Establishment of nonlinear network security situational awareness model based on random forest under the background of big data

Abstract

In order to explore the establishment of a nonlinear network security situational awareness model based on random forest in the context of big data, a multi-level network security knowledge system evaluation model based on random forest is proposed. This article proposes a multi-level CSSA analysis system and then uses random memory algorithm to create a CSSA evaluation model. Also, it proposes a CSSA multi-level analysis framework and then uses random forest algorithm to build a CSSA evaluation model. A random vector distribution of the same values is used for all forest trees. In this article, the interval [0,1] is used to quantitatively describe the weight of the security level. The training sample ratio of test samples is 110:40, in order to predict the security of the network, the prediction of knowledge is closer to the true value, and the complexity of multi-level security is predicted. Use unusual forests. The tree returns the most recommended part, which is a more realistic assessment of network security. The experimental results show that considering the network security situation, the prediction performance of this method is closer to the actual value, and the performance is better than the other two methods. Therefore, perception of multi-level security situations can be effectively predicted using random access memory. It is proved that random forest is faster and more efficient in network security.

A novel network security situation assessment technology for zero-day attacks based on improved adversarial autoencoder

“…Currently, machine learning-based network security situation assessment methods primarily utilize supervised learning approaches, which necessitate a considerable amount of labeled sample data. He [7] et al established a nonlinear network situation assessment model based on Random Forest, and achieved good assessment results. Yang [8] et al constructed a dual channel Convolutional neural network (CNN) intrusion detection model, organically combined multi-channel feature learning and cross channel feature dependency learning, and used genetic algorithm (GA) to find the optimal topology of CNN, obtaining good results.…”

A Multi-Feature Fusion and Situation Awareness-Based Method for Fatigue Driving Level Determination

“…Throughout the driver's journey, various elements are considered to determine the degree of goal attainment and assess the current outcome using different data types and information. Future state projection predicts potential future states based on the current state [26], estimating the driver's future driving risk. In summary, this paper studies the current and present situation levels to identify potential future trends and issue warnings for high-risk fatigue states.…”