ELM Based Improved Layered Ensemble Architecture for Security Situation Prediction
Shuming Fan, Feng Li, Bin Wang, Xiaoyu Zhang, Peipei Yan · 2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC ) · 2022
N etwork security situation prediction can predict the future security situation and its changing trend based on the existing network security data. In order to improve the accuracy and efficiency of the network security situation prediction model, a extreme learning machine based layered ensemble network is proposed. This architecture takes extreme learning machine networks as base predictors and consists of two ensemble layers. Each layer considers both accuracy and diversity of the individual networks in constructing the ensemble by takes the strategy in which the best was selected after classification. The first ensemble layer tries to find an appropriate lag, while the second one employs the obtained lag for forecasting. The proposed model has been tested in comparison experimental. The results have revealed clearly that compared with the layered ensemble architecture based on multilayer perceptron, new model not only improves the prediction accuracy but also improves the time efficiency by 1–2 orders of magnitude.