Pub Date : 2020-07-06DOI: 10.1109/infocomwkshps50562.2020.9162694
Jiaxin Liu, Wei Zhao, Ye Hong, Sheng Gao, Xi Huang, Yingjie Zhou
Brain network is a kind of biological networks, which could express complex connectivity among brain functional components. The node in brain network denotes region of interest, which executes specific function in the brain. The edge in brain network represents the connection relationship between nodes. Neuropsychiatric disorders can cause changes in the brain's nerves, which will further change the related characteristics of brain network. The detection for neuropsychiatric disorders with brain network could be treated as an anomaly detection problem. Recent researches have explored using complex networks or graph mining to deal with the detection problem. However, they neither ignore local structural features in critical regions nor fail to comprehensively extract the structural features for brain network. In this paper, we propose a feature learning method to build effective representations for brain network. By treating the closed frequent graph as a node, these representations contain both connection relationships in critical regions and local/global structural features for critical regions, which could benefit the detection with brain network. Experiments using real world data indicate that the proposed method could improve the detection ability of existing machine learning methods in the literatures.
{"title":"Learning Features of Brain Network for Anomaly Detection","authors":"Jiaxin Liu, Wei Zhao, Ye Hong, Sheng Gao, Xi Huang, Yingjie Zhou","doi":"10.1109/infocomwkshps50562.2020.9162694","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162694","url":null,"abstract":"Brain network is a kind of biological networks, which could express complex connectivity among brain functional components. The node in brain network denotes region of interest, which executes specific function in the brain. The edge in brain network represents the connection relationship between nodes. Neuropsychiatric disorders can cause changes in the brain's nerves, which will further change the related characteristics of brain network. The detection for neuropsychiatric disorders with brain network could be treated as an anomaly detection problem. Recent researches have explored using complex networks or graph mining to deal with the detection problem. However, they neither ignore local structural features in critical regions nor fail to comprehensively extract the structural features for brain network. In this paper, we propose a feature learning method to build effective representations for brain network. By treating the closed frequent graph as a node, these representations contain both connection relationships in critical regions and local/global structural features for critical regions, which could benefit the detection with brain network. Experiments using real world data indicate that the proposed method could improve the detection ability of existing machine learning methods in the literatures.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"46 1","pages":"900-905"},"PeriodicalIF":0.0,"publicationDate":"2020-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74340113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-01DOI: 10.1109/INFCOMW.2018.8406988
Nabeel Akhtar, I. Matta, A. Raza, Yuefeng Wang
The concept of Virtualized Network Functions (VNFs) aims to move Network Functions (NFs) out of dedicated hardware devices into software that runs on commodity hard-ware. A single NF consists of multiple VNF instances, usually running on virtual machines in a cloud infrastructure. The elastic management of an NF refers to load management across the VNF instances and the autonomic scaling of the number of VNF instances as load on the NF changes. In this demonstration, we present EL-SEC, an autonomic framework to elastically manage security NFs on a virtualized infrastructure. As a use case, we deploy the Snort Intrusion Detection System as the NF on the GENI testbed. Concepts from control theory are used to create an Elastic Manager, which implements various controllers — in this demo, Proportional Integral (PI) and Proportional Integral Derivative (PID) — to direct traffic across the VNF Snort instances by monitoring the current load. RINA (a clean-slate Recursive InterNetwork Architecture) is used to build a distributed application that monitors load and collects Snort alerts, which are processed by the Elastic Manager and an Attack Analyzer, respectively. Software Defined Networking (SDN) is used to steer traffic through the VNF instances, and to block attack traffic. Our demo shows that virtualized security NFs can be easily deployed using our EL-SEC framework. With the help of real-time graphs, we show that PI and PID controllers can be used to easily scale the system, which leads to quicker detection of attacks.
{"title":"Demo abstract: EL-SEC: ELastic management of security applications on virtualized infrastructure","authors":"Nabeel Akhtar, I. Matta, A. Raza, Yuefeng Wang","doi":"10.1109/INFCOMW.2018.8406988","DOIUrl":"https://doi.org/10.1109/INFCOMW.2018.8406988","url":null,"abstract":"The concept of Virtualized Network Functions (VNFs) aims to move Network Functions (NFs) out of dedicated hardware devices into software that runs on commodity hard-ware. A single NF consists of multiple VNF instances, usually running on virtual machines in a cloud infrastructure. The elastic management of an NF refers to load management across the VNF instances and the autonomic scaling of the number of VNF instances as load on the NF changes. In this demonstration, we present EL-SEC, an autonomic framework to elastically manage security NFs on a virtualized infrastructure. As a use case, we deploy the Snort Intrusion Detection System as the NF on the GENI testbed. Concepts from control theory are used to create an Elastic Manager, which implements various controllers — in this demo, Proportional Integral (PI) and Proportional Integral Derivative (PID) — to direct traffic across the VNF Snort instances by monitoring the current load. RINA (a clean-slate Recursive InterNetwork Architecture) is used to build a distributed application that monitors load and collects Snort alerts, which are processed by the Elastic Manager and an Attack Analyzer, respectively. Software Defined Networking (SDN) is used to steer traffic through the VNF instances, and to block attack traffic. Our demo shows that virtualized security NFs can be easily deployed using our EL-SEC framework. With the help of real-time graphs, we show that PI and PID controllers can be used to easily scale the system, which leads to quicker detection of attacks.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"56 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90986201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-01-01DOI: 10.1109/INFCOMW.2018.8406855
A. Asrese, Ermias Andargie Walelgne, Andra Lutu, O. Alay, J. Ott
—This work presents a new methodology to measure the performance of web browsing over operational Mobile Broadband (MBB) networks. We designed a web performance measurement tool that collects both the web QoS metrics and the web rendering time in a browser window. We used MONROE [1], European wide measurement platform, to deploy our tool and to conduct a web browsing measurement over operational MBB networks. The results from the initial deployment show that different operators across countries and within the same country have a significant difference in web browsing performance (e.g. in the median case TIM is 75 ms faster than I WIND regarding time to first byte (TTFB)).
{"title":"Measuring Web Latency in Cellular Networks","authors":"A. Asrese, Ermias Andargie Walelgne, Andra Lutu, O. Alay, J. Ott","doi":"10.1109/INFCOMW.2018.8406855","DOIUrl":"https://doi.org/10.1109/INFCOMW.2018.8406855","url":null,"abstract":"—This work presents a new methodology to measure the performance of web browsing over operational Mobile Broadband (MBB) networks. We designed a web performance measurement tool that collects both the web QoS metrics and the web rendering time in a browser window. We used MONROE [1], European wide measurement platform, to deploy our tool and to conduct a web browsing measurement over operational MBB networks. The results from the initial deployment show that different operators across countries and within the same country have a significant difference in web browsing performance (e.g. in the median case TIM is 75 ms faster than I WIND regarding time to first byte (TTFB)).","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78802851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-09-01DOI: 10.1109/ICRITO.2017.8342407
Y. Tamura, S. Yamada
Recently, many fault data sets are recorded on the bug tracking systems. These bug tracking systems are used on the Website for such as open source project management. The software managers of open source projects can comprehend the fault status by using the bug tracking system. However, these software systems for development support such as the bug tracking system cannot estimate the future trend of fault data. We discuss the methods of reliability and maintainability assessment based on the deep learning for fault big data. In particular, we develop the reliability and maintainability analysis tool based on deep learning for fault big data by using the latest programing technology. Moreover, we show several numerical illustrations of the developed software tool by using the fault big data in the actual software projects.
{"title":"Reliability and maintainability analysis and its toolbased on deep learning for fault big data","authors":"Y. Tamura, S. Yamada","doi":"10.1109/ICRITO.2017.8342407","DOIUrl":"https://doi.org/10.1109/ICRITO.2017.8342407","url":null,"abstract":"Recently, many fault data sets are recorded on the bug tracking systems. These bug tracking systems are used on the Website for such as open source project management. The software managers of open source projects can comprehend the fault status by using the bug tracking system. However, these software systems for development support such as the bug tracking system cannot estimate the future trend of fault data. We discuss the methods of reliability and maintainability assessment based on the deep learning for fault big data. In particular, we develop the reliability and maintainability analysis tool based on deep learning for fault big data by using the latest programing technology. Moreover, we show several numerical illustrations of the developed software tool by using the fault big data in the actual software projects.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"2021 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91397426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-01-01DOI: 10.1109/INFOCOM.2017.8057009
Shang Gao, Zhe Peng, Bin Xiao, A. Hu, K. Ren
{"title":"FloodDefender: Protecting data and control plane resources under SDN-aimed DoS attacks","authors":"Shang Gao, Zhe Peng, Bin Xiao, A. Hu, K. Ren","doi":"10.1109/INFOCOM.2017.8057009","DOIUrl":"https://doi.org/10.1109/INFOCOM.2017.8057009","url":null,"abstract":"","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"1 1","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81248144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/ICRITO.2016.7785012
Anjum Zameer Bhat, Dalal Khalfan Al Shuaibi, A. Singh
Cloud Computing in recent years has become a buzz word in the world of information technology. Cloud computing also referred as on demand computing has been extensively adapted by various organization irrespective of their scale and nature of work, essentially because of kind of flexibility, ease, scalability, less overhead and cost benefits that cloud computing provides. In recent years we have seen discrete and unique cloud implementations resulting in automation of complicated business processes at a never imaginable cost. Cloud computing provides three basic architecture to cater the needs of different users i.e. IaaS (Infrastructure as a Service), PaaS (Platform as a Service) and SaaS (Software as a Service). As the implementation of cloud computing is exponentially broadening and it is being implemented in newer and newer fields, need is being felt by cloud implementers to have unique service architectures for a specific implementation. In other words a unique cloud service architecture e.g. for Educational Establishments or e.g. a discrete service architecture for Virtual Private Network (VPN) if it is to be deployed through cloud. As Virtual Private Networks are a part of most of the network deployments all over the world connecting branches, business partners and outlets and providing seamless connectivity especially for SME's (Small-Medium sized Enterprises). Most of the organizations with VPN deployments want to reduce the operational cost, implementation cost and overhead associated with VPN's. This research paper is mere effort to study the need for discrete cloud architecture for the implementation of VPN service through cloud computing. This research paper introduces a unique cloud architecture VPNaaS (Virtual Private Network as a Service).
{"title":"Virtual private network as a service — A need for discrete cloud architecture","authors":"Anjum Zameer Bhat, Dalal Khalfan Al Shuaibi, A. Singh","doi":"10.1109/ICRITO.2016.7785012","DOIUrl":"https://doi.org/10.1109/ICRITO.2016.7785012","url":null,"abstract":"Cloud Computing in recent years has become a buzz word in the world of information technology. Cloud computing also referred as on demand computing has been extensively adapted by various organization irrespective of their scale and nature of work, essentially because of kind of flexibility, ease, scalability, less overhead and cost benefits that cloud computing provides. In recent years we have seen discrete and unique cloud implementations resulting in automation of complicated business processes at a never imaginable cost. Cloud computing provides three basic architecture to cater the needs of different users i.e. IaaS (Infrastructure as a Service), PaaS (Platform as a Service) and SaaS (Software as a Service). As the implementation of cloud computing is exponentially broadening and it is being implemented in newer and newer fields, need is being felt by cloud implementers to have unique service architectures for a specific implementation. In other words a unique cloud service architecture e.g. for Educational Establishments or e.g. a discrete service architecture for Virtual Private Network (VPN) if it is to be deployed through cloud. As Virtual Private Networks are a part of most of the network deployments all over the world connecting branches, business partners and outlets and providing seamless connectivity especially for SME's (Small-Medium sized Enterprises). Most of the organizations with VPN deployments want to reduce the operational cost, implementation cost and overhead associated with VPN's. This research paper is mere effort to study the need for discrete cloud architecture for the implementation of VPN service through cloud computing. This research paper introduces a unique cloud architecture VPNaaS (Virtual Private Network as a Service).","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"37 1","pages":"526-532"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91396256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-04-10DOI: 10.1109/INFCOMW.2016.7561994
Sung-Ju Lee, C. Petrioli, P. Wan, Kai Zeng
On behalf of the technical program committee, it is our great pleasure to welcome you to San Francisco for the 35th IEEE INFOCOM Conference. In line with its tradition, IEEE INFOCOM 2016 features a high quality technical program across a wide range of traditional and emerging research areas in computer communications and networking. IEEE INFOCOM 2016 received 1644 submissions from 54 countries spread over all continents, of which 300 were accepted to the main technical program after a thorough review process. The competitive acceptance rate of 18% reflects the prestige and popularity of IEEE INFOCOM to our research community. The papers included in this year's program represent the forefront of networking research, as they explore important new ideas and directions in the field.
{"title":"TPC Chair's welcome","authors":"Sung-Ju Lee, C. Petrioli, P. Wan, Kai Zeng","doi":"10.1109/INFCOMW.2016.7561994","DOIUrl":"https://doi.org/10.1109/INFCOMW.2016.7561994","url":null,"abstract":"On behalf of the technical program committee, it is our great pleasure to welcome you to San Francisco for the 35th IEEE INFOCOM Conference. In line with its tradition, IEEE INFOCOM 2016 features a high quality technical program across a wide range of traditional and emerging research areas in computer communications and networking. IEEE INFOCOM 2016 received 1644 submissions from 54 countries spread over all continents, of which 300 were accepted to the main technical program after a thorough review process. The competitive acceptance rate of 18% reflects the prestige and popularity of IEEE INFOCOM to our research community. The papers included in this year's program represent the forefront of networking research, as they explore important new ideas and directions in the field.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"24 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2016-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90763620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents the experimentation done in order to flourish a low price and impressionable information system to provide useful information to farmers in a timely manner so as to assist their decision making process. The primary reason behind development of this system was to automate the flow of information to farmers since agriculture is the backbone of our country. Gram Sandesh Transmission is a web disciplined system which targets all sort of audience by means of its ios application (for iphone users),android application(for android users), messaging server(for basic mobile handset) and gsm based led boards (for those who don't owe a mobile handset). Farmers are provided with weather related information on daily basis so that necessary decision regarding sowing of seeds, weeding, harvesting, irrigation could be taken. The system warns with any disaster related information so that necessary steps could be taken. Another module of the system deals with providing “Sarkari Mandi Bhaav” (Govt. Market Price) and thus reduces the chances of fraud prices quoted by middleman to farmers.
{"title":"Gram Sandesh Transmission-a web based information system for farmers","authors":"Parv Gupta, R. Majumdar, Mrigendra Kumar, Nishant Chauhan, Subhash Chand Gupta","doi":"10.1109/ICRITO.2015.7359246","DOIUrl":"https://doi.org/10.1109/ICRITO.2015.7359246","url":null,"abstract":"This paper presents the experimentation done in order to flourish a low price and impressionable information system to provide useful information to farmers in a timely manner so as to assist their decision making process. The primary reason behind development of this system was to automate the flow of information to farmers since agriculture is the backbone of our country. Gram Sandesh Transmission is a web disciplined system which targets all sort of audience by means of its ios application (for iphone users),android application(for android users), messaging server(for basic mobile handset) and gsm based led boards (for those who don't owe a mobile handset). Farmers are provided with weather related information on daily basis so that necessary decision regarding sowing of seeds, weeding, harvesting, irrigation could be taken. The system warns with any disaster related information so that necessary steps could be taken. Another module of the system deals with providing “Sarkari Mandi Bhaav” (Govt. Market Price) and thus reduces the chances of fraud prices quoted by middleman to farmers.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"69 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91397362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-04-21DOI: 10.1109/I4CT.2015.7219555
Aznor Hanah Abdul Halim, M. N. M. Warip, R. B. Ahmad, S. J. Elias
Vehicular Ad Hoc Network (VANET) is quite different from other ad hoc networks in term of functionality because of the variable node density, high node mobility, and unpredictable and harsh communication environment. There are two major applications VANET, namely safety applications and non-safety applications. In addition, network optimization is one way to maintain the existing protocols and other network parameter compare to design and implementing new improved protocols in which it too costly. Motivated with the reasons this paper presents an optimization of vehicular network for throughput, end-to-end delay and packet delivery ratio using Taguchi method. Highway scenario is chosen as the evaluation condition for this paper. For three performances evaluated, the highest rank value shows the different factors. For safety application which is delay-sensitive, routing protocols is the highest rank control factors. Non-safety application which is throughput sensitive, packet size is the main control factors.
{"title":"Optimization of Vehicular Ad Hoc Network using Taguchi method","authors":"Aznor Hanah Abdul Halim, M. N. M. Warip, R. B. Ahmad, S. J. Elias","doi":"10.1109/I4CT.2015.7219555","DOIUrl":"https://doi.org/10.1109/I4CT.2015.7219555","url":null,"abstract":"Vehicular Ad Hoc Network (VANET) is quite different from other ad hoc networks in term of functionality because of the variable node density, high node mobility, and unpredictable and harsh communication environment. There are two major applications VANET, namely safety applications and non-safety applications. In addition, network optimization is one way to maintain the existing protocols and other network parameter compare to design and implementing new improved protocols in which it too costly. Motivated with the reasons this paper presents an optimization of vehicular network for throughput, end-to-end delay and packet delivery ratio using Taguchi method. Highway scenario is chosen as the evaluation condition for this paper. For three performances evaluated, the highest rank value shows the different factors. For safety application which is delay-sensitive, routing protocols is the highest rank control factors. Non-safety application which is throughput sensitive, packet size is the main control factors.","PeriodicalId":6468,"journal":{"name":"2014 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"41 1","pages":"147-151"},"PeriodicalIF":0.0,"publicationDate":"2015-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82441248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：