{"title":"FPGA-based Acceleration of Deep Neural Networks Using High Level Method","authors":"Lei Liu, Jianlu Luo, Xiaoyan Deng, Sikun Li","doi":"10.1109/3PGCIC.2015.103","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.103","url":null,"abstract":"Deep neural network (DNN) is becoming more and more applied in data center applications such as speech recognition, image search, etc. However, the training in DNN is very time-consuming because of its deep structure. This paper presents FPGA-based acceleration of deep neural networks using a high level method and proposes a parallel optimizing strategy using the Kintex-7 FPGA board's features. Experimental results show that it can increase the utilization of FPGA computation units with low mini-batch size and reduce the transfer cost effectively. The optimized algorithm achieves up to 17.65x higher performance than CPU.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130495138","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}
{"title":"A Research Project on FPGA-accelerated Cryptographic Computing","authors":"Domenico Argenziano","doi":"10.1109/3PGCIC.2015.187","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.187","url":null,"abstract":"This invited presentation describes the contents of a research programme aimed at the definition of new components for FPGA-based cryptographic computing. The text describes the state of the art and the context of the proposed research, the methodology, as well as the current preliminary results, with particular emphasis on the ongoing development of an FPGA-based homomorphic encryption accelerator.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125500934","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}
{"title":"Development of the Big Data Management System on National Virtual Power Plant","authors":"Mijeom Kim, Jungin Choi, Jaeweon Yoon","doi":"10.1109/3PGCIC.2015.101","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.101","url":null,"abstract":"We are developing the Business Platform for demand side management in energy sector. This paper introduces the Business Platform and describes the development of the pilot platform and main components. In addition, main applications such as Automated Demand Response (AutoDR) and Monitoring Based Commissioning (MBCx) is introduced. One of main components of the platform is the Big Data Management System to save and analyze the energy big data. We constructed two big data cluster systems: one is a Hadoop cluster and the other is the one Spark installed. We also implemented software modules to collect and generate the energy big data. The data flow inside the platform is presented and implementation of Application Programing Interfaces (APIs) to access the big data is described. Furthermore, we developed various applications on top of the platform using the APIs. Among those, this paper presents the monitoring service.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127237875","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}
{"title":"Multiport Single Mode Fiber Coupler Technique for Mechanical Microactuator to Damped Blood Flow","authors":"T. Saktioto, D. Irawan, S. Anita, J. Ali","doi":"10.1109/3PGCIC.2015.150","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.150","url":null,"abstract":"We have proposed and optimize the optical parameters to fabricate multiport fiber coupler to support microactuator device based on fusion and elongation techniques. The coupling coefficient between the fibers was derived by using Hankel and Bessel function. However, the fusion technique was experimentally described as a function of elongation speed. Good performance of multi fiber coupler has been obtained for fabrication parameters of fusion temperature and elongation speed of 1350 oC and 125 μm/s respectively. The proposed coupling coefficient shows a better accuracy with empirical one for various coupling length. The coupling coefficient is exponentially increased by reducing the distance between fibers. Finally, the microscopic analysis of coupling region deformation has shown that the silica material was well dispersed and distributed.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127146167","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}
{"title":"A Scheduling Method to Reduce Waiting Time for Close-Range Delivery","authors":"Y. Gotoh, T. Yoshihisa","doi":"10.1109/3PGCIC.2015.116","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.116","url":null,"abstract":"Due to the recent popularization of digital broadcasting systems, close-range broadcasting using continuous media data, i.e. audio and video, has attracted great attention. For example, in a drama, after a user watches interesting content such as a highlight scene, he/she will watch the main scene continuously. In close-range broadcasting, the necessary bandwidth for continuously playing the two types of data increases. Conventional methods reduce the necessary bandwidth by producing an effective broadcast schedule for continuous media data. In addition, we have proposed the scheduling method to reduce the waiting time for close-range broadcasting. In this method, by setting the loading time of main scene, we can reduce total waiting time. However, when the server schedules two types of continuous media data, the loading time of highlight scene may increase. In this paper, we propose a scheduling method for close-range broadcasting based on loading time. In our proposed method, by producing an effective broadcast schedule considering both loading time of highlight scene and main scene, we can reduce the waiting time.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127131321","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}
{"title":"Practical Implementation of Private Cloud Based on Open Source ownCloud for Small Teams - Case Study","authors":"M. Greguš, Vincent Karovič","doi":"10.1109/3PGCIC.2015.149","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.149","url":null,"abstract":"Various companies in the manufacturing, but also in non-manufacturing sector, research and public organization use technology based on Internet to share data among staff but also with customers or in collaboration with other companies. Depending on the requirements of individual companies widely differing demands are placed on the technology in terms of features, administration, as well as security and the cost of the solution usually considered as one of the key issues. Cloud promises lower costs, high availability and scalability and that in the long term. The essence of any choice in selecting cloud solutions for corporate environment is to recognize its purpose, scope of use and content that will be uploaded to the storage. The paper discusses the project of setting up your own private cloud solution based on the open software ownCloud.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123469684","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}
{"title":"Learning from Annotated Video: An Initial Study Based on Oyama Karate Tournament Recordings","authors":"T. Hachaj, M. Ogiela, Katarzyna Koptyra","doi":"10.1109/3PGCIC.2015.16","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.16","url":null,"abstract":"The most of the up-to-date video data are amateur films consisted of an unbroken sequence of frames recorded from a single camera. In case of karate many even most important world tournaments do not have video broadcasting and the multimedia materials are mostly unprofessional. This type of recording is very difficult to analyze with automatic annotation methods. It is due the fact that a cameraman films the whole fight from stationary position. Only with a help of experienced specialists it is possible to distinguish the karate techniques fighters perform. Due to this fact annotations have to be done mostly manually. We have observed that none of the state of the art papers deal with problem of martial-arts annotated video analysis. It seems that this kind of data might be a very good source of knowledge about a kumite (a fight), a particular fighter and his or her strategies and abilities. In this paper we propose a novel video annotation method that enables both quantitative (numerical) and qualitative (categorical) features calculation. We also present and discuss example results we can obtain from those descriptions with popular data mining methods.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129254761","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}
{"title":"A Hierarchical Model for the Analysis of Efficiency and Speed-Up of Multi-core Cluster-Computers","authors":"Heinz Kredel, H. Kruse, S. Richling","doi":"10.1109/3PGCIC.2015.49","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.49","url":null,"abstract":"We develop a simple hierarchical model for the performance analysis of compute clusters assembled from multi-core compute nodes connected by a (high-speed) network. The performance is described by the dimensionless speed-up and efficiency in dependence on important hardware and application parameters. The hardware parameters are the number of compute nodes and the bandwidth the network, together with the number of cores per node, the theoretical performance of each core and the bandwidth of the main memory. The application parameters are the total number of operations performed on a number of bytes and the total number of bytes communicated between the processing units. In order to exemplify our concept we apply it to the scalar product of vectors, matrix multiplication, Linpack and FFT. Our previous performance models are contained as special cases in the new more comprehensive approach.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958456","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}
U. Gentile, S. Marrone, F. Paola, Roberto Nardone, N. Mazzocca, M. Giugni
{"title":"Model-Based Water Quality Assurance in Ground and Surface Provisioning Systems","authors":"U. Gentile, S. Marrone, F. Paola, Roberto Nardone, N. Mazzocca, M. Giugni","doi":"10.1109/3PGCIC.2015.97","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.97","url":null,"abstract":"The optimal management of water resources is a key problem for the sustainable exploitation of ground and surface water sources. One of the key issues is the assurance of quality of the provided water with respect to the presence of pollutant substances or micro biotic. This paper defines an automatic approach to evaluate the vulnerability of a provisioning network with respect the detection of a threat. By means of the creation of a high level model of a network and the automatic generation of proper formal models, it is possible to detect: (1) the effect of such threat on all the network nodes and (2) the most probable location of the contamination source.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123062002","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}
{"title":"Fast and Secure Elliptic Curve Scalar Multiplication Algorithm Based on a Kind of Deformed Fibonacci-Type Series","authors":"Shuanggen Liu, G. Qi, Xu An Wang","doi":"10.1109/3PGCIC.2015.21","DOIUrl":"https://doi.org/10.1109/3PGCIC.2015.21","url":null,"abstract":"The efficient and secure elliptic curve scalar multiplication can be constructed by combining the addition chain and elliptic curve. In this paper, a kind of \"Double-Addition\" additive chain is proposed by studying the Fibonacci sequence. The \"Double-Addition\" sequence of arbitrary integer k is calculated by using Fibonacci and the method of gold. In addition, each cycle of this method is fixed to perform double point and a point add operations based on the \"Double-Addition\" of the elliptic curve scalar multiplication algorithm, so as to be able to resist the simple power attack. At the same time, the length of the chain is greatly shortened by using the double point operation compared with the chain of the Fibonacci. Experimental results showed that the efficiency of proposed algorithm in this paper has preceded by 4% to 18% over the previous ones known in the literature and in the average chain length it has attained 38% to 55% reduction compared to other doubling-free addition chain methods.","PeriodicalId":395401,"journal":{"name":"2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127673682","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}