检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Naiyang Guan Long Lan Dacheng Tao Zhigang Luo Xuejun Yang Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Changsha Hunan 410073 China Centre for Quantum Computation and Intelligent Systems FEIT University of Technology Sydney Sydney NSW 2007 Australia State Key Laboratory of High Performance Computing National University of Defense Technology Changsha Hunan 410073 China

ISBN: (纸本)9781479928941

Regarding the non-negativity property of the magnitude spectrogram of speech signals, nonnegative matrix factorization (NMF) has obtained promising performance for speech separation by independently learning a dictionary on the speech signals of each known speaker. However, traditional NM-F fails to represent the mixture signals accurately because the dictionaries for speakers are learned in the absence of mixture signals. In this paper, we propose a new transductive NMF algorithm (TNMF) to jointly learn a dictionary on both speech signals of each speaker and the mixture signals to be separated. Since TNMF learns a more descriptive dictionary by encoding the mixture signals than that learned by NMF, it significantly boosts the separation performance. Experiments results on a popular TIMIT dataset show that the proposed TNMF-based methods outperform traditional NMF-based methods for separating the monophonic mixtures of speech signals of known speakers.

关键词： Speech Dictionaries as Topic Loudspeakers NMF protocol signals mixtures factorization HIGH-PERFORMANCE

来源：评论

学校读者我要写书评

暂无评论

Trace Bench: An Open Data Set for Trace-Oriented Monitoring

Trace Bench: An Open Data Set for Trace-Oriented Monitoring

引用

IEEE International Conference on Cloud Computing Technology and Science (CloudCom)

作者： Jingwen Zhou Zhenbang Chen Ji Wang Zibin Zheng Michael R. Lyu College of Computer National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China

User request trace-oriented monitoring is an effective method to improve the reliability of cloud systems. However, there are some difficulties in getting traces in practice, which hinder the development of trace-oriented monitoring research. In this paper, we release a fine-grained user request-centric open trace data set, called Trace Bench, collected on a real world cloud storage system deployed in a real environment. During collecting, many aspects are considered to simulate different scenarios, including cluster size, request type, workload speed, etc. Besides recording the traces when the monitored system is running normally, we also collect the traces under the situation with faults injected. With a mature injection tool, 14 faults are introduced, including function faults and performance faults. The traces in Trace Bench are clustered in different files, where each file corresponds to a certain scenario. The whole collection work lasted for more than half a year, resulting in more than 360, 000 traces in 361 files. In addition, we also employ several applications based on Trace Bench, which validate the helpfulness of Trace Bench for the field of trace-oriented monitoring.

关键词： Monitoring Servers Educational institutions Instruments Cloud computing Context Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

A novel secure inter-domain routing for identifier/locator split network

A novel secure inter-domain routing for identifier/locator s...

引用

2nd International Conference on Information Technology and Management Innovation, ICITMI 2013

作者： Liu, Ya Ping Liu, Zhi Hong Ma, Shi Cong Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology China College of Computer National University of Defense Technology China

ISBN: (纸本)9783037858646

With the rapid development of the Internet, the de facto inter-domain routing protocol, Border Gateway Protocol (BGP), has become very vulnerable to many attacks. For this, several secure inter-domain protocols have been proposed, most of which are focus on addressing the issue of faking AS path, but cannot address other issues, such as violating routing policies, reachability attacks and so on. Based on the concept of identifier/locator split and routing isolation, we have proposed a secure identifier-based inter-domain Routing, SIR [1], which can provide control plane security without using the high overhead mechanism. Then, we here optimize SIR and propose another secure inter-domain routing, Optimized SIR (O-SIR), which introduces a checked path table and records the path which has been checked before in each AS. We present the simulations based on the real world datasets CAIDA and compare the performance between SIR and O-SIR by different deployments and different position of attacks. The results show that O-SIR can reduce 18%-45% communication cost of verifying paths with additional below 0.1% routing table size. © (2013) Trans Tech Publications, Switzerland.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Correntropy induced metric based graph regularized non-negative matrix factorization

Correntropy induced metric based graph regularized non-negat...

引用

International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)

作者： Bin Mao Naiyang Guan Dacheng Tao Xuhui Huang Zhigang Luo College of Science National University of Defense Technology Changsha China College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha China Department of Computer Science and Technology College of Computer National University of Defense Technology Changsha China Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW Australia

Non-negative matrix factorization (NMF) is an efficient dimension reduction method and plays an important role in many pattern recognition and computer vision tasks. However, conventional NMF methods are not robust since the objective functions are sensitive to outliers and do not consider the geometric structure in datasets. In this paper, we proposed a correntropy graph regularized NMF (CGNMF) to overcome the aforementioned problems. CGNMF maximizes the correntropy between data matrix and its reconstruction to filter out the noises of large magnitudes, and expects the coefficients to preserve the intrinsic geometric structure of data. We also proposed a modified version of our CGNMF which construct the adjacent graph by using sparse representation to enhance its reliability. Experimental results on popular image datasets confirm the effectiveness of CGNMF.

关键词： Robustness Vectors Clustering algorithms Mutual information Measurement Computer integrated manufacturing

来源：评论

学校读者我要写书评

暂无评论

Automatic Mapping Single-Device OpenCL Program to Heterogeneous Multi-device Platform

Automatic Mapping Single-Device OpenCL Program to Heterogene...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Dong Chen Changqing Xun Dafei Huang Mei Wen Chunyuan Zhang National Key Laboratory of Parallel and Distributed Processing

In this paper, we propose a framework to automatically map single-device OpenCL programs to heterogeneous multi-device platforms with performance concerns. Our framework is based on the independence of work groups which built inside the OpenCL programming model and relies heavily on the knowledge of global memory access regions of work groups. So global memory access patterns of work groups are analyzed and an abstract representation CCRwS is designed to describe the exact memory access regions of each memory access statement in the kernels. A global memory access analyzer is designed to get CCRwSs by performing static program analysis on kernel codes. Based on CCRwSs, data transfer between multiple devices and host can be fully controlled by our framework. Then a kernel code regenerator is designed to distribute the workload and perform architecture specific optimizations by code transformation. Then we tested our framework on a platform with 2 Intel E5-2650 CPUs and 4 NVIDIA Tesla C2050 GPUs. Compared with the performance on single GPU, the kernels running on all the 6 devices can achieve about 4.5x faster.

关键词： Kernel Indexes Performance evaluation Benchmark testing Abstracts Optimization Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Pruning false positives of static data-race detection via thread specialization

Pruning false positives of static data-race detection via th...

引用

10th International Symposium on Advanced parallel processing Technologies, APPT 2013

作者： Chen, Chen Lu, Kai Wang, Xiaoping Zhou, Xu Fang, Li National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China Information Center National University of Defense Technology Changsha China

ISBN: (纸本)9783642452925

Static data-race detection is a powerful tool by providing clues for dynamic approaches to only instrument certain memory accesses. However, static data-race analysis suffers from high false positive rate. A key reason is that static analysis overestimates the set of shared objects a thread can access. We propose thread specialization to distinguish threads statically. By fixing the number of threads as well as the ID assigned to each thread, a program can be transformed to a simplified version. Static data-race analysis on this simplified program can infer the range of addresses accessed by each thread more accurately. Our approach prunes false positives by an average of 89.2% and reduces dynamic instrumentation by an average of 63.4% in seven benchmarks. © 2013 Springer-Verlag.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

A peak performance model for Matrix multiplication on general-purpose DSP

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences 2013年第11 SUPPL.期40卷 148-152页

作者： Liu, Jie Chi, Li-Hua Xie, Lin-Chuan Wang, Yang Gan, Xin-Biao Feng, Hua Hu, Qing-Feng Science and Technology on Parallel and Distributed Processing Laboratory National Univ of Defense Technology Changsha Hunan 410073 China

DSP processor can be used to solve the high performance computation problems, which has the characteristics of high computing performance and low power. Matrix multiplication algorithm is the kernel of many scientific and technology computation, so it is of importance for theorem and practice. Based on general purpose DSP (GPDSP), a new parallel algorithm for matrix multiplication was proposed. And a peak performance model for matrix multiplication was built. From the peak performance model, an architecture of GPDSP was set up, and the parameter of GPDSP with Tflops was given, which includes the number of pipe-line, the number of SIMD registers, the breadth and latency for the hierarchical memories.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

A Trusted Remote Attestation Model Based on Trusted Computing

A Trusted Remote Attestation Model Based on Trusted Computin...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Yue Yu Huaimin Wang Bo Liu Gang Yin National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9781479914449

Traditional security protocols can not be trusted in some application scenarios of high security level because the endpoints integrity is ignored. In this paper, we propose a novel trusted remote attestation model which combines the secure channel and the integrity measurement architecture of trusted computing. We design and implement a prototype system based on a mature security protocol, Transport Layer Security (TLS) protocol, integrated with integrity report provided by trusted platform module (TPM). The TLS protocol guarantees the security of data exchange process and the integrity report of TPM provides the evidence about the trustworthiness and the security state of the communication endpoints. Compared by traditional approaches, our method is more efficient and can be deployed in large scale systems easily.

关键词： Protocols Servers Principal component analysis Authentication Computer architecture Privacy

来源：评论

学校读者我要写书评

暂无评论

The Hi-GAL compact source catalogue. I : The physical properties of the clumps in the inner Galaxy (−71.0◦ 67.0◦)

arXiv

引用

arXiv 2017年

作者： Elia, Davide Molinari, S. Schisano, E. Pestalozzi, M. Pezzuto, S. Merello, M. Noriega-Crespo, A. Moore, T.J.T. Russeil, D. Mottram, J.C. Paladini, R. Strafella, F. Benedettini, M. Bernard, J.P. Di Giorgio, A. Eden, D.J. Fukui, Y. Plume, R. Bally, J. Martin, P.G. Ragan, S.E. Jaffa, S.E. Motte, F. Olmi, L. Schneider, N. Testi, L. Wyrowski, F. Zavagno, A. Calzoletti, L. Faustini, F. Natoli, P. Palmerim, P. Piacentini, F. Piazzo, L. Pilbratt, G.L. Polychroni, D. Baldeschi, A. Beltrán, M.T. Billot, N. Cambrésy, L. Cesaroni, R. García-Lario, P. Hoare, M.G. Huang, M. Joncas, G. Liu, S.J. Maiolo, B.M.T. Marsh, K.A. Maruccia, Y. Mège, P. Peretto, N. Rygl, K.L.J. Schilke, P. Thompson, M.A. Traficante, A. Umana, G. Veneziani, M. Ward-Thompson, D. Whitworth, A.P. Arab, H. Bandieramonte, M. Becciani, U. Brescia, M. Buemi, C. Bufano, F. Butora, R. Cavuoti, S. Costa, A. Fiorellino, E. Hajnal, A. Hayakawa, T. Kacsuk, P. Leto, P. Li Causi, G. Marchili, N. Martinavarro-Armengol, S. Mercurio, A. Molinaro, M. Riccio, G. Sano, H. Sciacca, E. Tachihara, K. Torii, K. Trigilio, C. Vitello, F. Yamamoto, H. INAF-IAPS via del Fosso del Cavaliere 100 Roma00133 Italy Space Telescope Science Institute 3700 San Martin Dr. BaltimoreMD21218 United States Astrophysics Research Institute Liverpool John Moores University Liverpool Science Park Ic2 146 Brownlow Hill LiverpoolL3 5RF United Kingdom Aix Marseille Univ. CNRS LAM Laboratoire d’Astrophysique de Marseille Marseille France Max-Planck Institute for Astronomy Königstuhl 17 HeidelbergD-69117 Germany Infrared Processing Analysis Center California Institute of Technology 770 South Wilson Ave. PasadenaCA91125 United States Dipartimento di Matematica e Fisica Università del Salento Lecce73100 Italy CNRS IRAP 9 Av. colonel Roche BP 44346 Toulouse cedex 4F-31028 France Université de Toulouse UPS-OMP IRAP Toulouse cedex 4F-31028 France Department of Physics Nagoya University Chikusa-ku Nagoya Aichi464-8601 Japan Department of Physics & Astronomy University of Calgary ABT2N 1N4 Canada Center for Astrophysics and Space Astronomy University of Colorado BoulderCO80309 United States Canadian Institute for Theoretical Astrophysics University of Toronto McLennan Physical Laboratories 60 St. George Street TorontoON Canada School of Physics and Astronomy University of Leeds LeedsLS2 9JT United Kingdom School of Physics and Astronomy Cardiff University Cardiff WalesCF24 3AA United Kingdom IPAG University Grenoble Alpes Grenoble38000 France AIM Paris-Saclay CEA/IRFU - CNRS INSU - Univ. Paris Diderot Service d’Astrophysique CEA-Saclay Gif-surYvette Cedex91191 France INAF Osservatorio Astrofisico di Arcetri Largo E. Fermi 5 Firenze50125 Italy I. Physik. Institut University of Cologne Zülpicher Strasse Köln50937 Germany European Southern Observatory Karl Schwarzschild str. 2 Garching85748 Germany Max-Planck-Institut für Radioastronomie Auf dem Hügel 69 Bonn53121 Germany ASI Science Data centre 00044 Frascati Roma Italy ESA/ESAC PO Box 78 Villanueva de la Cañada Madrid28691 Spain

Hi-GAL is a large-scale survey of the Galactic plane, performed with Herschel in five infrared continuum bands between 70 and 500 µm. We present a band-merged catalogue of spatially matched sources and their properties derived from fits to the spectral energy distributions (SEDs) and heliocentric distances, based on the photometric catalogs presented in Molinari et al. (2016a), covering the portion of Galactic plane −71.0◦ 67.0◦. The band-merged catalogue contains 100922 sources with a regular SED, 24584 of which show a 70 µm counterpart and are thus considered proto-stellar, while the remainder are considered starless. Thanks to this huge number of sources, we are able to carry out a preliminary analysis of early stages of star formation, identifying the conditions that characterise different evolutionary phases on a statistically significant basis. We calculate surface densities to investigate the gravitational stability of clumps and their potential to form massive stars. We also explore evolutionary status metrics such as the dust temperature, luminosity and bolometric temperature, finding that these are higher in proto-stellar sources compared to pre-stellar ones. The surface density of sources follows an increasing trend as they evolve from pre-stellar to proto-stellar, but then it is found to decrease again in the majority of the most evolved clumps. Finally, we study the physical parameters of sources with respect to Galactic longitude and the association with spiral arms, finding only minor or no differences between the average evolutionary status of sources in the fourth and first Galactic quadrants, or between "on-arm" and "inter-arm" positions. Copyright © 2017, The Authors. All rights reserved.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Data storage optimization of application-level checkpointing on heterogeneous systems

Data storage optimization of application-level checkpointing...

引用

IEEE Conference Anthology

作者： Jia Jia Wei Song National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

General purpose GPU's (GPGPU) appearance made it possible that heterogeneous computing can be used by human beings. And it's also produce a reform for GPU's general purpose computing and parallel computing. Heterogeneous Systems has been adopted by large-scale of high-performance computers. Nowadays, fault tolerance technique is necessary among these large-scale kinds of scientific computing, but in a few years of GPGPU and heterogeneous system appearance, there is not an effective fault tolerance method come out, therefore, towards this situation, this paper will apply the traditional fault tolerance technique—application-level checkpointing to heterogeneous system. Cause the main solution of reducing overhead of the application-level checkpointing is reducing checkpoint data size, so after analyzing the heterogeneous system and GPGPU program, we propose a method to optimize the data storage of application-level checkpointing technique and validate its optimization by experiments.

关键词： Graphics processing units Checkpointing Kernel Fault tolerance Fault tolerant systems Optimization Hardware

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：