检索结果-内蒙古大学图书馆

international conference on Renewable Energies for Developing Countries (REDEC)

作者： Mohcin Mekhfioui Amal Satif Omar Mouhib Rachid Elgouri Abdelkader Hadjoudja Laamari Hlou Laboratory of Electrical Engineering and Energy Systems Faculty of Science Ibn Tofail University Kenitra Morocco

ISBN: (数字)9781728155951

ISBN: (纸本)9781728155968

Blind Source Separation (BSS) is termed as the extraction of source signals from mixed data without or with little knowledge about the source signals. It is used in many fields of research such as military, medical and industry. Among the many challenges that must be overcome to apply BSS to a real system, implementation restrictions are the most difficult. Software implementations require a significant amount of overhead to make them applicable to real-time systems and have a lower maximum speed of operation than hardware implementations. When speed is desired, the algorithm should be implemented on specialized hardware such as a Field Programmable Gate Array(FPGA) which allows the user to take advantage of parallel computational abilities. this paper describes the methodology for implementing real-time DSP applications on FPGA and the concept of hardware software cosimulation of the Second Order Blind Identification (SOBI) algorithm using MATLAB Simulink and Xilinx System Generator (XSG). Performances of efficient architectures are implemented on FPGA ZYBO Z7 Zynq-7020.

关键词： Field programmable gate arrays Blind source separation Generators Signal processing algorithms Hardware Real-time systems Software packages

来源：评论

学校读者我要写书评

暂无评论

Device View Redundancy: an adaptive low-overhead fault tolerance mechanism for many-core system

Device View Redundancy: an adaptive low-overhead fault toler...

引用

international Workshop on Intelligent Communication and Social Networks

作者： Wentao Jia Chunyuan Zhang Jian Fu National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Institute for Informatics University of Amsterdam

ISBN: (纸本)9781479909735

Continued increasing of fault rate in integrate circuit makes processors more susceptible to errors, especially many-core processor. Meanwhile, most systems or applications do not need full fault coverage, which has excessive overhead. So on-demand fault tolerance is desired for these applications. In this paper, we propose an adaptive low-overhead fault tolerance mechanism for many-core system, called Device View Redundancy (DVR). It treats fault tolerance as a device that can be configured and used by application when high reliability is needed. Nevertheless, DVR exploits the idle resources for low-overhead fault tolerance, which is based on the observation that the utilization of many-core system is low due to lack of parallelism in application. Finally, the experiment shows that the performance overhead of DVR is reduced by 16% to 98% compared with full Dual Modular Redundancy (DMR).

关键词： On-demand redundancy Idle resource exploitation Dynamic coupling Low-overhead Many core system

来源：评论

学校读者我要写书评

暂无评论

Adapting neural architectures between domains 20

Adapting neural architectures between domains

引用

Proceedings of the 34th international conference on Neural Information processing Systems

作者： Yanxi Li Zhaohui Yang Yunhe Wang Chang Xu School of Computer Science University of Sydney Australia Noah's Ark Lab Huawei Technologies China and Key Lab of Machine Perception (MOE) Department of Machine Intelligence Peking University China Noah's Ark Lab Huawei Technologies China

ISBN: (纸本)9781713829546

Neural architecture search (NAS) has demonstrated impressive performance in automatically designing high-performance neural networks. the power of deep neural networks is to be unleashed for analyzing a large volume of data (e.g. ImageNet), but the architecture search is often executed on another smaller dataset (e.g. CIFAR-10) to finish it in a feasible time. However, it is hard to guarantee that the optimal architecture derived on the proxy task could maintain its advantages on another more challenging dataset. this paper aims to improve the generalization of neural architectures via domain adaptation. We analyze the generalization bounds of the derived architecture and suggest its close relations with the validation error and the data distribution distance on both domains. these theoretical analyses lead to AdaptNAS, a novel and principled approach to adapt neural architectures between domains in NAS. Our experimental evaluation shows that only a small part of ImageNet will be sufficient for AdaptNAS to extend its architecture success to the entire ImageNet and outperform state-of-the-art comparison algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TripleID: A low-overhead representation and querying using GPU for large RDFs

Communications in Computer and Information Science

引用

Communications in Computer and Information Science 2016年 613卷 400-415页

作者： Chantrapornchai, Chantana Choksuchat, Chidchanok Haidl, Michael Gorlatch, Sergei Department of Computer Engineering Kasetsart University Bangkok Thailand Department of Computing Silpakorn University Bangkok Thailand University of Münster Münster Germany

ISBN: (纸本)9783319340982

Resource Description Framework (RDF) is a commonly used format for semantic web processing. It basically contains strings representing terms and their relationships which can be queried or inferred. RDF is usually a large text file which contains many million relationships. In this work, we propose a framework, TripleID, for processing queries of large RDF data. the framework utilises Graphics processing Units (GPUs) to search RDF relations. the RDF data is first transformed to the encoded form suitable for storing in the GPU memory. then parallel threads on the GPU search the required data. We show in the experiments that one GPU on a personal desktop can handle 100 million triple relations, while a traditional RDF processing tool can process up to 10 million triples. Furthermore, we can query sample relations within 0.18 s with the GPU in 7 million triples, while the traditional tool takes at least 6 s for 1.8 million triples. © Springer international Publishing Switzerland 2016.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Design and development of high performance, scalable content based publish subscribe system: doctoral symposium 16

Design and development of high performance, scalable content...

引用

Proceedings of the 10th ACM international conference on Distributed and Event-based Systems

作者： M. A. Shah D. B. Kulkarni Walchand College of Engineering Vishrambag Sangli

ISBN: (纸本)9781450340212

In many application scenarios, content based pub/sub systems are required to provide stringent service guarantees such as reliable delivery, high performance in terms of throughput and low latency for event notification to interested subscribers. Matching algorithm play a critical role in content based pub/sub systems. the aim of our work is design and development of parallel, scalable and high performance content based publish subscribe system. We parallelize event processing using thread based and multi GPU approaches. We achieved low latency and high throughput when pub/sub is deployed on Apache Storm, a real time event processing system. throughput gain and reduction in matching time is nearly 48% and 40% respectively in multi GPGPU approach of event processing compared to earlier work mentioned in [1].

关键词： throughput matching algorithm matching time multiple GPGPU real time event processing system data decomposition

来源：评论

学校读者我要写书评

暂无评论

Fast and accurate implementation of Canny edge detector on embedded many-core platform

Fast and accurate implementation of Canny edge detector on e...

引用

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Taieb Lamine Ben Cheikh Gabriela Nicolescu Jelena Trajkovic Youcef Bouchebaba Pierre Paulin Department of Computer Engineering Ecole Polytechnique de Montréal Montréal Canada Department of Electrical and Computer Engineering Concordia University Montréal Canada Synopsys Inc. Ottawa Canada

Image processing and computer vision applications are used intensively in several domains in particular multimedia and medicine. the main challenge in developing such applications is how to guarantee both high accuracy and low execution time. Accordingly, we observe two research directions: the first focuses on improving the algorithms and the second focuses on designing fast hardware platforms. In this paper, we propose an efficient parallel implementation of an accurate extended Canny edge detection algorithm suitable for medical applications on embedded many-core platform. the proposed implementation is running at a frame rate of 10 frames/s for image size of 512×512 with high accurate and smooth line edges.

关键词： Image edge detection Computer architecture Fabrics Accuracy Graphics processing units Hardware Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Investigation into Massively parallel MIMD Architecture based IPU System through Application Benchmarking

Investigation into Massively Parallel MIMD Architecture base...

引用

international conference on Information Technology, Computer and Electrical Engineering (ICITACEE)

作者： Shashank Sharma Samrit Kumar Maity Krishan Gopal Gupta Abhishek Das Mohammad Sajeed Sanjay Wandhekar HPC Technologies C-DAC Pune India

We present a performance benchmarking analysis of Intelligent processing Unit (IPU). IPU is a new architecture developed by Graphcore, specifically designed for handling Neural Network (NN) and Graph Computing (GC) workloads. IPU-POD16 is a 5U server solution, from Graphcore, consisting of four IPU servers and one host server. Each IPU server (IPU M2000) consists of 4 MK2 GC200 IPU. Our performance evaluation is focused on two aspects. First -To measure throughput, considering IPU-POD16 as a single machine, Second-To assess the scalability, by varying the number of IPUs assigned to current workload. For compute workload we used the Tensorflow implementation of ResNet-50 and performed training and validation with the Imagenet dataset. Experiments are conducted to measure the performance of the IPU system with respect to scaling, precision, network latency by devising three separate strategies. We reported throughput numbers (images/second) for training and validation, with both real data and synthetic data. Our initial conclusion is that applications are easy to port and run in the IPU platform, due to availability and support of popular frameworks like tensorflow and pytorch. In order to fully utilize the capabilities of the IPU hardware platform, advanced engineering techniques are required. In this case, we measured the performance by benchmarking with limited application varieties. More study and experimentation are required to fully understand and realize the power of the architecture (computation, networking). It would also be interesting to see how applications from other domains (other than AI/ML/DL) take benefit of this new platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Handwritten Signature Recognition using parallel CNNs and Transfer Learning for Forensics

Handwritten Signature Recognition using Parallel CNNs and Tr...

引用

international conference on Control, Decision and Information Technologies (CoDIT)

作者： Jaouhar Fattahi Feriel Sghaier Mohamed Mejri Ridha Ghayoula Emil Pricop Baha Eddine Lakdher Department of Computer Science and Software Engineering Laval University Quebec Canada Carthage National Engineering School Carthage University Tunis Tunisia Faculty of Engineering University of Moncton Canada Computers & Electronics Department Automatic Control Petroleum-Gas University of Ploieşti Ploieşti Romania Faculty of Science University of Monastir Monastir Tunisia

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Handwritten signatures hold paramount importance in legal, financial, and administrative domains, necessitating the development of robust signature recognition tools for forensic applications. this paper introduces a handwritten signature recognition (HSR) model employing parallel Convolutional Neural Networks (CNN) tailored for forensic endeavors. Utilizing the parallel processing capabilities of CNN, our proposed approach adeptly analyzes and extracts discriminative features from handwritten signature images to facilitate precise recognition. In addition, we leverage several transfer learning techniques by parallelizing proven pre-trained CNNs. Extensive experimentation validates the efficacy of our approach on a standard dataset, demonstrating high accuracy and resilience in signature recognition tasks. the proposed approach exhibits substantial promise in augmenting forensic investigations by automating signature verification processes, thereby bolstering fraud detection efforts and upholding the integrity of legal documentation.

关键词： Deep learning Handwriting recognition Forensics Face recognition Transfer learning Feature extraction Fraud Convolutional neural networks Standards Resilience

来源：评论

学校读者我要写书评

暂无评论

Stateful complex event detection on event streams using parallelization of event stream aggregations and detection tasks 16

Stateful complex event detection on event streams using para...

引用

Proceedings of the 10th ACM international conference on Distributed and Event-based Systems

作者： Saeed Fathollahzadeh Kia Teymourian Mohsen Sharifi Iran University of Science and Technology Rice University

ISBN: (纸本)9781450340212

Detection of stateful complex event patterns using parallel programming features is a challenging task because of statefulness of event detection operators. parallelization of event detection tasks needs to be implemented in a way that keeps track of state changes by new arriving *** this paper, we describe our implementation for a customized complex event detection engine by using Open Multi-processing (OpenMP), a shared memory programming model. In our system event detection is implemented using Deterministic Finite Automata (DFAs). We implemented a data stream aggregator that merges 4 given event streams into a sequence of C++ objects in a buffer used as source event stream for event detection in a next processing step. We describe implementation details and 3 architectural variations for stream aggregation and parallelized of event processing. We conducted performance experiments with each of the variations and report some of our experimental results. A comparison of our performance results shows that for event processing on single machine with multi cores and limited memory, using mutli-threads with shared buffer has better stream processing performance than an implementation with multi-processes and shared memory.

关键词： event detection data streams complex event processing

来源：评论

学校读者我要写书评

暂无评论

Doped Fiber Lasers: from Telecom to Industrial Applications

Doped Fiber Lasers: from Telecom to Industrial Applications

引用

Proceedings of 2008 10th Anniversary international conference on Transparent Optical Networks

作者： Stefano Selleri Federica Poli Information Engineering Department University of Parma 43100 -

Erbium and ytterbium doped fiber lasers are becoming important sources from telecom to industrial applications. this work focuses on laser architectures for non-conventional telecommunication bands and high power puls... 详细信息

ISBN: (纸本)9781424426257;9781424426256

关键词： fiber lasers erbium-doped ytterbium-doped S-band amplification material processing

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：