检索结果-内蒙古大学图书馆

Nonnegative Constrained Graph Based Canonical Correlation Analysis for Multi-view Feature Learning

NEURAL processing LETTERS 2019年第2期50卷 1215-1240页

作者： Tan, Huibin Zhang, Xiang Lan, Long Huang, Xuhui Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Inst Quantum Informat State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Dept Comp Sci Coll Comp Changsha Hunan Peoples R China

Understanding and analyzing multi-view data is a fundamental research topic of feature learning for a wide range of practical applications such as image classification. Canonical correlation analysis (CCA) is a popular unsupervised method of analyzing multi-view data, which captures common subspace of two groups of variable sets by maximizing the correlations between them. However, traditional CCA ignores the underlying geometric structure within dataset, which shows great power in describing data distribution, and thus fails in some tasks such as classification. To handle this limitation, this paper proposes an improved CCA variant of Nonnegative Constrained Graph regularized CCA (NCGCCA). Specifically, we improve CCA to NCGCCA with the following two contributions. Firstly, we develop a nonnegative constrained graph based self-representation to explore the underlying group-wise structure within dataset. Secondly, based on the proposed informative representation, we offer a graph embedding schema to incorporate the underlying structure into CCA. Experiments of image classification on four face datasets including Yale, ORL, UMIST, and YaleB demonstrate the efficacy of NCGCCA compared with existing baseline CCA methods.

关键词： Canonical correlation analysis Face recognition Sparse projection Cross-view correlation

来源：评论

学校读者我要写书评

暂无评论

On distributed information composition in big data systems 15

On distributed information composition in big data systems

引用

15th IEEE International conference on eScience, eScience 2019

作者： Alquwaiee, Haifa He, Songlin Wu, Chase Tang, Qiang Shen, Xuewen Department of Computer Science New Jersey Institute of Technology NewarkNJ07102 United States School of Electronics and Information Communication University of Zhejiang Hangzhou Zhejiang310018 China

ISBN: (纸本)9781728124513

Modern big data computing systems exemplified by Hadoop employ parallel processing based on distributed storage. The results produced by parallel tasks such as computing modules in scientific workflows or reducers in the MapReduce framework are typically stored in a distributed file system across multiple data nodes. However, most existing systems do not provide a mechanism to compose such distributed information, as required by many big data applications. We construct analytical cost models and formulate a distributed Information Composition problem in Big Data Systems, referred to as DIC-BDS, to aggregate multiple datasets stored as data blocks in Hadoop distributed File System (HDFS) using a composition operator of specific complexity to produce one final output. We rigorously prove that DIC-BDS is NP-complete, and propose two heuristic algorithms: Fixed-window distributed Composition Scheme (FDCS) and Dynamic-window distributed Composition Scheme with Delay (DDCS-D). We conduct extensive experiments in Google clouds with various composition operators of commonly considered degrees of complexity including O(n), O(n log n), and O(n2). Experimental results illustrate the performance superiority of the proposed solutions over existing methods. Specifically, FDCS outperforms all other algorithms in comparison with a composition operator of complexity O(n) or O(n log n), while DDCS-D achieves the minimum total composition time with a composition operator of complexity O(n2). These algorithms provide an additional level of data processing for efficient information aggregation in existing workflow and big data systems. © 2019 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Blurring the Lines between Blockchains and Database Systems: the Case of Hyperledger Fabric 19

Blurring the Lines between Blockchains and Database Systems:...

引用

ACM SIGMOD International conference on Management of Data (SIGMOD)

作者： Sharma, Ankur Schuhknecht, Felix Martin Agrawal, Divya Dittrich, Jens Saarland Univ Big Data Analyt Grp Saarbrucken Germany

ISBN: (纸本)9781450356435

Within the last few years, a countless number of blockchain systems have emerged on the market, each one claiming to revolutionize the way of distributed transaction processing in one way or the other. Many blockchain features, such as byzantine fault tolerance, are indeed valuable additions in modern environments. However, despite all the hype around the technology, many of the challenges that blockchain systems have to face are fundamental transaction management problems. These are largely shared with traditional database systems, which have been around for decades already. These similarities become especially visible for systems, that blur the lines between blockchain systems and classical database systems. A great example of this is Hyperledger Fabric, an open-source permissioned blockchain system under development by IBM. By implementing parallel transaction processing, Fabric's workflow is highly motivated by optimistic concurrency control mechanisms in classical database systems. This raises two questions: (1) Which conceptual similarities and differences do actually exist between a system such as Fabric and a classical distributed database system? (2) Is it possible to improve on the performance of Fabric by transitioning technology from the database world to blockchains and thus blurring the lines between these two types of systems even further? To tackle these questions, we first explore Fabric from the perspective of database research, where we observe weaknesses in the transaction pipeline. We then solve these issues by transitioning well-understood database concepts to Fabric, namely transaction reordering as well as early transaction abort. Our experimental evaluation under the Smallbank benchmark as well as under a custom workload shows that our improved version Fabric++ significantly increases the throughput of successful transactions over the vanilla version by up to a factor of 12x, while decreasing the average latency to almost half.

关键词： information systems distributed ledger ledger fabric distributed systems transactions blockchain hyperledger concurrenct control

来源：评论

学校读者我要写书评

暂无评论

FPGA Acceleration of Bolt Inspection Algorithm for a High-Speed Embedded Machine Vision System (ICCAS 2019) 19

FPGA Acceleration of Bolt Inspection Algorithm for a High-Sp...

引用

19th International conference on Control, Automation and Systems (ICCAS)

作者： Oh, SeonTaek You, Ji-Hwan Kim, Young-Keun Handong Global Univ Dept Mech & Control Engn Pohang 37554 South Korea

ISBN: (纸本)9788993215182

Most machine vision systems for bolt inspection are implemented on PC-based platforms for an embedded platform have limited computation performance. In order to implement a bolt inspection machine vision system on an embedded platform with advantages of high power-efficiency and lower cost as well as improved computation power, this paper proposes accelerating bolt inspection algorithms on an SoC of Embedded CPU and FPGA using HardwareSoftware codesign methods. First, image processing algorithms for bolt defect detection are designed and implemented on an embedded CPU (ARM Cortex-A53). Then, the computation load of each algorithms is analyzed to find key functions responsible for CPU bottleneck. These heavy loaded functions are identified as morphology, threshold, and center-finding, which are then accelerated using parallel processing on an FPGA. The proposed bolt machine vison algorithms of combining processing software (embedded CPU) and programmable logic (FPGA) were implemented on an SoC platform (Xilinx ZCU-104). Experiments conducted on images of normal and defected bolts showed that the proposed system could accelerate calculation speeds by up to 18.9 times, and the overall system by 1.3 times, compared to the software-only embedded CPU platform.

关键词： FPGA Bolt Inspection Embedded machine vision SDSoC parallel-processing Hardware Acceleration

来源：评论

学校读者我要写书评

暂无评论

distributed parallel Super-Block-Based Star Detection and Centroid Calculation

引用

IEEE SENSORS JOURNAL 2018年第19期18卷 8096-8107页

作者： Wang, Zhen Jiang, Jie Zhang, Guangjun Beijing Univ Aeronaut & Astronaut Sch Instrumentat Sci & Optoelect Engn Minist Educ Key Lab Precis Optomechatron Technol Beijing 100191 Peoples R China

Due to the inadequacies of the speed of star detection and centroid calculation (SDCC), the applications of high-resolution and high-frame-rate image sensors are greatly limited in star trackers, restricting the performance of the star trackers. To resolve this problem, a novel distributed parallel super-block-based SDCC method is proposed in this paper. In contrast to the previous SDCC methods, the proposed method divides the star images into several sub-images and processes these sub-images in parallel. Then, by using a super-block-based method and a distributed shared memory-based method to process the stars in sub-images (sub-stars) and in adjacent sub-images (boundary stars), respectively, the position information of all the stars are detected during the parallel scan of the sub-images. The proposed method exhibits a speed that is up to 4 x M times faster than the previous SDCC methods in processing the star images that are divided into M sub-images. Experimental results demonstrate that the proposed method is correct and effective. It is applicable to the use of most high-performance image sensors and resolves the performance limitation of star trackers to achieve better attitude accuracy and attitude update rate.

关键词： distributed parallel star detection centroid location star tracker distributed shared memory image sensors application

来源：评论

学校读者我要写书评

暂无评论

Research on Massive Video image processing based on Cloud Server 4

Research on Massive Video Image Processing based on Cloud Se...

引用

4th IEEE International conference on image, Vision and Computing, ICIVC 2019

作者： Haigen, Yang Qian, DIng Yusheng, Huang Longyan, Yu Wenting, Xu Longbao, Han Xiao, Fu Feng, Guo Ministry of Education Nanjing University of Posts and Telecommunications Engineering Research Center of Wider and Wireless Communication Technology Nanjing China Beijing Institute of Mechanical and Electrical Engineering Beijing China China International Engineering Consulting Corporation Beijing China Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781728123257

In order to solve the problems in security field such as public security, traffic and anti-terrorism, which require high real-time performance of massive video analysis and computation, large amount of data and many analysis dimensions, this paper designs a cloud load balancing algorithm, scheduling strategy and real-time analysis for massive video processing by studying distributed parallel computing, cloud computing, intelligent video analysis and massive data processing technologies. A cloud server system for real-time analysis of massive video is also developed. The reliability and practicability of the system are verified by the deployment and application of the actual project. © 2019 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A distributed Dynamic Resource Allocation Strategy in A Large-scale Micro-grids Group 6

A Distributed Dynamic Resource Allocation Strategy in A Larg...

引用

6th International conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2019

作者： Fu, Zao He, Xing Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9781728158570

In this paper, a dynamic economic dispatch problem (DEDP) with renewable energy generators is studied. With the purpose of minimizing the cost of DEDP and optimally allocate the load demand among the interconnected generators considering ramp-rate limits and generation limits, an effective continuous-time distributed algorithm based on interior point methods and primal-dual methods is proposed. In order to overcome the drawbacks of the renewable energy, a parallel system composed with flywheel energy storage systems and renewable energy generators is proposed to work in a constant power output mode. In addition, the using of switched systems makes the optimal solution more accurate. The excellent performance of the proposed algorithm is verified by IEEE 30-bus system with the REG based simulation. © 2019 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Round Robin processing Element for Deep Learning Accelerator

Implementation of a Round Robin Processing Element for Deep ...

引用

International SoC Design conference, ISOCC

作者： Eunchong Lee Yongseok Lee Sang-Seol Lee Byoung-Ho Choi Intelligent Image Processing Research Center Korea Electronics Technology Institute Gyeonggi-do South Korea

ISBN: (数字)9781728183312

ISBN: (纸本)9781728183329

The deep learning acceleration hardware performance is greatly affected by processing Elements (PEs). In order to apply deep learning accelerators to mobile devices, optimized PE must be designed as ASIC. To improve the performance of PE, we focused on methods of minimizing external memory access and parallelization. As a result, a deep learning accelerator architecture consisting of 512 PEs in parallel is proposed and the results of FPGA implementation is presented.

关键词： Deep learning Performance evaluation Accelerator architectures Mobile handsets Acceleration Round robin Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

K-means image classification algorithm based on hadoop

K-means image classification algorithm based on hadoop

引用

International conference on Intelligent Computing, Communication and Devices, ICCD 2017

作者： Xiong, Huiyun JiangXi Tourism & Commerce Vocational College Nanchang China

ISBN: (纸本)9789811089435

image classification has constituted a "hot" issue in large-scale image data processing in recent years. In this context, a significant number of using deep learning theory has been proposed for machine learning. Some works had a great development;however, most works deal with these problems need training a lot of parameters, so this process cost a lot of time and resources. This chapter proposes a hierarchical learning method, based on distributed Hadoop, to solve these problems. Initially, input images are extracted randomly in image blocks and reduced, in terms of redundant information, to maintain key information. Next, a regularization algorithm and noise processes are used on the image blocks between multiple image nodes in parallel. The following steps are to extract the dictionary of image classification by k-means algorithm. Finally, in order to select the feature mapping function in above dictionary, and mapped to a new image feature, it will be as a vector. The experimental results show that the algorithm is both reasonable and effective compared with the results of K-means. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

3D Tomographic image Reconstruction for Multistatic Ground Penetrating Radar

3D Tomographic Image Reconstruction for Multistatic Ground P...

引用

IEEE Radar conference (RadarConf)

作者： Pereira, Mauricio Zhang, Yu Orfeo, Daniel Burns, Dylan Huston, Dryver Xia, Tian Univ Vermont Sch Engn Burlington VT 05405 USA

ISBN: (纸本)9781728116792

Multistatic GPR has the advantages of reducing survey time and leverages more comprehensive data collection. Traditionally in multistatic GPR data processing, the 2D B-scan image obtained from each receive antenna are simply stacked for 3D image reconstructions. However, such approach is typically inadequate as the multistatic GPR receivers are mounted with spatial offsets, causing back-scattering signals from the same target to have differing time of arrivals. For proper fusion of multistatic GPR data, migration methods that consider the transmitters and receivers spatial offset and data variations among different receiving antennas may be employed. In this study, the back-projection algorithm (BPA) is investigated. The algorithm consists of determining the wave travel path and associated travel time, and projecting the corresponding signal value back into space domain. Furthermore, antenna radiation pattern is incorporated. The BPA enables scatter shape reconstruction and is prone to parallel computing. For validation, multistatic GPR 3D tomographic image reconstruction is successfully applied to laboratory data.

关键词： Multistatic GPR 3D imaging tomography

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：