检索结果-内蒙古大学图书馆

Improving Auction Mechanisms for Online Real-Time Bidding Advertising with a Two-stage Resale Model

IFAC-PapersOnLine 2017年第1期50卷 13575-13580页

作者： Qin, Rui Yuan, Yong Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China Research Center of Military Computational Experiments and Parallel System National University of Defense Technology Changsha China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China

Real Time Bidding (RTB), widely publicized as one of the most promising big-data-driven business models for online computational advertising, has the potential of effectively monetizing user clicks and impressions via two-stage auctions with resale. Demand side platforms (DSPs) play a key role as intermediators in this auction process. Typically, the first-stage auctions will be conducted separately in each DSP to determine one winning advertiser registered on it, and in the second-stage auction, each DSP submits a bid based on its winning advertiser's bid to the ad exchange platform (AdX). The highest-bid DSP wins the ad impression from AdX and resells it to its winning advertiser in pursuit of the intermediate fee. This two-stage resale auction is a critical component in maintaining the effectiveness and efficiency of RTB ecosystems. In this paper, we strive to identify and design potential improvements for this auction mechanism with the aim of enhancing the total revenue of both advertisers and DSPs. We also validated our proposed auction mechanisms using the computational experiment approach. The experimental results indicate that our proposed mechanisms can make both advertisers and DSPs better off. Our work represents the first step towards a new research area of optimal mechanism design for RTB auctions, and is expected to provide useful managerial insights in RTB market practice. © 2017

关键词： Sales Commerce Machine design Auction mechanisms Computational advertisings Computational experiment Critical component Demand side Effectiveness and efficiencies Optimal mechanism designs Real time

来源：评论

学校读者我要写书评

暂无评论

Genetic drivers of heterogeneity in type 2 diabetes pathophysiology

引用

Nature 2024年第8003期627卷 347-357页

作者： Ken Suzuki Konstantinos Hatzikotoulas Lorraine Southam Henry J Taylor Xianyong Yin Kim M Lorenz Ravi Mandla Alicia Huerta-Chagoya Giorgio E M Melloni Stavroula Kanoni Nigel W Rayner Ozvan Bocher Ana Luiza Arruda Kyuto Sonehara Shinichi Namba Simon S K Lee Michael H Preuss Lauren E Petty Philip Schroeder Brett Vanderwerff Mart Kals Fiona Bragg Kuang Lin Xiuqing Guo Weihua Zhang Jie Yao Young Jin Kim Mariaelisa Graff Fumihiko Takeuchi Jana Nano Amel Lamri Masahiro Nakatochi Sanghoon Moon Robert A Scott James P Cook Jung-Jin Lee Ian Pan Daniel Taliun Esteban J Parra Jin-Fang Chai Lawrence F Bielak Yasuharu Tabara Yang Hai Gudmar Thorleifsson Niels Grarup Tamar Sofer Matthias Wuttke Chloé Sarnowski Christian Gieger Darryl Nousome Stella Trompet Soo-Heon Kwak Jirong Long Meng Sun Lin Tong Wei-Min Chen Suraj S Nongmaithem Raymond Noordam Victor J Y Lim Claudia H T Tam Yoonjung Yoonie Joo Chien-Hsiun Chen Laura M Raffield Bram Peter Prins Aude Nicolas Lisa R Yanek Guanjie Chen Jennifer A Brody Edmond Kabagambe Ping An Anny H Xiang Hyeok Sun Choi Brian E Cade Jingyi Tan K Alaine Broadaway Alice Williamson Zoha Kamali Jinrui Cui Manonanthini Thangam Linda S Adair Adebowale Adeyemo Carlos A Aguilar-Salinas Tarunveer S Ahluwalia Sonia S Anand Alain Bertoni Jette Bork-Jensen Ivan Brandslund Thomas A Buchanan Charles F Burant Adam S Butterworth Mickaël Canouil Juliana C N Chan Li-Ching Chang Miao-Li Chee Ji Chen Shyh-Huei Chen Yuan-Tsong Chen Zhengming Chen Lee-Ming Chuang Mary Cushman John Danesh Swapan K Das H Janaka de Silva George Dedoussis Latchezar Dimitrov Ayo P Doumatey Shufa Du Qing Duan Kai-Uwe Eckardt Leslie S Emery Daniel S Evans Michele K Evans Krista Fischer James S Floyd Ian Ford Oscar H Franco Timothy M Frayling Barry I Freedman Pauline Genter Hertzel C Gerstein Vilmantas Giedraitis Clicerio González-Villalpando Maria Elena González-Villalpando Penny Gordon-Larsen Myron Gross Lindsay A Guare Sophie Hackinger Liisa Hakaste Sohee Han Andrew T Hattersley Christian Herder Momoko Horikoshi Annie-Green Howard Willa Centre for Genetics and Genomics Versus Arthritis Centre for Musculoskeletal Research Division of Musculoskeletal and Dermatological Sciences University of Manchester Manchester UK. Department of Diabetes and Metabolic Diseases Graduate School of Medicine University of Tokyo Tokyo Japan. Department of Statistical Genetics Osaka University Graduate School of Medicine Suita Japan. Institute of Translational Genomics Helmholtz Zentrum München German Research Center for Environmental Health Neuherberg Germany. konstantinos.hatzikotoulas@helmholtz-munich.de. Institute of Translational Genomics Helmholtz Zentrum München German Research Center for Environmental Health Neuherberg Germany. Center for Precision Health Research National Human Genome Research Institute National Institutes of Health Bethesda MD USA. British Heart Foundation Cardiovascular Epidemiology Unit Department of Public Health and Primary Care University of Cambridge Cambridge UK. Heart and Lung Research Institute University of Cambridge Cambridge UK. Department of Epidemiology School of Public Health Nanjing Medical University Nanjing China. Department of Biostatistics and Center for Statistical Genetics University of Michigan Ann Arbor MI USA. Corporal Michael J. Crescenz VA Medical Center Philadelphia PA USA. Department of Systems Pharmacology and Translational Therapeutics University of Pennsylvania Perelman School of Medicine Philadelphia PA USA. Department of Genetics University of Pennsylvania Perelman School of Medicine Philadelphia PA USA. Programs in Metabolism and Medical and Population Genetics Broad Institute of Harvard and MIT Cambridge MA USA. Diabetes Unit and Center for Genomic Medicine Massachusetts General Hospital Boston MA USA. TIMI Study Group Division of Cardiovascular Medicine Brigham and Women's Hospital Harvard Medical School Boston MA USA. William Harvey Research Institute Barts and the London School of Medicine and Dentistry Queen Mary University of London L

Type 2 diabetes (T2D) is a heterogeneous disease that develops through diverse pathophysiological processes and molecular mechanisms that are often specific to cell type. Here, to characterize the genetic contribution to these processes across ancestry groups, we aggregate genome-wide association study data from 2,535,601 individuals (39.7% not of European ancestry), including 428,452 cases of T2D. We identify 1,289 independent association signals at genome-wide significance (P < 5 × 10) that map to 611 loci, of which 145 loci are, to our knowledge, previously unreported. We define eight non-overlapping clusters of T2D signals that are characterized by distinct profiles of cardiometabolic trait associations. These clusters are differentially enriched for cell-type-specific regions of open chromatin, including pancreatic islets, adipocytes, endothelial cells and enteroendocrine cells. We build cluster-specific partitioned polygenic scores in a further 279,552 individuals of diverse ancestry, including 30,288 cases of T2D, and test their association with T2D-related vascular outcomes. Cluster-specific partitioned polygenic scores are associated with coronary artery disease, peripheral artery disease and end-stage diabetic nephropathy across ancestry groups, highlighting the importance of obesity-related processes in the development of vascular outcomes. Our findings show the value of integrating multi-ancestry genome-wide association study data with single-cell epigenomics to disentangle the aetiological heterogeneity that drives the development and progression of T2D. This might offer a route to optimize global access to genetically informed diabetes care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of radar antenna based on HFSS 2

Design of radar antenna based on HFSS

引用

2nd International Conference on Robotics and automation Engineering, ICRAE 2017

作者： Jie, Gao Jinsong, Du Xing, Tian Rigang, Cong Shenyang Institute of Automation Chinese Academy of Science China Key Laboratory On Radar System Research and Application Technology of Liaoning Province Shenyang110179 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781538613054

In this paper, a millimeter-wave radar array antenna with practical application is designed. According to the requirements of practical application of the speed radar, the actual detection range and return loss characteristics of the radar antenna are very demanding. At this request, the radar antenna array arrangement, through the power distributor to allocate the current of the single-patch antenna, and through the application of U shaped slot change the return loss, the application of HFSS software simulation analysis of the parameters of the antenna. At the same time the application of a variety of equipment testing and the actual road vehicle speed test, to meet the design requirements of the microstrip array antenna. © 2017 IEEE.

关键词： Radar antennas

来源：评论

学校读者我要写书评

暂无评论

Evolution of Surface Sensible Heat over the Tibetan Plateau Under the Recent Global Warming Hiatus

引用

Advances in Atmospheric Sciences 2017年第10期34卷 1249-1262页

作者： Lihua ZHU Gang HUANG Guangzhou FAN Xia QU Guijie ZHAO Wei HUA State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China University of Chinese Academy of Sciences Beijing 100049China School of Atmospheric Sciences/Plateau Atmosphere and Environment Key Laboratory of Sichuan Province/Joint Laboratory of Climate and Environment Change Chengdu University of lnformation TechnologyChengdu 610225China Laboratory for Regional Oceanography and Numerical Modeling Qingdao National Laboratory for Marine Science and TechnologyQingdao 266237China Joint Center for Global Change Studies Beijing 100875China Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science and TechnologyNanjing 210044China Center for Monsoon System Research Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China

Based on regular surface meteorological observations and NCEP/DOE reanalysis data, this study investigates the evolution of surface sensible heat（SH） over the central and eastern Tibetan Plateau（CE-TP） under the recent global warming hiatus. The results reveal that the SH over the CE-TP presents a recovery since the slowdown of the global warming. The restored surface wind speed together with increased difference in ground-air temperature contribute to the recovery in *** the global warming hiatus, the persistent weakening wind speed is alleviated due to the variation of the meridional temperature gradient. Meanwhile, the ground surface temperature and the difference in ground-air temperature show a significant increasing trend in that period caused by the increased total cloud amount, especially at night. At nighttime, the increased total cloud cover reduces the surface effective radiation via a strengthening of atmospheric counter radiation and subsequently brings about a clear upward trend in ground surface temperature and the difference in ground-air ***–radiation feedback plays a significant role in the evolution of the surface temperature and even SH during the global warming hiatus. Consequently, besides the surface wind speed, the difference in ground-air temperature becomes another significant factor for the variation in SH since the slowdown of global warming, particularly at night.

关键词： surface sensible heat Tibetan Plateau ground-air temperature difference surface wind speed global warming hiatus

来源：评论

学校读者我要写书评

暂无评论

Optical and Radiative Properties of Aerosols during a Severe Haze Episode over the North China Plain in December 2016

引用

Journal of Meteorological research 2017年第6期31卷 1045-1061页

作者： Yu ZHENG Huizheng CHE Leiku YANG Jing CHEN Yaqiang WANG Xiangao XIA Hujia ZHAO Hong WANG Deying WANG Ke GUI Linchang AN Tianze SUN Jie YU Xiang KUANG Xin LI Enwei SUN Dapeng ZHAO Dongsen YANG Zengyuan GUO Tianliang ZHAO Xiaoye ZHANG Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment Change/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological AdministrationNanjing University of Information Science&TechnologyNanjing 210044 State Key Laboratory of Severe Weather/Institute of Atmospheric Composition of China Meteorological Administration Chinese Academy of Meteorological SciencesBeijing 100081 School of Surveying and Land Information Engineering Henan Polytechnic UniversityJiaozuo 454000 Shijiazhuang Meteorological Bureau Shijiazhuang 050081 Laboratory for Middle Atmosphere and Global Environment Observation Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029 6 University of Chinese Academy of Sciences Beijing 100049 National Meteorological Center China Meteorological AdministrationBeijing 100081 Institute of Meteorological Science of Jilin Province Changchun 130062 Key Laboratory for Earth System Modeling of Ministry of Education Department of Earth System Scienceand Joint Center for Global Change StudiesTsinghua UniversityBeijing 100084

The optical and radiative properties of aerosols during a severe haze episode from 15 to 22 December 2016 over beijing, Shijiazhuang, and Jiaozuo in the North China Plain were analyzed based on the ground-based and satellite data, meteorological observations, and atmospheric environmental monitoring data. The aerosol optical depth at 500 nm was 〈 0.30 and increased to 〉 1.4 as the haze pollution developed. The Angstr6m exponent was 〉 0.80 for most of the study period. The daily single-scattering albedo was 〉 0.85 over all of the North China Plain on the most polluted days and was 〉 0.97 on some particular days. The volumes of fine and coarse mode particles during the haze event were approximately 0.05-0.21 and 0.01-0.43 μm^3, respectively-that is, larger than those in the time without haze. The daily absorption aerosol optical depth was about 0.01-0.11 in beijing, 0.01-0.13 in Shijiazhuang, and 0.01-0.04 in Jiaozuo, and the average absorption Angstrom exponent varied between 0.6 and 2.0. The aerosol radiative forcing at the bottom of the atmosphere varied from -23 to -227, -34 to -199, and -29 to -191 W m^-2 for the whole haze period, while the aerosol radiative forcing at the top of the atmosphere varied from -4 to -98, -10 to -51, and -21 to -143 W m^-2 in beijing, Shijiazhuang, and Jiaozuo, respectively. Satellite observations showed that smoke, polluted dust, and polluted continental components of aerosols may aggravate air pollution during haze episodes. The analysis of the potential source contribution function and concentration-weighted trajectory showed that the contribu- tion from local emissions and pollutants transport from upstream areas were 190-450 and 100-410 btg m-3, respectively.

关键词： haze episodes aerosols optical properties radiative forcing North China Plain

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Global estimates on the number of people blind or visually impaired by cataract: a meta-analysis from 2000 to 2020

引用

Eye (London, England) 2024年第11期38卷 2229-2231页

作者： Konrad Pesudovs Hugh R. Taylor Tabassom Sedighi Rupert R. A. Bourne Shahina Pardhan Van Charles Lansingh John H. Kempen Ian Tapply Arthur G. Fernandes Maria Vittoria Cicinelli Alessandro Arrigo Nicolas Leveziel Serge Resnikoff Seth Flaxman Mukkharram M. Bikbov Tasanee Braithwaite Alain Bron Ching-Yu Cheng Monte A. Del Monte Joshua R. Ehrlich Leon B. Ellwein David Friedman João M. Furtado Gus Gazzard Ronnie George M. Elizabeth Hartnett Jost B. Jonas Rim Kahloun Moncef Khairallah Rohit C. Khanna Janet Leasher Julie-Anne Little Vinay Nangia Michal Nowak Tunde Peto Pradeep Ramulu Fotis Topouzis Mitiadis Tsilimbaris Ya Xing Wang Ningli Wang Paul Svitil Briant Theo Vos Katrin Burkart Kaleb Coberly Xiaochen Dai Stephen S. Lim Tomislav Mestrovic Ali H. Mokdad Christopher J. L. Murray Jaimie D. Steinmetz Awoke Misganaw Yohannes Habtegiorgis Abate Mohammad Abdollahi Mozhan Abdollahi Ayele Mamo Abebe Olumide Abiodun Richard Gyan Aboagye Woldu Aberhe Abrha Hasan Abualruz Hiwa Abubaker Ali Eman Abu-Gharbieh Salahdein Aburuz Tadele Girum Girum Adal Mesafint Molla Adane Isaac Yeboah Addo Qorinah Estiningtyas Sakilah Adnani Muhammad Sohail Afzal Muhammad Umair Shahin Aghamiri Bright Opoku Ahinkorah Aqeel Ahmad Sajjad Ahmad Ali Ahmadi Siamak Sabour Ayman Ahmed Haroon Ahmed Ahmad Samir Alfaar Abid Ali Syed Shujait Shujait Ali Awais Altaf Hubert Amu Emmanuel Manu Sofia Androudi Rodrigo Anguita Abhishek Anil Rimple Jeet Kaur Muhammad Aaqib Shamim Saeid Anvari Anayochukwu Edward Anyasodor Francis Appiah Jalal Arabloo Haleh Ayatollahi Mosab Arafat Damelash Areda Reza Arefnezhad Brhane Berhe Aregawi Akeza Awealom Asgedom Tahira Ashraf Seyyed Shamsadin Athari Bantalem Tilaye Tilaye Atinafu Birhan Tsegaw Taye Maha Moh’d Wahbi Atout Alok Atreya Ahmed Y. Azzam Hassan Babamohamadi Sara Bagherieh Yogesh Bahurupi Atif Amin Baig Shumaila Nargus Biswajit Banik Mainak Bardhan Saurav Basu Kavita Batra Nebiyou Simegnew Bayileyegn Fatemeh Bazvand Addisu Shunu Beyene Awoke Masrie Asrat Derese Devidas S. Bhagat Akshaya Srikanth Bhagavathula Pankaj Bh Medicine & Health University of New South Wales Sydney NSW Australia School of Optometry and Vision Science University of New South Wales Sydney NSW Australia School of Population and Global Health University of Melbourne Carlton VIC Australia Vision and Eye Research Institute Anglia Ruskin University Cambridge UK HelpMeSee Instituto Mexicano de Oftalmologia Santiago de Querétaro Mexico University of Miami Gables FL USA University of Utah Salt Lake City UT USA Chief Medical Office HelpMeSee New York NY USA Mexican Institute of Ophthalmology Queretaro Mexico Department of Ophthalmology Massachusetts Eye and Ear/Shepens Eye Research Institute/Harvard Medical School Boston MA USA Eye Unit MyungSung Christian Medical Center (MCM) Comprehensive Specialized Hospital and MyungSun Medical College Addis Ababa Ethiopia Department of Ophthalmology Addis Ababa University Addis Ababa Ethiopia Sight for Souls Bellevue WA USA Department of Ophthalmology Harvard University Boston MA USA Eye Unit MyungSung Medical College Addis Ababa Ethiopia Addenbrooke’s Hospital Cambridge UK Department of Ophthalmology Cambridge University Hospitals Cambridge UK Federal University of Sao Paolo Sao Paolo SP Brazil University of Calgary Calgary AB Canada Department of Ophthalmology and Visual Sciences Federal University of São Paulo Sao Paulo Brazil School of Medicine Vita-Salute San Raffaele University Milan Italy Department of Ophthalmology IRCCS San Raffaele Scientific Institute Milan Italy Department of Ophthalmology San Raffaele Scientific Institute Milano Italy IRCCS San Raffaele Scientific Institute Vita-Salute University Milan Italy Scientific Institute San Raffaele Hospital Vita-Salute University Milan Italy University of Poitiers Poitiers France CHU de Poitiers Poitiers France Ophthalmology Department CHU de Poitiers (Poitiers University Hospital) Poitiers France Unité 1084 National Institute of Health and Medical Research (INSERM) Poitiers France

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Model with Probability Constraints of Trans-Provincial Hydropower Consumption Considering Dynamic Stability Limit

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期692卷

作者： Ke Yang Rui Mao Xu Wen Chuncheng Gao Miao Huang Wei Yan Southwest Subsection of State Grid Chengdu China State Key Laboratory of Power Transmission Equipment & System Security and New Technology(Chongqing University) Chongqing China College of Automation Chongqing University of Posts and Telecommunications Chongqing China Beijing Ke Dong Electric Power Control System Co. Ltd.Beijing China Nari Group Corporation/State Grid Electric Power Research Institute Nanjing China

With the rapid development of clean energy and serious delay of grid construction, water abandonment is becoming more and more severe. Under this condition, this paper proposed a multi-objective model with probability constraints of trans-provincial hydropower consumption considering dynamic stability limit. Firstly, a mathematical expression about the dynamic stability limit of trans-provincial channel is constructed. Secondly, a risk assessment index of abandoned water is established on the basis of semi-absolute deviation. Then, based on the framework of stochastic programming, a multi-objective model with probability constraints is proposed for hydropower transmission in trans-provincial trade. By means of genetic algorithm with embedded Monte-Carlo simulation technology, the model can be solved efficiently. Finally, data of Tibet power grid is calculated to verify the validity and universality of the research. The results show that the established model can achieve optimal economic benefit between grid companies and generation enterprises, and also effective management of water abandonment risk.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-driven deep learning for physical layer communications

arXiv

引用

arXiv 2018年

作者： He, Hengtao Jin, Shi Wen, Chao-Kai Gao, Feifei Li, Geoffrey Ye Xu, Zongben National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Institute of Communications Engineering National Sun Yat-sen University Kaohsiung804 Taiwan State Key Lab of Intelligent Technologies and Systems Tsinghua University Department of Automation Tsinghua University Beijing China School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States Institute for Information and System Sciences Xian Jiaotong University Xi'an710049 China

Intelligent communication is gradually becoming a mainstream direction. As a major branch of machine learning, deep learning (DL) has been applied in physical layer communications and demonstrated an impressive performance improvement in recent years. However, most of the existing works related to DL focus on data-driven approaches, which consider the communication system as a black box and train it by using a huge volume of data. Training a network requires sufficient computing resources and extensive time, both of which are rarely found in communication devices. By contrast, modeldriven DL approaches combine communication domain knowledge with DL to reduce the demand for computing resources and training time. This article discusses the recent advancements in model-driven DL approaches in physical layer communications, including transmission schemes, receiver design, and channel information recovery. Several open issues for future research are also highlighted. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

5G ENTERING INTO A NEW ERA

引用

China Communications 2017年第12期14卷 I0002-I0004页

作者： Feifei Gao Changle Li Jun Fang Kaizhi Huang Zhi Quan Chengwen Xing Jianhua Zhang Zhongshan Zhang Liqiang Zhao Yulong Zou Department of Automation Tsinqhua UniversityBeiiingChina the State Key Laboratory of Integrated Services Networks Xidian University china communications ieee communications magazine ieee signal processing letters national digital switching system engineering&technological research center the college of information engineering shenzhen university the school of information and electronics beijing institute of technology bupt itu-r imt-2020 channel model ieee comm the school of computer and communication engineering in the university of science and technology beijing(ustb) state key lab.of integrated ser vice networks xidian university the nanjing university of posts and telecommunications(nupt)

The ever increasing wireless data services, such asimaging, video, audio, multimedia, etc., have de-mands for the very high speed wireless communicationsand network, which are unfortunately a bottleneck whencombining with the wireline core network. Users＇ arenow expecting high quality of experience with low-costdevices, ubiquitous connectivity, energy efficiency, highreliability, or even ultra-low latency if a vehicle terminalis applied.

关键词： 5G ENTERING A NEW ERA

来源：评论

学校读者我要写书评

暂无评论

A novel RNN-GBRBM based feature decoder for anomaly detection technology in industrial control network

A novel RNN-GBRBM based feature decoder for anomaly detectio...

引用

作者： Zhang, Hua Zhu, Shixiang Ma, Xiao Zhao, Jun Shou, Zeng State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications 100876 China Data Network of Power Dispatch Safety Protection of Electric Power Supervisory Control System State Gird Jiangsu Electric Power Company Shanghai Road No 215 Nanjing Jiangsu210024 China Safety Protection of Electric Power Supervisory Control System NARI Group Corporation No. 19 Chengxin Rd Jiangning Nanjing Jiangsu211000 China Dispatching Data Network and Secondary Safty Protection Electric Power Science Research Institute State Gird Jiangsu Electric Power Company Jiangning Paweier Road No 1 Nanjing Jiangsu211103 China

As advances in networking technology help to connect industrial control networks with the Internet, the threat from spammers, attackers and criminal enterprises has also grown accordingly. However, traditional Network Intrusion Detection system makes significant use of pattern matching to identify malicious behaviors and have bad performance on detecting zero-day exploits in which a new attack is employed. In this paper, a novel method of anomaly detection in industrial control network is proposed based on RNN-GBRBM feature decoder. The method employ network packets and extract high-quality features from raw features which is selected manually. A modified RNN-RBM is trained using the normal traffic in order to learn feature patterns of the normal network behaviors. Then the test traffic is analyzed against the learned normal feature pattern by using osPCA to measure the extent to which the test traffic resembles the learned feature pattern. Moreover, we design a semi-supervised incremental updating algorithm in order to improve the performance of the model continuously. Experiments show that our method is more efficient in anomaly detection than other traditional approaches for industrial control network. Copyright © 2017 The Institute of Electronics, Information and Communication Engineers.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：