Modern cloud computing platforms based on virtual machine monitors carry a variety of complex business that present many network security vulnerabilities. At present, the traditional architecture employs a number of security devices at front-end of cloud computing to protect its network security. Under the new environment, however, this approach can not meet the needs of cloud security. New cloud security vendors and academia also made great efforts to solve network security of cloud computing, unfortunately, they also cannot provide a perfect and effective method to solve this problem. We introduce a novel network security architecture for cloud computing (NSCC) that addresses this problem. NSCC not only provides an effective solution for network security issues of cloud computing, but also greatly improves in scalability, fault-tolerant, resource utilization, etc. We have implemented a proof-of-concept prototype about NSCC and proved by experiments that NSCC is an effective architecture with minimal performance overhead that can be applied to the extensive practical promotion in cloud computing.
{"title":"NSCC: Self-Service Network Security Architecture for Cloud Computing","authors":"Jin He, M. Dong, K. Ota, Minyu Fan, Guangwei Wang","doi":"10.1109/CSE.2014.109","DOIUrl":"https://doi.org/10.1109/CSE.2014.109","url":null,"abstract":"Modern cloud computing platforms based on virtual machine monitors carry a variety of complex business that present many network security vulnerabilities. At present, the traditional architecture employs a number of security devices at front-end of cloud computing to protect its network security. Under the new environment, however, this approach can not meet the needs of cloud security. New cloud security vendors and academia also made great efforts to solve network security of cloud computing, unfortunately, they also cannot provide a perfect and effective method to solve this problem. We introduce a novel network security architecture for cloud computing (NSCC) that addresses this problem. NSCC not only provides an effective solution for network security issues of cloud computing, but also greatly improves in scalability, fault-tolerant, resource utilization, etc. We have implemented a proof-of-concept prototype about NSCC and proved by experiments that NSCC is an effective architecture with minimal performance overhead that can be applied to the extensive practical promotion in cloud computing.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125890041","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}
In this paper, a new algorithm for fractional order system identification is set up. We study the structure of vector fitting and give a decomposition through the computational instance. In the vector fitting method, we use the complex least-square method to instead least-square method when calculating the residues and dealing with the errors based on vector fitting. And the rational fractional function has been extended from integer field to fractional domain. For validity, a comparison between the original and the present method is conducted.
{"title":"An Algorithm for Fractional Order System Identification","authors":"Xixiao Liu, Guishu Liang","doi":"10.1109/CSE.2014.46","DOIUrl":"https://doi.org/10.1109/CSE.2014.46","url":null,"abstract":"In this paper, a new algorithm for fractional order system identification is set up. We study the structure of vector fitting and give a decomposition through the computational instance. In the vector fitting method, we use the complex least-square method to instead least-square method when calculating the residues and dealing with the errors based on vector fitting. And the rational fractional function has been extended from integer field to fractional domain. For validity, a comparison between the original and the present method is conducted.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124629539","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}
High performance of data-intensive computation is required to deal with the complexity of analysis and simulation for hydrological modeling jobs like parameter estimation. The vigorously developing cloud computing has emerged as a promising platform for HPC (High Performance Computing) of science community. This paper presents our work in developing and implementing HPC environment on Azure cloud for applications of hydrological parameter estimation. According to the requirements of hydrological modeling, we design and construct a HPC environment on Azure cloud. After deploying parameter estimation applications on the HPC environment, a case study on groundwater uncertainty analysis in Heihe River Basin using the HPC environment is presented. Our work demonstrates that Azure cloud can advantageously complement traditional high performance computing infrastructure and help hydrological researchers improve model computing efficiency by handy process steps.
{"title":"HPC Environment on Azure Cloud for Hydrological Parameter Estimation","authors":"Guangjun Zhang, Yingying Yao, C. Zheng","doi":"10.1109/CSE.2014.83","DOIUrl":"https://doi.org/10.1109/CSE.2014.83","url":null,"abstract":"High performance of data-intensive computation is required to deal with the complexity of analysis and simulation for hydrological modeling jobs like parameter estimation. The vigorously developing cloud computing has emerged as a promising platform for HPC (High Performance Computing) of science community. This paper presents our work in developing and implementing HPC environment on Azure cloud for applications of hydrological parameter estimation. According to the requirements of hydrological modeling, we design and construct a HPC environment on Azure cloud. After deploying parameter estimation applications on the HPC environment, a case study on groundwater uncertainty analysis in Heihe River Basin using the HPC environment is presented. Our work demonstrates that Azure cloud can advantageously complement traditional high performance computing infrastructure and help hydrological researchers improve model computing efficiency by handy process steps.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125061280","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}
Jie He, Yuexiang Yang, Xiaolei Wang, Chuan Tang, Yingzhi Zeng
P2P technology has been widely applied in many areas due to its excellent properties. Some botnets also shift towards the decentralized architectures, since they provide a better resiliency against detection and takedown efforts. Besides, modern P2P bots tend to run on compromised hosts in a stealthy way, which renders most existing approaches ineffective. In addition, few approaches address the problem of real-time detection. However, it is important to detect bots as soon as possible in order to minimize their harm. In this paper, we propose Peer Digger, a novel real-time system capable of detecting stealthy P2P bots. Peer Digger first detects all P2P hosts base on several basic properties of flow records, and then distinguishes P2P bots from benign P2P hosts by analyzing their network behavior patterns. The experimental results demonstrate that our system is able to identity P2P bots with an average TPR of 98.07% and an average FPR of 1.5% within 4 minutes.
{"title":"PeerDigger: Digging Stealthy P2P Hosts through Traffic Analysis in Real-Time","authors":"Jie He, Yuexiang Yang, Xiaolei Wang, Chuan Tang, Yingzhi Zeng","doi":"10.1109/CSE.2014.283","DOIUrl":"https://doi.org/10.1109/CSE.2014.283","url":null,"abstract":"P2P technology has been widely applied in many areas due to its excellent properties. Some botnets also shift towards the decentralized architectures, since they provide a better resiliency against detection and takedown efforts. Besides, modern P2P bots tend to run on compromised hosts in a stealthy way, which renders most existing approaches ineffective. In addition, few approaches address the problem of real-time detection. However, it is important to detect bots as soon as possible in order to minimize their harm. In this paper, we propose Peer Digger, a novel real-time system capable of detecting stealthy P2P bots. Peer Digger first detects all P2P hosts base on several basic properties of flow records, and then distinguishes P2P bots from benign P2P hosts by analyzing their network behavior patterns. The experimental results demonstrate that our system is able to identity P2P bots with an average TPR of 98.07% and an average FPR of 1.5% within 4 minutes.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129458005","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}
Yu-Huei Chang, Jinn-Shyong Yang, Jou-Ming Chang, Yue-Li Wang
Zehavi and Itai (1989) proposed the following conjecture: every k-connected graph has k independent spanning trees (ISTs for short) rooted at an arbitrary node. An n-dimensional parity cube, denoted by PQn, is a variation of hyper cubes with connectivity n and has many features superior to those of hyper cubes. Recently, Wang et al. (2012) confirm the ISTs conjecture by providing an O(N log N) algorithm to construct n ISTs rooted at an arbitrary node on PQn, where N=2n is the number of nodes in PQn. However, this algorithm is executed in a recursive fashion and thus is hard to be parallelized. In this paper, we present a non-recursive and fully parallelized approach to construct n ISTs rooted at an arbitrary node of PQn in O(log N) time using N processors. In particular, the constructing rule of spanning trees is simple and the proof of independency is easier than ever before.
Zehavi和Itai(1989)提出了以下猜想:每个k连通图在任意节点上都有k棵独立的生成树(简称ISTs)。用PQn表示的n维奇偶校验立方体是连通度为n的超立方体的一种变体，它具有许多优于超立方体的特征。最近，Wang et al.(2012)提供了一种O(N log N)算法来构造N个ist猜想，该算法在PQn上的任意节点上构造N个ist，其中N=2n为PQn中的节点数。然而，这种算法是以递归的方式执行的，因此很难并行化。在本文中，我们提出了一种非递归的、完全并行的方法，在O(log n)时间内使用n个处理器在PQn的任意节点上构造n个ist。特别是生成树的构造规则简单，独立性的证明比以往任何时候都容易。
{"title":"Parallel Construction of Independent Spanning Trees on Parity Cubes","authors":"Yu-Huei Chang, Jinn-Shyong Yang, Jou-Ming Chang, Yue-Li Wang","doi":"10.1109/CSE.2014.225","DOIUrl":"https://doi.org/10.1109/CSE.2014.225","url":null,"abstract":"Zehavi and Itai (1989) proposed the following conjecture: every k-connected graph has k independent spanning trees (ISTs for short) rooted at an arbitrary node. An n-dimensional parity cube, denoted by PQn, is a variation of hyper cubes with connectivity n and has many features superior to those of hyper cubes. Recently, Wang et al. (2012) confirm the ISTs conjecture by providing an O(N log N) algorithm to construct n ISTs rooted at an arbitrary node on PQn, where N=2n is the number of nodes in PQn. However, this algorithm is executed in a recursive fashion and thus is hard to be parallelized. In this paper, we present a non-recursive and fully parallelized approach to construct n ISTs rooted at an arbitrary node of PQn in O(log N) time using N processors. In particular, the constructing rule of spanning trees is simple and the proof of independency is easier than ever before.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128234356","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}
The Dictionary is the most important basis of sparse representation which is the key issue of sparse component analysis and compressed sensing. Most of the existing dictionaries are constructed in frequency domain. This paper presented a novel dictionary constructed in time domain for radar signal representation based on geometrical theory of diffraction (GTD) model. Since Radar signal is distributed non-uniformly in time domain, the low-energy part of time responses can be cut-off with insignificant energy loss. As a result, the time-domain dictionary (TD) can be viewed as a sparse matrix, which can save memory and reduce computation complexity greatly, compared with frequency domain dictionaries. Finally, experimental results demonstrate the effectiveness and superiority of the time-domain dictionary.
{"title":"Time-Domain Dictionary for Sparse Representation of Radar High Resolution Range Profile","authors":"Jinrong Zhong, G. Wen, Conghui Ma, Boyuan Ding","doi":"10.1109/CSE.2014.363","DOIUrl":"https://doi.org/10.1109/CSE.2014.363","url":null,"abstract":"The Dictionary is the most important basis of sparse representation which is the key issue of sparse component analysis and compressed sensing. Most of the existing dictionaries are constructed in frequency domain. This paper presented a novel dictionary constructed in time domain for radar signal representation based on geometrical theory of diffraction (GTD) model. Since Radar signal is distributed non-uniformly in time domain, the low-energy part of time responses can be cut-off with insignificant energy loss. As a result, the time-domain dictionary (TD) can be viewed as a sparse matrix, which can save memory and reduce computation complexity greatly, compared with frequency domain dictionaries. Finally, experimental results demonstrate the effectiveness and superiority of the time-domain dictionary.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630669","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}
Symmetric Tori connected Torus Network (STTN) is a 2D-torus network of multiple basic modules, where each basic module is a 2D-torus network that are hierarchically interconnected for higher-level networks. The static network performance for STTN has already been studied earlier and shown to be good than that of other networks considering very large size networks. In this paper, we evaluate the dynamic communication performance of STTN using the virtual cut-through (VCT) flow control under different traffic patterns, and also evaluate the static cost factor for STTN against the most recently adopted 5D Torus network. We have found that with the non-uniform traffic patterns of STTN yields much better performance than that of 2D Torus, 2D Mesh, TESH and TTN networks in terms of network throughput and latency. The static cost factor of STTN is also better than that of 5D Torus network.
{"title":"Dynamic Communication Performance of STTN under Various Traffic Patterns Using Virtual Cut-Through Flow Control","authors":"F. A. Faisal, M. Rahman, Y. Inoguchi","doi":"10.1109/CSE.2014.331","DOIUrl":"https://doi.org/10.1109/CSE.2014.331","url":null,"abstract":"Symmetric Tori connected Torus Network (STTN) is a 2D-torus network of multiple basic modules, where each basic module is a 2D-torus network that are hierarchically interconnected for higher-level networks. The static network performance for STTN has already been studied earlier and shown to be good than that of other networks considering very large size networks. In this paper, we evaluate the dynamic communication performance of STTN using the virtual cut-through (VCT) flow control under different traffic patterns, and also evaluate the static cost factor for STTN against the most recently adopted 5D Torus network. We have found that with the non-uniform traffic patterns of STTN yields much better performance than that of 2D Torus, 2D Mesh, TESH and TTN networks in terms of network throughput and latency. The static cost factor of STTN is also better than that of 5D Torus network.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127131304","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}
In this paper, we present a saliency-aware image completion method which takes full advantage of a saliency detection result. On one hand, the saliency map is incorporated into the completion order computation procedure to take human visual attention into account. On the other hand, the saliency map used in patch matching makes the searched result more accurate and smooth. Furthermore, we employ an adaptive patch size determination algorithm which considers the color, structure, and saliency information simultaneously. Experiment results demonstrate the effectiveness of our system in preserving the structural information and robustness in various image content. We also show that the proposed system synthesizes more photo-realistic images than other image completion approaches.
{"title":"Saliency-Aware Image Completion","authors":"Z. Li, Haoqian Wang, Kai Li","doi":"10.1109/CSE.2014.119","DOIUrl":"https://doi.org/10.1109/CSE.2014.119","url":null,"abstract":"In this paper, we present a saliency-aware image completion method which takes full advantage of a saliency detection result. On one hand, the saliency map is incorporated into the completion order computation procedure to take human visual attention into account. On the other hand, the saliency map used in patch matching makes the searched result more accurate and smooth. Furthermore, we employ an adaptive patch size determination algorithm which considers the color, structure, and saliency information simultaneously. Experiment results demonstrate the effectiveness of our system in preserving the structural information and robustness in various image content. We also show that the proposed system synthesizes more photo-realistic images than other image completion approaches.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127132743","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}
One main challenge of prototyping a SoC (System on Chip) on FPGA (Field Programmable Gate Array) is to tune at best the communication architecture according to the task graph of an application and the available resources of the chosen FPGA. The exploration of the potential design candidates is time consuming, tedious and does not scale. The sheer number of parameters leads to a wide design space that cannot be explored in a limited time. The aim of this paper is to identify mathematical models applied to NoC to estimate FPGA resources. Mathematical models are obtained from a database containing a set of observed results. Using the database, the Pearson's correlation coefficient and the variable clustering are used to set the most appropriate variables and constants. The mathematical models are obtained and then validated with a set of experimental results. The validation shows that the error rate between observed results and the analytically estimated results is less than 5%. The designer can therefore tune the NoC in shorter exploration time.
{"title":"Mathematical Models Applied to On-Chip Network on FPGA for Resource Estimation","authors":"V. Fresse, C. Combes, Hatem Belhasseb","doi":"10.1109/CSE.2014.117","DOIUrl":"https://doi.org/10.1109/CSE.2014.117","url":null,"abstract":"One main challenge of prototyping a SoC (System on Chip) on FPGA (Field Programmable Gate Array) is to tune at best the communication architecture according to the task graph of an application and the available resources of the chosen FPGA. The exploration of the potential design candidates is time consuming, tedious and does not scale. The sheer number of parameters leads to a wide design space that cannot be explored in a limited time. The aim of this paper is to identify mathematical models applied to NoC to estimate FPGA resources. Mathematical models are obtained from a database containing a set of observed results. Using the database, the Pearson's correlation coefficient and the variable clustering are used to set the most appropriate variables and constants. The mathematical models are obtained and then validated with a set of experimental results. The validation shows that the error rate between observed results and the analytically estimated results is less than 5%. The designer can therefore tune the NoC in shorter exploration time.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130046091","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}
The mobile social network (MSN) can be considered as a system which provides a variety of data delivery services involving the social relationship among mobile users. Mobile social networks have the surprising property of being "searchable": Ordinary users contact with each other more frequently when they have more social features in common. In this paper, we first define a priority relationship between two mobile users in terms of their internal social features, and then we present a social feature-based priority relation graph of MSNs. The social feature-based priority relation graph is an (n{m1,...,mn}, k)-hypercube, in which two nodes are adjacent if and only if they differ in no more than k positions where k is the number of key features and k≪n. The priority relation graph of MSNs has some applications. First, it is the fundamental framework of data deliver routing. And then, a large area of circuit communication services can be guaranteed based on the priority relation graph in MSNs, which only need to a little cost.
{"title":"The Social Feature-Based Priority Relation Graph of Mobile Social Networks","authors":"Limei Lin, Li Xu, Shuming Zhou, Wei Wu","doi":"10.1109/CSE.2014.352","DOIUrl":"https://doi.org/10.1109/CSE.2014.352","url":null,"abstract":"The mobile social network (MSN) can be considered as a system which provides a variety of data delivery services involving the social relationship among mobile users. Mobile social networks have the surprising property of being \"searchable\": Ordinary users contact with each other more frequently when they have more social features in common. In this paper, we first define a priority relationship between two mobile users in terms of their internal social features, and then we present a social feature-based priority relation graph of MSNs. The social feature-based priority relation graph is an (n{m1,...,mn}, k)-hypercube, in which two nodes are adjacent if and only if they differ in no more than k positions where k is the number of key features and k≪n. The priority relation graph of MSNs has some applications. First, it is the fundamental framework of data deliver routing. And then, a large area of circuit communication services can be guaranteed based on the priority relation graph in MSNs, which only need to a little cost.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"4 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128817584","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：