An Improved Prediction Model for the Network Security Situation
This research seeks to improve the long training time of traditional methods that use support vector machine (SVM) for cyber security situation prediction. This paper proposes a cyber security situation prediction model based on the MapReduce and SVM. The base classifier for this model uses an SVM. In order to find the optimal parameters of the SVM, parameter optimization is performed by the Cuckoo Search (CS). Considering the problem of time cost when a data set is too large, we choose to use MapReduce to perform distributed training on SVMs to improve training speed. Experimental results show that the SVM network security situation prediction model using MapReduce and CS has improved the accuracy and decreased the training time cost compared to the traditional SVM prediction model.
KeywordsNetwork security situation Prediction SVM Acceleration
This work has been supported by the National Key Research and Development Program of China (Grant No. 2016YFB0800700) and the National Natural Science Foundation of China (Grant No. 61772070).
- 2.Hao, H., Hongqi, Z., Yuling, L.: Quantitative method for network security situation based on attack prediction. Secur. Commun. Netw. 2017, 19 (2017)Google Scholar
- 6.Ding, S., Zhu, Z., Zhang, X.: An overview on semi-supervised support vector machine. Neural Comput. Appl. 28, 1–10 (2017)Google Scholar
- 9.Madani, Y., Erritali, M., Bengourram, J.: Sentiment analysis using semantic similarity and Hadoop MapReduce. Knowl. Inf. Syst. 8, 413–436 (2018)Google Scholar
- 14.Vijayashree, J., Sultana, H.P.: A machine learning framework for feature selection in heart disease classification using improved particle swarm optimization with support vector machine classifier (2018)Google Scholar