High Level Architecture (HLA) is a distributed simulation architecture which is applied to many simulation environments. In most of these environments, the simulation entities (called the federate in HLA) communicate with each other by interconnected local area networks (LANs). Due to the communications among federates which are in the same LAN have shorter latency and higher bandwidth, this paper proposes a message publish/subscribe scheme of HLA based on structured peer-to-peer overlay according to the principle of locality, by increasing the size of affordable federates and the size of workload by using the same hardware environment. Moreover, the run-time infrastructure (RTI) is implemented in accordance with HLA for performance evaluation. Experimental results show that the proposed scheme improves the performance of simulations.
{"title":"A Locality-Aware Publish/Subscribe Scheme for High Level Architecture on Structured Peer-to-Peer Networks","authors":"Wei-Chao Chang, Shih-Hsiang Lo, Kuan-Chou Lai, Kuan-Ching Li, Yeh-Ching Chung","doi":"10.1109/CSE.2010.69","DOIUrl":"https://doi.org/10.1109/CSE.2010.69","url":null,"abstract":"High Level Architecture (HLA) is a distributed simulation architecture which is applied to many simulation environments. In most of these environments, the simulation entities (called the federate in HLA) communicate with each other by interconnected local area networks (LANs). Due to the communications among federates which are in the same LAN have shorter latency and higher bandwidth, this paper proposes a message publish/subscribe scheme of HLA based on structured peer-to-peer overlay according to the principle of locality, by increasing the size of affordable federates and the size of workload by using the same hardware environment. Moreover, the run-time infrastructure (RTI) is implemented in accordance with HLA for performance evaluation. Experimental results show that the proposed scheme improves the performance of simulations.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"52 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122473303","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}
Batch processing process denotes the process used in the workflow management systems (WfMSs) supporting dynamic batch processing. During the run time of their concurrent process instances, multiple activity cases of the same type may be vertically combined together according to some batch logics and submitted for execution as a whole. Therefore, it is necessary to study the actual way process instances are executed. In this paper, we propose an algorithm to mine batch processing process from system logs. A case study is also done to illustrate its effectiveness.
{"title":"An Algorithm on the Mining of Batch Processing Process","authors":"Yiping Wen, Jianxun Liu, Zhigang Chen","doi":"10.1109/CSE.2010.58","DOIUrl":"https://doi.org/10.1109/CSE.2010.58","url":null,"abstract":"Batch processing process denotes the process used in the workflow management systems (WfMSs) supporting dynamic batch processing. During the run time of their concurrent process instances, multiple activity cases of the same type may be vertically combined together according to some batch logics and submitted for execution as a whole. Therefore, it is necessary to study the actual way process instances are executed. In this paper, we propose an algorithm to mine batch processing process from system logs. A case study is also done to illustrate its effectiveness.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122558048","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 recent years, Cloud computing is considered the next-generation computing paradigm. Cloud services could be broadly classified as software as a service (SaaS), platform as a service (PaaS) and infrastructure as a service (IaaS). However, most cloud providers only pay attention to certain services. This makes users vex about which cloud provider to be chosen, and when they need different services. Therefore, integrating these computing resources to satisfy users’ various requirements is an important issue. In this study, we present a Peer-to-Peer (P2P) resource search mechanism which adopts P2P networking technologies to orchestrate all the computing resources. Through this P2P resource search mechanism, cloud users can discover the computing resources in different cloud provides.
{"title":"A Semi-structured Overlay for Multi-attribute Range Queries in Cloud Computing","authors":"You-Fu Yu, Kuan-Chou Lai","doi":"10.1109/CSE.2010.67","DOIUrl":"https://doi.org/10.1109/CSE.2010.67","url":null,"abstract":"In recent years, Cloud computing is considered the next-generation computing paradigm. Cloud services could be broadly classified as software as a service (SaaS), platform as a service (PaaS) and infrastructure as a service (IaaS). However, most cloud providers only pay attention to certain services. This makes users vex about which cloud provider to be chosen, and when they need different services. Therefore, integrating these computing resources to satisfy users’ various requirements is an important issue. In this study, we present a Peer-to-Peer (P2P) resource search mechanism which adopts P2P networking technologies to orchestrate all the computing resources. Through this P2P resource search mechanism, cloud users can discover the computing resources in different cloud provides.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"447 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124950591","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 a novel low-cost and high-performance VLSI architecture for fuzzy c-means clustering. In the architecture, the operations at both the centroid and data levels are pipelined to attain high computational speed while consuming low hardware resources. In addition, the usual iterative operations for updating the membership matrix and cluster centroid are merged into one single updating process to evade the large storage requirement. Experimental results show that the proposed solution is an effective alternative for cluster analysis with low computational cost and high performance.
{"title":"Fast Fuzzy C-Means Clustering Based on Low-Cost High-Performance VLSI Architecture in Reconfigurable Hardware","authors":"Y. Yeh, Hui-Ya Li, C. Yang, Wen-Jyi Hwang","doi":"10.1109/CSE.2010.22","DOIUrl":"https://doi.org/10.1109/CSE.2010.22","url":null,"abstract":"This paper presents a novel low-cost and high-performance VLSI architecture for fuzzy c-means clustering. In the architecture, the operations at both the centroid and data levels are pipelined to attain high computational speed while consuming low hardware resources. In addition, the usual iterative operations for updating the membership matrix and cluster centroid are merged into one single updating process to evade the large storage requirement. Experimental results show that the proposed solution is an effective alternative for cluster analysis with low computational cost and high performance.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128392535","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}
Like most wireless network protocols, IEEE 802.15.4 adopts a CA (Congestion Avoidance) algorithm to avoid early collisions of new frames by randomizing its first transmission delay instead of delivering them immediately. The traditional CA scheme of IEEE 802.15.4 selects its random access time from the predetermined range without considering the degree of underlying network congestion. This static behavior often incurs a long delay to settle in the suitable range for the current network load or frequent clashes especially when heavy traffic lasts long. This paper proposes an ACA(Adaptive Congestion Avoidance) algorithm which dynamically adjusts the initial back off range according to the measurement of the average collision rate. It also introduces an analytical model to predict the performance spectrum in which ACA algorithm¡¯s throughput falls. With only small deviations from corresponding simulations, our model shows that ACA scheme can improve the throughput of IEEE 802.15.4 by up-to 41% while shortening the frame delays.
{"title":"Performance Evaluation of an Adaptive Congestion Avoidance Algorithm for IEEE 802.15.4","authors":"Ki-Chul Noh, Seung-Yeon Lee, Youn-Soon Shin, Kang-Woo Lee, Jong-Suk Ahn","doi":"10.1109/CSE.2010.12","DOIUrl":"https://doi.org/10.1109/CSE.2010.12","url":null,"abstract":"Like most wireless network protocols, IEEE 802.15.4 adopts a CA (Congestion Avoidance) algorithm to avoid early collisions of new frames by randomizing its first transmission delay instead of delivering them immediately. The traditional CA scheme of IEEE 802.15.4 selects its random access time from the predetermined range without considering the degree of underlying network congestion. This static behavior often incurs a long delay to settle in the suitable range for the current network load or frequent clashes especially when heavy traffic lasts long. This paper proposes an ACA(Adaptive Congestion Avoidance) algorithm which dynamically adjusts the initial back off range according to the measurement of the average collision rate. It also introduces an analytical model to predict the performance spectrum in which ACA algorithm¡¯s throughput falls. With only small deviations from corresponding simulations, our model shows that ACA scheme can improve the throughput of IEEE 802.15.4 by up-to 41% while shortening the frame delays.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125709070","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}
Flight Parameters stage classification is the premise of the fault diagnosis and trend forecast based on flight parameters. Stage classification belongs to the classification optimization problem of multi-attribute data through analysis the flight data. This paper carried out the research for the two-class classification based on the semi-supervised learning methods PTSVM (Progressive Transductive Support Vector Machines) and improved the PTSVM algorithm, which extends the application of PTSVM to the multi-class classification problem. The research and simulation work were carried out using the real flight parameters, and the comparison between the criterion of the flight parameters stage and the simulation results proved the validity of the research work for the flight parameters stage classification.
飞行参数阶段分类是基于飞行参数进行故障诊断和趋势预测的前提。通过对飞行数据的分析，阶段分类属于多属性数据的分类优化问题。本文对基于半监督学习方法的PTSVM (Progressive Transductive Support Vector Machines)进行了两类分类的研究，并对PTSVM算法进行了改进，将PTSVM扩展到多类分类问题中。利用真实飞行参数进行了研究和仿真工作，并将飞行参数分级准则与仿真结果进行了对比，验证了研究工作对飞行参数分级的有效性。
{"title":"Research on Stage Classification of Flight Parameter Based on PTSVM","authors":"Hui Lu, Kefei Mao","doi":"10.1109/CSE.2010.17","DOIUrl":"https://doi.org/10.1109/CSE.2010.17","url":null,"abstract":"Flight Parameters stage classification is the premise of the fault diagnosis and trend forecast based on flight parameters. Stage classification belongs to the classification optimization problem of multi-attribute data through analysis the flight data. This paper carried out the research for the two-class classification based on the semi-supervised learning methods PTSVM (Progressive Transductive Support Vector Machines) and improved the PTSVM algorithm, which extends the application of PTSVM to the multi-class classification problem. The research and simulation work were carried out using the real flight parameters, and the comparison between the criterion of the flight parameters stage and the simulation results proved the validity of the research work for the flight parameters stage classification.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134443462","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 Harmony Search (HS) method is an emerging meta-heuristic optimization algorithm. However, like most of the evolutionary computation techniques, it sometimes suffers from a rather slow search speed, and fails to find the global optima in an efficient way. In this paper, we propose and study a hybrid optimization approach, in which the HS is merged together with the Opposition-Based Learning (OBL). Our modified HS, namely HS-OBL, has an improved convergence property. Simulations of 23 typical benchmark problems demonstrate that the HS-OBL can indeed yield a superior optimization performance over the regular HS method.
{"title":"A Hybrid Harmony Search Method Based on OBL","authors":"X. Gao, Xiaolei Wang, S. Ovaska","doi":"10.1109/CSE.2010.26","DOIUrl":"https://doi.org/10.1109/CSE.2010.26","url":null,"abstract":"The Harmony Search (HS) method is an emerging meta-heuristic optimization algorithm. However, like most of the evolutionary computation techniques, it sometimes suffers from a rather slow search speed, and fails to find the global optima in an efficient way. In this paper, we propose and study a hybrid optimization approach, in which the HS is merged together with the Opposition-Based Learning (OBL). Our modified HS, namely HS-OBL, has an improved convergence property. Simulations of 23 typical benchmark problems demonstrate that the HS-OBL can indeed yield a superior optimization performance over the regular HS method.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"41 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114099206","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}
Convergence of technologies enabling physical and information security makes it possible to combine the features of location-aware and continuous authentication in a single system. We discuss the design of a location-aware continuous authentication system and discuss different implementation approaches that would strike a balance between usability and security of such a system. Issues of location privacy arising from using such systems are also discussed.
{"title":"Approaches and Issues in Location-Aware Continuous Authentication","authors":"S. Kurkovsky, Ewa Syta","doi":"10.1109/CSE.2010.42","DOIUrl":"https://doi.org/10.1109/CSE.2010.42","url":null,"abstract":"Convergence of technologies enabling physical and information security makes it possible to combine the features of location-aware and continuous authentication in a single system. We discuss the design of a location-aware continuous authentication system and discuss different implementation approaches that would strike a balance between usability and security of such a system. Issues of location privacy arising from using such systems are also discussed.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"29 21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116737009","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}
H.264/AVC provides high video quality at substantially low bit rates. However, the computational complexity of H.264/AVC is very high. A high-speed general-purpose processor is necessary to process H.264/AVC. However, it is difficult to use such a processor for a portable device. Therefore, an application-specific processor is necessary. A dynamic reconfiguration can virtually expand the circuit area in a limited chip area. Therefore, this article proposes a dynamically reconfigurable processor for H.264/AVC image prediction. H.264/AVC contains inter-prediction processes and de-blocking filter. The inter-prediction processes and de-blocking filter are not used at the same time. The proposed processor was designed and synthesized, and dynamically reconfigures those circuits. As a result, look up tables (LUTs) were reduced 10%, flip-flops were about the same, and the maximum delay was increased 10%.
{"title":"Design of Dynamically Reconfigurable Processor for the H.264/AVC Image Prediction and De-blocking Filter","authors":"Yukihiko Hayakawa, A. Kanasugi","doi":"10.1109/CSE.2010.24","DOIUrl":"https://doi.org/10.1109/CSE.2010.24","url":null,"abstract":"H.264/AVC provides high video quality at substantially low bit rates. However, the computational complexity of H.264/AVC is very high. A high-speed general-purpose processor is necessary to process H.264/AVC. However, it is difficult to use such a processor for a portable device. Therefore, an application-specific processor is necessary. A dynamic reconfiguration can virtually expand the circuit area in a limited chip area. Therefore, this article proposes a dynamically reconfigurable processor for H.264/AVC image prediction. H.264/AVC contains inter-prediction processes and de-blocking filter. The inter-prediction processes and de-blocking filter are not used at the same time. The proposed processor was designed and synthesized, and dynamically reconfigures those circuits. As a result, look up tables (LUTs) were reduced 10%, flip-flops were about the same, and the maximum delay was increased 10%.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128637277","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}
Recent developments in high performance computer architecture have a significant effect on all fields of scientific computing. Linear algebra and especially the solution of linear systems of equations lies at the heart of many applications in scientific computing. This paper describes and analyzes three parallel versions of the dense LU factorization method that is used in linear system solving on a multicore using OpenMP interface. More specifically, we present two naive parallel algorithms based on row block and row cyclic data distribution and we put special emphasis on presenting a third parallel algorithm based on the pipeline technique. Further, we propose an implementation of the pipelining technique in OpenMP. Experimental results on a multicore CPU show that the proposed OpenMP pipeline implementation achieves good overall performance compared to the other two naive parallel methods. Finally, in this work we propose a simple, fast and reasonably analytical model to predict the performance of the LU decomposition method with the pipelining technique.
{"title":"Implementing Parallel LU Factorization with Pipelining on a MultiCore Using OpenMP","authors":"Panagiotis D. Michailidis, K. Margaritis","doi":"10.1109/CSE.2010.39","DOIUrl":"https://doi.org/10.1109/CSE.2010.39","url":null,"abstract":"Recent developments in high performance computer architecture have a significant effect on all fields of scientific computing. Linear algebra and especially the solution of linear systems of equations lies at the heart of many applications in scientific computing. This paper describes and analyzes three parallel versions of the dense LU factorization method that is used in linear system solving on a multicore using OpenMP interface. More specifically, we present two naive parallel algorithms based on row block and row cyclic data distribution and we put special emphasis on presenting a third parallel algorithm based on the pipeline technique. Further, we propose an implementation of the pipelining technique in OpenMP. Experimental results on a multicore CPU show that the proposed OpenMP pipeline implementation achieves good overall performance compared to the other two naive parallel methods. Finally, in this work we propose a simple, fast and reasonably analytical model to predict the performance of the LU decomposition method with the pipelining technique.","PeriodicalId":342688,"journal":{"name":"2010 13th IEEE International Conference on Computational Science and Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129448639","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：