EMD-ELM) wind power prediction method based on the hierarchical clustering method was proposed to solve the current problem of insufficient power prediction accuracy of wind power stations in this paper. This method uses the aggregation algorithm of hierarchical clustering to cluster the data with similar weather conditions, and uses the EMD method to decompose the power sequence of each group, which can obtain relatively stable data components, and finally uses the ELM method to predict and combine each component. Compared with the ELM wind power prediction model, the numerical simulation shows that the EMD-ELM wind power prediction model based on hierarchical clustering method makes the data characteristics of similar weather conditions more obvious, the value of each evaluation index is better and the model has higher prediction accuracy.

A prediction model of cloud security situation based on evolutionary functional network

Abstract: Aiming at the dynamic uncertainty and prediction accuracy of security situation prediction in complex cloud network environment, a prediction model of cloud security situation based on evolutionary functional network is proposed. Firstly, the evolutionary functional network model is constructed by combining the evolutionary algorithm with the functional network, which solves the problem of basis function selection and basis function coefficient correction of the prediction model. Secondly, the stochastic approximation algorithm is used to process and comprehend the cloud security situation elements, and the computational complexity of the prediction model is reduced by the dimensionality reduction method. Finally, by constructing the credibility matrix of the uncertain influence relationship of security situation elements, we use the multivariate non-linear regression algorithm to predict the cloud security situation. The simulation results show that compared with BP model and RAN-RBF model, the prediction accuracy of the proposed model is improved by 8.2% and 6.9% respectively, and the convergence efficiency is improved by 12.3% and 10.8% respectively.

Network Security Situation Prediction of Improved Lanchester Equation Based on Time Action Factor

Abstract: Existing network security situational awareness assessment and prediction are not fully considered network defense utility, time factor and other indicators, and the randomness of attacks and the accuracy of the prediction of attack intentions and methods may appear both in active and passive defense this situation leads to uncertainty in attack prediction, which makes it impossible to discover defects in the network system in a timely manner, and there is a lack of effective emergency response strategies for impending or already occurring network attacks. Therefore, this paper proposes a network behavior calculation model based on the Lanchester equation of time action factor is proposed. This paper uses smooth differential manifold homeomorphic transformation to define network behavior, defines the calculation method of behavior utility based on the principle of differential geometry, combines the second linear law of the Lanchester equation and the square law, and uses the time action factor to defend the active defense. The simulation results show that the model can be used to analyze the network offensive and defensive process, and can effectively predict the network offensive and defensive results under both active and passive defense.

Method of network security situation prediction based on IHS_LSSVR

Abstract: To address the situation prediction problem in the network security situation awareness, this paper presents a prediction method of network security situation based on the algorithm of IHS_LSSVR. An improved Harmony Search(IHS)algorithm is proposed since the principle of the Harmony Search(HS)algorithm is studied. This method embeds the Least Squares Support Vector machine for Regression(LSSVR)in the process of the objective function calculation of the improved harmony search algorithm, and takes advantage of the global searching ability of the IHS algorithm to optimize the parameters of the LSSVR. To some extent, this enhances the learning ability and generalization ability of the LSSVR. Simulation experiments show that this method has better prediction affection in comparison with other existing prediction methods.

Application Strategies of Waste Sorting Facilities Based on Internet of Things

Abstract: The sprawling urbanization in China has given birth to the increasingly prominent “garbage-teeming city,” and hence how to use the Internet of things to turn “garbage-teeming city” into “garbage mineral” is the issue in this paper. Compared with the waste sorting facility systems in developed countries, China is still suffering from single function, imperfect mechanisms and residents’ weak awareness of trash sorting. Through the analysis of the intelligent solar garbage bin developed by Lucia from Cambridge University and the smart sorting system of Canadian “Oscar” and Japanese ZenRobotics Recycler, this paper puts forward an efficient and accurate smart system based on Zigbee technology for the intelligent sorting mechanism, garbage sorting facilities and knowledge popularization. The smart system monitoring environmental and circulating garbage sorting will be implanted with ICL7107 chips, and the thoughtful and reasonable reward and punishment mechanism for garbage classification will also be combined with APP or mini program.

Network security situation prediction model based on grey wolf optimization algorithm to optimize support vector machine

Abstract: When making network security situation prediction, researchers usually use historical network security situation values to make predictions. Such predictive models often do not perform well on complex networks with multi-source inputs. Aiming at the problem that the prediction accuracy of the existing prediction models is not high in complex networks, a network security situation prediction model based on grey wolf optimization algorithm to optimize support vector machine is proposed. In this paper, the situation elements are first accumulated, and then the support vector machine is used to independently predict different situation elements in the network, and finally the predicted values are fused into the network security situation value. The parameters of the support vector machine are determined using the grey wolf optimization algorithm. The simulation results show that the model has a good prediction effect.