典型文献
An Efficient Correlation-Aware Anomaly Detection Framework in Cellular Network
文献摘要：
Nowadays,the fifth-generation(5G)mo-bile communication system has obtained prosperous development and deployment,reshaping our daily lives.However,anomalies of cell outages and conges-tion in 5G critically influence the quality of experience and significantly increase operational expenditures.Although several big data and artificial intelligence-based anomaly detection methods have been proposed for wireless cellular systems,they change distributions of the data and ignore the relevance among user activ-ities,causing anomaly detection ineffective for some cells.In this paper,we propose a highly effective and accurate anomaly detection framework by utiliz-ing generative adversarial networks(GAN)and long short-term memory(LSTM)neural networks.The framework expands the original dataset while simul-taneously keeping the distribution of data unchanged,and explores the relevance among user activities to further improve the system performance.The results demonstrate that our framework can achieve 97.16％accuracy and 2.30％false positive rate by utilizing the correlation of user activities and data expansion.
文献关键词：
中图分类号：
作者姓名：
Haihan Nan;Xiaoyan Zhu;Jianfeng Ma
作者机构：
State Key Laboratory of Integrated Service Networks,Xidian University,Xi'an 710071,China;School of Cyber Engineering,Xidian University,Xi'an 710071,China
文献出处：
引用格式：
[1]Haihan Nan;Xiaoyan Zhu;Jianfeng Ma-.An Efficient Correlation-Aware Anomaly Detection Framework in Cellular Network)[J].中国通信（英文版）,2022(08):168-180
A类：
conges,utiliz
B类：
Efficient,Correlation,Aware,Anomaly,Detection,Framework,Cellular,Network,Nowadays,fifth,generation,bile,communication,has,obtained,prosperous,development,deployment,reshaping,our,daily,lives,However,anomalies,outages,critically,influence,quality,experience,significantly,increase,operational,expenditures,Although,several,big,artificial,intelligence,anomaly,detection,methods,have,been,proposed,wireless,cellular,systems,they,distributions,ignore,relevance,among,user,causing,ineffective,some,cells,In,this,paper,highly,accurate,framework,by,generative,adversarial,networks,GAN,long,short,term,memory,neural,expands,original,dataset,while,simul,taneously,keeping,unchanged,explores,activities,further,improve,performance,results,demonstrate,that,achieve,accuracy,false,positive,utilizing,correlation,expansion
AB值：
0.662069
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
