检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kato, Taiki Yamagiwa, Shinichi Wada, Koichi Master's Program in Computer Science Degree Program in Systems and Information Engineering University of Tsukuba Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350324457

IoT edge platform has become popular in various distributed environments. The edge devices need to communicate BigData among them or with the cloud servers by collaborating with AI technologies for finding events from the applications. Those devices exchange data streams from such as distributed sensors and remote image/video devices. We focus on an acceleration technique for the communication performance using a stream-based lossless data compression technology. This paper proposes a parallelization technique for the compression process in a software environment running on a multicore processor. The technique invokes concurrent compression processes assigned to multiple threads with splitting a data stream to chunks. The paper exposes three scheduling methods for assigning the chunks to the threads: in-order, hybrid and out-of-order. As an original data order of chunks must be obtained in decompression side, the proposed technique introduces packeting mechanisms in each chunk by adding headers to support the scheduling methods. Through experimental performance evaluations, we discuss the packeting overhead focusing on compression ratio and speedup by the parallelization with three scheduling methods. © 2023 IEEE.

关键词： Data Stream IoT Lossless Data Compression Multi-Threading Parallelization

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Stream-Based Decompression Process by Notifying Compression Buffer Size 28

Performance Enhancement of Stream-Based Decompression Proces...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Kato, Taiki Yamagiwa, Shinichi Marumo, Koichi University of Tsukuba Master's Program in Computer Science Degree Program in Systems and Information Engineering Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350300482

This paper focuses on a performance enhancement of communication performance by compressing data stream. ASE coding is an effective lossless data compression method for data stream. The software implementation of the coding/decoding method inevitably meets a performance mismatch in memory and storage devices. In the compressor side, it is predictable to decide the size of an original data block and is available to process a flexible buffer memory. However, the decompressor is not able to predict the buffer size because the original data size is not obvious before the decompression. This causes a performance mismatch in the filesystem level. This paper proposes a novel method to address the performance mismatch by applying a notification mechanism of compression size from the compressor. This paper describes the mechanism focusing on the system call usage. Through experimental evaluations, we show the performance improvement of the decompression performance for handling data stream. © 2023 IEEE.

关键词： Virtual storage

来源：评论

学校读者我要写书评

暂无评论

Implementation and Performance Evaluation of Collective Communications Using CIRCUS on Multiple FPGAs

Implementation and Performance Evaluation of Collective Comm...

引用

2023 International Conference on High Performance Computing in Asia-Pacific Region Workshops, HPC Asia 2023

作者： Kikuchi, Kohei Fujita, Norihisa Kobayashi, Ryohei Boku, Taisuke Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Center for Computational Sciences University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781450399890

In the high-performance computing domain, Field programmable Gate Array (FPGA) is a novel accelerator that exhibits high flexibility and performance characteristics distinct from other accelerators such as the Graphics Processing Unit (GPU). Recent advanced high-end FPGA is equipped with multiple channels of high speed optical link up to 100Gbps performance for each. This is a crucial feature when we construct PC clusters with FPGAs as accelerators, however it is not easy to utilize from user kernels because this feature is implemented in low level and simple direct communication between neighboring FPGAs. In order to provide the communication feature between FPGAs for accelerated PC clusters, we developed a communication system named CIRCUS which implies a user-friendly API from OpenCL and is equipped with routing function over multi-hop communication on multi-dimensional torus network of FPGAs. However, current CIRCUS only provides a point-to-point communication between source and destination FPGAs. In ordinary parallel processing environment such as MPI, the user program the message passing with various collective communication functions for parallel algorithm, for instance Allreduce, Allgather, etc. In this paper, we implement the collective communication function over CIRCUS for user-friendly programming of ordinary parallel algorithms on FPGAs. As the first target, we implement Allreduce function which is the most essential and important function. The paper describes the CIRCUS system briefly followed by the design, implementation and preliminary performance evaluation on Intel Stratix10 FPGAs. © 2023 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification: A LSTM and MediaPipe Approach for Intelligent Systems Application 6

Human Activity Classification: A LSTM and MediaPipe Approach...

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Chen, Yi-An Yang, Pei-Ching Chang Jung Christian University Master Degree Program in Information and Design Tainan Taiwan Chang Jung Christian University Department of Computer Science and Information Engineering Tainan Taiwan Chang Jung Christian University Artificial Intelligence Research Center Tainan Taiwan

ISBN: (纸本)9798331518158

With advancements in artificial intelligence, computer vision technologies have seen significant progress, enabling applications like facial recognition, autonomous driving, and medical imaging. This study leverages the Multi-Camera Action Dataset (MCAD) and MediaPipe Pose to create a skeletal dataset for training a Long Short-Term Memory (LSTM) model to recognize 18 types of daily actions. Evaluation using confusion matrix and F1 score reveals that Action 16 (Object Carry) is often misclassified as Action 7 (Walk) due to similar leg movements, and Action 9 (Cell to Ear) as Action 1 (Wave) due to similar hand movements. Future work aims to enhance model accuracy and explore broader applications in physical activity and exercise analysis. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Improved IP lookup technology for trie-based data structures

引用

Journal of computer and System sciences 2023年 133卷 41-55页

作者： Lin, Yen-Heng Hsieh, Sun-Yuan Master Degree Program on Artificial Intelligence National Cheng Kung University Tainan701 Taiwan Department of Computer Science and Information Engineering Institute of Manufacturing Information Systems Institute of Medical Informatics National Cheng Kung University Tainan701 Taiwan Department of Computer Science and Information Engineering National Chi Nan University Nantou Puli Township54561 Taiwan

Many Internet protocol (IP) lookup algorithms have been formulated to improve network performance. This study reviewed and experimentally evaluated technologies for trie-based methods that reduce memory access, memory consumption and IP lookup time. Experiments involving binary tries (for simplicity) were conducted on four real-world data sets, two of which were on IPv4 router tables (855,997 and 876,489 active prefixes) and two of which were on IPv6 router tables (155,310 and 157,579 active prefixes). Technologies designed to reduce time taken (at the expense of memory consumption) worked well for IPv4, and those designed to reduce memory consumption worked well for IPv6. Various combinations of these technologies were applied together in the experiments. © 2022 Elsevier Inc.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

A Design Study on Integrated Complex Coefficient Filters with Peripheral Circuits for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2025年第1期145卷 16-24页

作者： Shouno, Kazuhiro Sato, Lina Fukagawa, Kanta Tanimoto, Hiroshi Muto, Cosy Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan

This paper proposes a measurement technique for an integrated complex filter. The proposed method is based on two measurement methods with integrated circuitry for calibration. It is accomplished by applying square waves to an FUT (Filter Under Test) instead of sinusoidal waves or by superposing transfer characteristics obtained by applying a single sinusoidal wave to an FUT. In both of the above methods, the output signal connected to the external measurement equipment via a 50 Ω coaxial cable and so on. In this case, the output signal of the FUT should be amplified by internal or external amplifiers, which degrades the response. However, it is cancelled out by the proposed calibration circuitry with some analog switches. In addition to the above, for the RC polyphase filter, the source resistance and the load capacitance degrade the measurement results and their effect is discussed. The validity of the proposal is confirmed through computer simulation for a third-order RCPF whose passband is 8–40 MHz fabricated by Phenitec 0.6 µm CMOS process. It is shown that the measurement error is −1.10 dB for the square-wave method and −1.00 dB and −0.43 degrees for the superposition method at 40 MHz. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Using SYCLomatic to Migrate CUDA Code to oneAPI Adapting NVIDIA GPU

Using SYCLomatic to Migrate CUDA Code to oneAPI Adapting NVI...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Wentao Liang Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Program in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

Nowadays, the use of accelerators in high performance computing has become more common than ever before. The most used accelerators must be the Graphics Processing Unit (GPU). It has emerged as an important component in most of the parallel computing scenarios, surpassing the capabilities of the traditional Central Processing Unit (CPU) in perspective of both performance and energy efficiency.

关键词： Codes Conferences High performance computing Graphics processing units Cluster computing Parallel processing Energy efficiency Central Processing Unit

来源：评论

学校读者我要写书评

暂无评论

The design of the cse-ucla evaluation model using topsis and ahp methods for optimizing digital library services in badung regency 3

The design of the cse-ucla evaluation model using topsis and...

引用

3rd International Conference on Vocational Education and Technology, IConVET 2020

作者： Atmaja, I.M.D.S. Divayana, D.G.H. Setemen, K. Master Degree Program in Computer Science Universitas Pendidikan Ganesha Indonesia Universitas Pendidikan Ganesha Indonesia

The Regional Archives and Library Office of Badung Regency must optimize the services provided in order to achieve excellent service quality. In its implementation, the office encountered difficulties in prioritizing aspects of services that require optimization. The purpose of this study was to design a Center for the Study of Evaluation-University of California in Los Angeles (CSE-UCLA) evaluation model using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Analytical Hierarchy Process (AHP) to provide recommendations on which aspects of services need to be optimized. The research method used stages that included problem identification, problem formulation, literature review, data collection, data analysis, design, and conclusions. The TOPSIS and AHP methods had the ability to rank a variety of aspects in the CSE-UCLA model. Aspect with the lowest ranking was considered as the aspect that is prioritized for optimization. That aspects used five service criteria: Tangible, reliability, assurance, responsiveness, and empathy, all of which were classified in the "benefit"category. Each criterion had a value of 0.200, 0.200, 0.200, 0.200, 0.200 for the weight values for system assessment, program planning, program implementation, and program improvement, while for program certification: 0.556, 0.111, 0.111, 0.111, 0.111, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

Preliminary Evaluation of Kyokko for Inter-FPGA Communication Framework CIRCUS

Preliminary Evaluation of Kyokko for Inter-FPGA Communicatio...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Kaito Kitazume Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

In recent years, Field-programmable Gate Arrays (FPGAs) are gaining attention as computational acceleration devices in the field of high-performance computing. By implementing specialized circuits that can be customiz... 详细信息

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

关键词： Conferences High performance computing Circuits Cluster computing Low latency communication Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

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

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

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：