一种云计算环境下海量数据安全特征提取算法

详细信息    查看全文 | 推荐本文 |

英文篇名：A Massive data security feature extraction algorithm in cloud computing environment 作者：胡声秋 ; 吴玲丽 英文作者：HU Sheng-qiu;WU Ling-li;China Mobile Communications Group Chongqing Co.,Ltd.; 关键词：云计算环境 ; 特征提取 ; 网络安全 ; 离散狼群算法 英文关键词：cloud computing environment;;feature extraction;;network security;;discrete wolf pack algorithm 中文刊名：HDZJ 英文刊名：Information Technology 机构：中国移动通信集团重庆有限公司; 出版日期：2019-01-17 出版单位：信息技术 年：2019 期：v.43;No.326 语种：中文; 页：HDZJ201901024 页数：4 CN：01 ISSN：23-1557/TN 分类号：101-104

摘要

面对云计算环境下大规模数据和多变入侵行为,提出了一种云计算环境下海量数据安全特征提取算法。该算法在定义最佳提取特征指标的基础上,构建基于改进离散狼群算法(Improved Discrete Wolf Pack Algorithm,IDWPA)的安全特征提取模型,最大限度的降低了提取特征冗余度和问题复杂度。针对安全特征提取问题特点,重新设计IDWPA个体编码方式和更新策略,并将IDWPA应用于安全特征提取模型求解,从而实现了最佳安全特征提取。仿真结果表明,相比于其他特征提取算法,基于该算法特征提取的数据分类准确率明显改善。
        Aiming at large-scale data and multiple intrusion behaviors in cloud computing environ-ment,an algorithm for extracting security features of large-scale data in cloud computing environment is proposed. On the basis of defining the best feature extraction index,a security feature extraction model based on improved discrete wolf pack algorithm( IDWPA) is constructed to minimize the redundancy and complexity of feature extraction. Aiming at the characteristics of security feature extraction,the particle encoding method and update strategy of IDWPA are redesigned,and IDWPA is applied to solve the model of security feature extraction to achieve the best security feature extraction. The simulation results show that,compared with other feature extraction algorithms,the accuracy of data classification based on this algorithm is significantly improved.

引文

[1]Mell P,Grance T.The NIST definition of cloud computing(draft)[J].NIST special publication,2011,800(145):7.
    [2]Zhao Zheng,Wang Lei,Liu Huan,et al.On similarity preserving feature selection[J].IEEE Trans on Knowledge and Data Engineering,2013,25(3):619-632.
    [3]王珺,卫金茂,张璐.基于保留分类信息的多任务特征学习算法[J].计算机研究与发展,2017,54(3):537-548.
    [4]Feng D C,Chen F,Xu W L.Detecting local manifold structure for unsupervised feature selection[J].Acta Automatica Sinica,2014,40(10):2253-2261.
    [5]孙广路,宋智超,刘金来,等.基于最大信息系数和近似马尔科夫毯的特征选择方法[J].自动化学报,2017,43(5):795-805.
    [6]仇利克,郭忠文,刘青,等.基于冗余分析的特征选择算法[J].北京邮电大学学报,2017,40(1):36-41.
    [7]吴丽云,李生林,甘旭升,等.基于PLS特征提取的网络异常入侵检测CVM模型[J].控制与决策,2017,32(4):755-758.
    [8]LIU C A,YAN X H,LIU C Y.The wolf colony algorithm and its application[J].Chinese Journal of Electronics,2011,20(2):212-216.
    [9]吴虎胜,张凤鸣,吴庐山.一种新的群体智能算法一狼群算法[J].系统工程与电子技术,2013,35(11):2430-2438.
    [10]王艳娇,李晓杰,肖婧.基于动态学习策略的群集蜘蛛优化算法[J].控制与决策,2015,30(9):1575-1582.
    [11]刘志新,刘强,袁亚洲,等.基于贝叶斯估计与虚拟力导向混合遗传算法的无线传感网络定位方案[J].控制与决策,2013,28(6):899-903.