摘要
舰船网络非法入侵行为识别受到识别算法的影响,使得误检率较高。因此,提出特征优化和机器学习算法的舰船网络非法入侵行为识别方法设计。采用自适应遗传算法,完成舰船网络数据特征优化处理,有效提升了识别效率。以SVM算法为核心设计行为分类算法,完成舰船网络数据的分类。最后,通过构建网络非法入侵行为识别模型,实现非法入侵行为的准确识别。实验结果表明:从单一类型非法入侵行为识别结果分析,本文方法的平均误检率相比传统方法降低了4.8%,8.69%;从多种类型非法入侵行为识别结果分析,本文方法将平均误检率分别降低了10.02%、10.74%。
Due to the influence of recognition algorithm, the identification of illegal intrusion in ship network has a high false detection rate. Therefore, this paper proposes the design of feature optimization and machine learning algorithm to identify the illegal intrusion behavior of the ship network. Adaptive genetic algorithm is used to optimize the characteristics of ship network data, which effectively improves the recognition efficiency. The behavior classification algorithm is designed based on SVM algorithm to complete the classification of ship network data. Finally, the identification model of illegal intrusion behavior is constructed to realize the accurate identification of illegal intrusion. The experimental results show that: compared with the traditional methods, the average false detection rate of the proposed method is reduced by 4.8% and8.69% from the single type of illegal intrusion identification results;from the multiple types of illegal intrusion identification results, the average false detection rate of the proposed method is reduced by 10.02% and 10.74% respectively.
作者
黄琨
吴雪琴
舒晓苓
HUANG Kun;WU Xue-qin;SHU Xiao-ling(Southwest Jiaotong University,Chengdu 6101031,China;Urban Vocational College of Sichuan,Chengdu 610100,China;Chengdu College,University of Electronic Science and Technology of China,Chengdu 610036,China)
出处
《舰船科学技术》
北大核心
2021年第12期157-159,共3页
Ship Science and Technology
基金
四川教育厅研究项目(SCJY20190924)
关键词
舰船
特征优化
机器学习
非法入侵
ship
feature optimization
machine learning
illegal intrusion
