多源头网络用户访问信息自适应识别算法
|
摘要
为了解决传统算法学习规则有效性低、无法保证学习性能、匹配模板不全面、容易出现误识别现象的问题,提出一种改进的反向传播(back propagation,BP)神经网络算法研究多源头网络用户访问信息自适应识别问题。对多源头网络用户访问信息进行数据清洗处理,用多源头网络用户访问矩阵对全部会话集合进行描述;在矩阵中引入网络用户位置信息,将得到的信息保存至数据库,构成信息集。将一段时间内用户访问日志构成用户访问路径数据,依据访问请求抵达顺序,将其保存至相应用户缓冲区。把多源头网络用户访问路径当成隐马尔科夫模型的状态转移序列,将网页中信息集当成状态输出符号集,通过离散隐马尔科夫模型对不同源头网络用户访问信息进行分析,提取其特征。将多源头网络用户访问不同种类信息的概率特征作为输入,建立改进BP神经网络算法,得到的输出结果即为多源头网络用户访问信息自适应识别结果。结果表明:采用的BP神经网络算法学习性能优;所提算法识别准确性高。可见所提算法识别结果可靠。
In order to solve the problems of low efficiency of learning rules,insufficient learning performance,incomplete matching templates and easy to misidentify in traditional algorithms,an improved back propagation( BP) neural network algorithm was proposed to study the self-adaptive identification of multi-source network users' access information. The multi-source network user access information was cleaned by data. The multi-source network user access matrix was used to describe all session sets. The location information of network user was introduced into the matrix and saved to the database to form the information set. A period of time the user access were constructed to user access path to the data access request,based on the arrival order,save it to the corresponding user buffer. The multi-source network user access path was regarded as the state transition sequence of hidden Markov model,and the information set in the web page was regarded as the state output symbol set. The discrete hidden Markov model was used to analyze the access information of different source network users and extract their characteristics. Taking the probabilistic characteristics of multi-source network users' access to different kinds of information as input,an improved BP neural network algorithm was established. The output result was the self-adaptive recognition result of multi-source network users' access information. The results show that the BP neural network algorithm has excellent learning performance and the algorithm has high recognition accuracy. The result shows that the algorithm is reliable.
In order to solve the problems of low efficiency of learning rules,insufficient learning performance,incomplete matching templates and easy to misidentify in traditional algorithms,an improved back propagation( BP) neural network algorithm was proposed to study the self-adaptive identification of multi-source network users' access information. The multi-source network user access information was cleaned by data. The multi-source network user access matrix was used to describe all session sets. The location information of network user was introduced into the matrix and saved to the database to form the information set. A period of time the user access were constructed to user access path to the data access request,based on the arrival order,save it to the corresponding user buffer. The multi-source network user access path was regarded as the state transition sequence of hidden Markov model,and the information set in the web page was regarded as the state output symbol set. The discrete hidden Markov model was used to analyze the access information of different source network users and extract their characteristics. Taking the probabilistic characteristics of multi-source network users' access to different kinds of information as input,an improved BP neural network algorithm was established. The output result was the self-adaptive recognition result of multi-source network users' access information. The results show that the BP neural network algorithm has excellent learning performance and the algorithm has high recognition accuracy. The result shows that the algorithm is reliable.
引文
1黄磊,李寿山,王晶晶.基于认证用户信息的微博用户类型识别方法[J].计算机科学与探索,2015,9(6):719-725Huang Lei,Li Shoushan,Wang Jingjing. User-type classification in micro-blog based on information of authenticated user[J]. Journal of Frontiers of Computer Science&Technology,2015,9(6):719-725
2 史达,杨洋.一种面向多层次异构信息平台的数据访问链路识别算法[J].信息与控制,2014,43(1):14-18Shi Da,Yang Yang. A database operation route identification method for multi-layer heterogeneous information architecture[J]. Information and Control,2014,43(1):14-18
3 王末,王卷乐. Web环境下地学数据共享用户行为模式分析[J].地球信息科学学报,2016,18(9):1174-1183Wang Mo,Wang Juanle. A study on the user behavior of geoscience data sharing based on Web usage mining[J]. Journal of Geo-Information Science,2016,18(9):1174-1183
4 Sun W,Zhang X,Peeta S,et al. A self-adaptive dynamic recognition model for fatigue driving based on multi-source information and two levels of fusion[J]. Sensors,2015,15(9):24191-24213
5 史姣丽,黄传河,王晶,等.云存储下多用户协同访问控制方案[J].通信学报,2016,37(1):88-99Shi Jiaoli,Huang Chuanhe,Wang Jing,et al. Multi-user collaborative access control scheme in cloud storage[J]. Journal on Communications,2016,37(1):88-99
6 张晶.大数据平台下数据库访问信息安全管理仿真[J].计算机仿真,2017,34(7):436-440Zhang Jing. Simulation of database access information security management under big data platform[J]. Computer Simulation,2017,34(7):436-440
7 王中卿,李寿山,周国栋.基于文本与社交信息的用户群组识别[J].软件学报,2017,28(9):2468-2480Wang Zhongqing,Li Shoushan,Zhou Guodong. Personal group recommendation via textual and social information[J]. Journal of Software,2017,28(9):2468-2480
8 刘珏,王永.网络疑似入侵环境下的最优接口访问控制模型仿真[J].计算机测量与控制,2016,24(11):182-184Liu Jue,Wang Yong. Simulation of optimal interface access control model in network suspected intrusion[J]. Computer Measurement&Control,2016,24(11):182-184
9 吴铮,于洪涛,刘树新,等.基于信息熵的跨社交网络用户身份识别方法[J].计算机应用,2017,37(8):2374-2380Wu Zheng,Yu Hongtao,Liu Shuxin,et al. User identification across multiple social networks based on information entropy[J]. Journal of Computer Applications,2017,37(8):2374-2380
10 孙彬.基于ABS细粒度隐私隔绝的身份追溯研究[J].电子设计工程,2018,26(3):10-14Sun Bin. Research on fine-grained privacy preserving identity traceability based on ABS[J]. Electronic Design Engineering,2018,26(3):10-14
11 虞尚智.模糊云计算环境下特定数据目标资源识别定位[J].科技通报,2015,31(10):157-159Yu Shangzhi. Target recognition and location of specific data resources under fuzzy cloud computing environment[J]. Bulletin of Science and Technology,2015,31(10):157-159
12 许闻秋,雒江涛,杨军超.基于Hadoop的校园网视频流量访问偏好分析[J].重庆邮电大学学报(自然科学版),2016,28(6):897-902Xu Wenqiu,Luo Jiangtao,Yang Junchao. Hadoop based analysis of access preference for campus video traffic[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2016,28(6):897-902
13 Singha J,Laskar R H. Recognition of global hand gestures using self co-articulation information and classifier fusion[J]. Journal on Multimodal User Interfaces,2016,10(1):1-17
14 胡开先,梁英,许洪波,等.一种社会网络用户身份特征识别方法[J].计算机研究与发展,2016,53(11):2630-2644Hu Kaixian,Liang Ying,Xu Hongbo,et al. A method for social network user identity feature recognition[J]. Journal of Computer Research and Development,2016,53(11):2630-2644
15 耿晓中.云计算环境中数据分布式强制访问控制算法[J].科学技术与工程,2017,17(29):114-119Geng Xiaozhong. Distributed mandatory access control algorithm in cloud computing environment[J]. Science Technology and Engineering,2017,17(29):114-119
2 史达,杨洋.一种面向多层次异构信息平台的数据访问链路识别算法[J].信息与控制,2014,43(1):14-18Shi Da,Yang Yang. A database operation route identification method for multi-layer heterogeneous information architecture[J]. Information and Control,2014,43(1):14-18
3 王末,王卷乐. Web环境下地学数据共享用户行为模式分析[J].地球信息科学学报,2016,18(9):1174-1183Wang Mo,Wang Juanle. A study on the user behavior of geoscience data sharing based on Web usage mining[J]. Journal of Geo-Information Science,2016,18(9):1174-1183
4 Sun W,Zhang X,Peeta S,et al. A self-adaptive dynamic recognition model for fatigue driving based on multi-source information and two levels of fusion[J]. Sensors,2015,15(9):24191-24213
5 史姣丽,黄传河,王晶,等.云存储下多用户协同访问控制方案[J].通信学报,2016,37(1):88-99Shi Jiaoli,Huang Chuanhe,Wang Jing,et al. Multi-user collaborative access control scheme in cloud storage[J]. Journal on Communications,2016,37(1):88-99
6 张晶.大数据平台下数据库访问信息安全管理仿真[J].计算机仿真,2017,34(7):436-440Zhang Jing. Simulation of database access information security management under big data platform[J]. Computer Simulation,2017,34(7):436-440
7 王中卿,李寿山,周国栋.基于文本与社交信息的用户群组识别[J].软件学报,2017,28(9):2468-2480Wang Zhongqing,Li Shoushan,Zhou Guodong. Personal group recommendation via textual and social information[J]. Journal of Software,2017,28(9):2468-2480
8 刘珏,王永.网络疑似入侵环境下的最优接口访问控制模型仿真[J].计算机测量与控制,2016,24(11):182-184Liu Jue,Wang Yong. Simulation of optimal interface access control model in network suspected intrusion[J]. Computer Measurement&Control,2016,24(11):182-184
9 吴铮,于洪涛,刘树新,等.基于信息熵的跨社交网络用户身份识别方法[J].计算机应用,2017,37(8):2374-2380Wu Zheng,Yu Hongtao,Liu Shuxin,et al. User identification across multiple social networks based on information entropy[J]. Journal of Computer Applications,2017,37(8):2374-2380
10 孙彬.基于ABS细粒度隐私隔绝的身份追溯研究[J].电子设计工程,2018,26(3):10-14Sun Bin. Research on fine-grained privacy preserving identity traceability based on ABS[J]. Electronic Design Engineering,2018,26(3):10-14
11 虞尚智.模糊云计算环境下特定数据目标资源识别定位[J].科技通报,2015,31(10):157-159Yu Shangzhi. Target recognition and location of specific data resources under fuzzy cloud computing environment[J]. Bulletin of Science and Technology,2015,31(10):157-159
12 许闻秋,雒江涛,杨军超.基于Hadoop的校园网视频流量访问偏好分析[J].重庆邮电大学学报(自然科学版),2016,28(6):897-902Xu Wenqiu,Luo Jiangtao,Yang Junchao. Hadoop based analysis of access preference for campus video traffic[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2016,28(6):897-902
13 Singha J,Laskar R H. Recognition of global hand gestures using self co-articulation information and classifier fusion[J]. Journal on Multimodal User Interfaces,2016,10(1):1-17
14 胡开先,梁英,许洪波,等.一种社会网络用户身份特征识别方法[J].计算机研究与发展,2016,53(11):2630-2644Hu Kaixian,Liang Ying,Xu Hongbo,et al. A method for social network user identity feature recognition[J]. Journal of Computer Research and Development,2016,53(11):2630-2644
15 耿晓中.云计算环境中数据分布式强制访问控制算法[J].科学技术与工程,2017,17(29):114-119Geng Xiaozhong. Distributed mandatory access control algorithm in cloud computing environment[J]. Science Technology and Engineering,2017,17(29):114-119