期刊文献+

基于云计算的船舶通信网络入侵特征提取方法 被引量:6

Intrusion feature extraction method for ship communication network based on cloud computing
下载PDF
导出
摘要 普通船舶通信特征提取方法,不能根据入侵数据所处位置,快速完成数据特征的提取。为有效解决上述问题,设计基于云计算的船舶通信网络入侵特征提取方法。通过船舶通信入侵问题描述、特征数据的信号处理,完成云计算环境下,船舶通信入侵特征数据的确定。通过入侵特征架构的搭建、多序列船舶数据入侵特征提取,完成基于云计算的船舶通信网络入侵特征提取方法的搭建。设计对比实验结果表明,新型特征提取方法,与传统方法相比,可更加准确的确定入侵数据所处位置,并适当缩短完成数据特征提取所需时间。 The extraction method of common ship communication features can not extract the data features quickly according to the location of the intrusion data. In order to solve the above problems, a method for extracting intrusion characteristics of ship communication network based on cloud computing is designed. Through the description of the ship communication intrusion and the signal processing of the characteristic data, the identification of the characteristic data of the ship's communication intrusion is completed under the cloud computing environment. Through the building of Intrusion Feature Architecture and the extraction of multi sequential ship data intrusion feature, we complete the construction of intrusion detection method based on cloud computing. The results of design contrast experiments show that compared with the traditional methods, the new feature extraction method can identify the location of the intrusion data more accurately and shorten the time needed to complete the data feature extraction.
作者 杨文虎
机构地区 山东职业学院
出处 《舰船科学技术》 北大核心 2018年第5X期145-147,共3页 Ship Science and Technology
关键词 云计算 传统通信 网络入侵 特征提取 问题描述 信号处理 特征架构 多序列 cloud computing traditional communication network intrusion feature extraction problem description signal processing feature architecture multi sequence
  • 相关文献

参考文献4

二级参考文献29

  • 1史坤鹏,穆钢,李婷,吕陆.基于经验模式分解的聚类树方法及其在同调机组分群中的应用[J].电网技术,2007,31(22):21-25. 被引量:22
  • 2GREZL F,FOUSEK P. Optimizing bottleneck feature for LVCSR[C]//IEEE International Conference on Acouslics, Speech and Signal Processing,2008 :4729-4732.
  • 3LI Deng. An overviewof deep-structured learning for in formation processing[C]//Proceedings of the Asian Pa- cific Signal and Information Processing-Annual Summit and Conference,2011 : 1-4.
  • 4HINTON G E,SALAKHUTDINOV R N R. Reducing the dimensionality of data with neural networks[J]. Sci- ence,2006,313(5786) :504-507.
  • 5YU D,SELTZER M L. Improved bottleneck features u- sing pretrained deep neural network [C]//INTER SPEECH, 2011: 237-240.
  • 6HINTON G E, OSINDERO S, TEH Y W. The fast learning algorithm for deep nets [J]. Neural Computa- tion,2006,18(7) :1527- 1554.
  • 7BAO Yebo,JIANG Hui,LIU Cong, et al. Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems[C]// Proceedings of the IEEE llth International Conference on Signal Processing,2012 :562-566.
  • 8百度百科,归一化,http://baike.baidu.corn/view/829823.htm,2015/9/21.
  • 9文俊,刘天琪,李兴源,任景.在线识别同调机群的优化支持向量机算法[J].中国电机工程学报,2008,28(25):80-85. 被引量:31
  • 10潘炜,刘文颖,杨以涵.采用受扰轨迹和独立分量分析技术识别同调机群的方法[J].中国电机工程学报,2008,28(25):86-92. 被引量:20

共引文献15

同被引文献39

引证文献6

二级引证文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部