检索结果-内蒙古大学图书馆

algorithms, Computing and Artificial Intelligence (ACAI), International Conference on

作者： Tianyu Huang Zhijiong Wang Guannan Hu Sio Hang Pun Hung Chun Li Mang I Vai Department of Electrical and Computer Engineering Joint Laboratory of Zhuhai UM Science and Technology Research Institute - Lingyange Semiconductor Incorporated University of Macau Macao China Department of Electrical and Computer Engineering Joint Laboratory of Zhuhai UM Lingyange Semiconductor Incorporated Science and Technology Research Institute - Lingyange Semiconductor Incorporated University of Macau Macao China Joint Laboratory of Zhuhai UM Lingyange Semiconductor Incorporated Science and Technology Research Institute - Lingyange Semiconductor Incorporated Zhuhai China Department of Electrical and Computer Engineering Joint Laboratory of Zhuhai UM Institute of Microelectronics Science and Technology Research Institute - Lingyange Semiconductor Incorporated University of Macau Macao China

ISBN: (数字)9798331529314

ISBN: (纸本)9798331529321

Electrocardiogram (ECG) is an important non-invasive technique for diagnosing cardiovascular diseases (CVD). After acquiring the patients' raw ECG signal data, signal processing is essential for the diagnosis. Conventional ECG signal processing is usually performed serially, which takes a long time to process signals with large amounts of data. In this study, we have proposed a GPGPU-based algorithm acceleration system to improve the efficiency of ECG signal processing. This system utilizes OpenCL for parallel algorithm development on GPGPU. GPGPU executes certain steps in the QRS complex detection algorithm via parallel computing, thereby accelerating the algorithmic process. Experimental results showed that the system achieved a speedup of 1.279 compared to serial computing when processing 39 ECG signal sequences in parallel. In addition, our system has been equipped with a progressive transmission mechanism and a function that intelligently determines whether an algorithm can be accelerated. These features make this system practical not only in biomedical signal processing but also in engineering and research fields with large amounts of data.

关键词： Signal processing algorithms Signal processing Electrocardiography Cardiovascular diseases Biomedical communication parallel algorithms Detection algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Scalable Node Embedding algorithms Using Distributed Sparse Matrix Operations

Scalable Node Embedding Algorithms Using Distributed Sparse ...

引用

IEEE International Symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Isuru Ranawaka Ariful Azad Indiana University Bloomington IN USA

ISBN: (数字)9798350364606

ISBN: (纸本)9798350364613

We introduce a distributed memory parallel algorithm for force-directed node embedding that places vertices of a graph into a low-dimensional vector space based on the interplay of attraction among neighboring vertices and repulsion among distant vertices. We develop our algorithms using two sparse matrix operations, SDDMM and SpMM. We propose a configurable pull-push-based communication strategy that optimizes memory usage and data transfers based on computing resources and asynchronous MPI communication to overlap communication and computation. Our algorithm scales up to 256 nodes on distributed supercomputers by surpassing the performance of state-of-the-art algorithms.

关键词： Distributed processing Conferences Data transfer Vectors Supercomputers Sparse matrices parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

A Distributed Feature Extraction Method Based on MapReduce

A Distributed Feature Extraction Method Based on MapReduce

引用

Control, Electronics and Computer Technology (ICCECT), IEEE International Conference on

作者： Yongchang Wang Hongqiang Hu Xuning Liu College of Future Information Technology Shijiazhuang University Shijiazhuang China

ISBN: (数字)9798350380958

ISBN: (纸本)9798350380965

For data with complex dimensions, Kernel Principal Component Analysis (KPCA) is a common method of feature extraction, it has a better generalization performance. However, it often face with significant difficulties in computation on large datasets. Therefore, we developed a parallel KPCA algorithm based on MapReduce (MRKPCA) in this paper, it's a parallel computing method which can run in a cluster. We apply our algorithm to an experiment of datasets of face recognition, the experimental results show that our algorithm can scale well and has better timeliness for some specific problems which require a lot of computation, and it can significantly reduce computation time.

关键词： Face recognition Clustering algorithms Distributed databases Feature extraction parallel algorithms Kernel Standards

来源：评论

学校读者我要写书评

暂无评论

Research on GPU Accelerated Polar Power Flow Calculation

Research on GPU Accelerated Polar Power Flow Calculation

引用

Energy, Power and Electrical Engineering (EPEE), International Conference on

作者： Haowei Li Tong Jiang School of Electrical and Electronic Engineering North China Electric Power University Beijing China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

The increasing scale of power systems necessitates corresponding enhancements in the speed and accuracy of power flow calculations. Leveraging the study of Graphics Processing Unit (GPU) architecture, parallel algorithms, and power flow calculation methods, we exploit the high parallelism offered by GPU. In this paper, we optimize the Newton method under traditional polar coordinates to develop parallel programs and utilize Compute Unified Device Architecture (CUDA) for data parallel computing. Simulation results demonstrate that as the number of nodes in the test system increases, our proposed program exhibits more pronounced advantages, effectively improving power flow calculation speed and providing a promising approach for further research in this field.

关键词： Electrical engineering Accuracy Simulation Graphics processing units Computer architecture Programming Power systems Newton method parallel algorithms Load flow

来源：评论

学校读者我要写书评

暂无评论

Generating Robust Counterfactual Witnesses for Graph Neural Networks

Generating Robust Counterfactual Witnesses for Graph Neural ...

引用

International Conference on Data Engineering

作者： Dazhuo Qiu Mengying Wang Arijit Khan Yinghui Wu Aalborg University Denmark Case Western Reserve University USA

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

This paper introduces a new class of explanation structures, called robust counterfactual witnesses (RCWs), to provide robust, both counterfactual and factual explanations for graph neural networks. Given a graph neural network $\mathcal{M}$ , a robust counterfactual witness refers to the fraction of a graph $G$ that are counterfactual and factual explanation of the results of $\mathcal{M}$ over $G$ , but also remains so for any “disturbed” $G$ by flipping up to $k$ of its node pairs. We establish the hardness results, from tractable results to co-NP-hardness, for verifying and generating robust counterfactual witnesses. We study such structures for GNN-based node classification, and present efficient algorithms to verify and generate RCWs. We also provide a parallel algorithm to verify and generate RCWs for large graphs with scalability guarantees. We experimentally verify our explanation generation process for benchmark datasets, and showcase their applications.

关键词： Scalability Benchmark testing Data engineering Graph neural networks Classification algorithms parallel algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

parallel Breadth-First Search and Exact Shortest Paths and Stronger Notions for Approximate Distances

arXiv

引用

arXiv 2022年

作者： Rozhoň, Václav Haeupler, Bernhard Martinsson, Anders Grunau, Christoph Zuzic, Goran ETH Zurich Switzerland Carnegie Mellon University United States

We introduce stronger notions for approximate single-source shortest-path distances, show how to efficiently compute them from weaker standard notions, and demonstrate the algorithmic power of these new notions and transformations. One application is the first work-efficient parallel algorithm for computing exact single-source shortest paths graphs - resolving a major open problem in parallel computing. Given a source vertex in a directed graph with polynomially-bounded nonnegative integer lengths the algorithm computes an exact shortest path tree in mlogO(1) n work and n1/2+o(1) depth. Previously, no parallel algorithm improving the trivial linear depths of Dijkstra's algorithm without significantly increasing the work was known, even for the case of undirected and unweighted graphs (i.e., for computing a BFS-tree). Our main result is a black-box transformation that uses logO(1) n standard approximate distance computations to produce approximate distances which also satisfy the subtractive triangle inequality (up to a (1 + Ε) factor) and even induce an exact shortest path tree in a graph with only slightly perturbed edge lengths. These strengthened approximations are algorithmically significantly more powerful and overcome well-known and often encountered barriers for using approximate distances. In directed graphs they can even be boosted to exact distances. This results in a black-box transformation of any (parallel or distributed) algorithm for approximate shortest paths in directed graphs into an algorithm computing exact distances at essentially no cost. Applying this to the recent breakthroughs of Fineman et al. for compute approximate SSSP-distances via approximate hopsets gives new parallel and distributed algorithm for exact shortest paths. Copyright © 2022, The Authors. All rights reserved.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

parallelized Equivalence Principle Algorithm for Multiple PEC Bodies of Revolution

Parallelized Equivalence Principle Algorithm for Multiple PE...

引用

International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications (MAPE)

作者： Jinwei Zhang Jihong Gu Mengmeng Li Dazhi Ding School of Microelectronics (School of Integrated Circuits) Nanjing University Science & Technology Nanjing China

ISBN: (数字)9798331533922

ISBN: (纸本)9798331533939

parallelized equivalence principle algorithm (EPA) for multiple PEC bodies of revolution (BoR) is proposed. Due to the introduction of the equivalent spheres (ES), the scattering and translation operators of EPA for Fourier modes can be obtained independently, making the parallel algorithm more efficient. The strategies based on supercomputer architecture for matrix generation and solver are both developed.

关键词： Microwave antennas Wireless communication Translation Scattering Microwave communication Electromagnetic compatibility Supercomputers parallel algorithms Microwave propagation

来源：评论

学校读者我要写书评

暂无评论

EEiF: Efficient Isolated Forest with e Branches for Anomaly Detection

EEiF: Efficient Isolated Forest with e Branches for Anomaly ...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yifan Zhang Haolong Xiang Xuyun Zhang Xiaolong Xu Wei Fan Qin Zhang Lianyong Qi School of software Nanjing University of Information Science and Technology China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China School of Computing Macquarie University Australia Uffield Department of Women's & Reproductive Health University of Oxford England College of Computer Science and Software Engineering Shenzhen University China Faculty of Science and Engineering University of Petroleum (East China) China

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods.

关键词： Learning systems Training Accuracy Clustering algorithms Forestry Network security Fraud Time complexity parallel algorithms Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

On the parallel Parameterized Complexity of MaxSAT Variants

arXiv

引用

arXiv 2022年

作者： Bannach, Max Skambath, Malte Tantau, Till Institute for Theoretical Computer Science Universität zu Lübeck Germany Department of Computer Science Kiel University Germany

In the maximum satisfiability problem (max-sat) we are given a propositional formula in conjunctive normal form and have to find an assignment that satisfies as many clauses as possible. We study the parallel parameterized complexity of various versions of max-sat and provide the first constant-time algorithms parameterized either by the solution size or by the allowed excess relative to some guarantee ("above guarantee" versions). For the dual parameterized version where the parameter is the number of clauses we are allowed to leave unsatisfied, we present the first parallel algorithm for max-2sat (known as almost-2sat). The difficulty in solving almost-2sat in parallel comes from the fact that the iterative compression method, originally developed to prove that the problem is fixed-parameter tractable at all, is inherently sequential. We observe that a graph flow whose value is a parameter can be computed in parallel and use this fact to develop a parallel algorithm for the vertex cover problem parameterized above the size of a given matching. Finally, we study the parallel complexity of max-sat parameterized by the vertex cover number, the treedepth, the feedback vertex set number, and the treewidth of the input's incidence graph. While max-sat is fixed-parameter tractable for all of these parameters, we show that they allow different degrees of possible parallelization. For all four we develop dedicated parallel algorithms that are constructive, meaning that they output an optimal assignment - in contrast to results that can be obtained by parallel meta-theorems, which often only solve the decision version. © 2022, CC BY.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Stock Market Portfolio Valuation Using CPU Based parallelism

Stock Market Portfolio Valuation Using CPU Based Parallelism

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： Kumaran K Sarath Rajan Senthilkumar P Kiranteja Arun Karthik Anand Kumar P K Desigan School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

In the past decade, the volume and variety of financial instruments has grown exponentially. Hence, portfolio valuation has become a computationally intensive task, especially for large portfolios and complex financial models. This research explores the application of CPU-based parallelism to accelerate the valuation process. By utilizing the multi-core architecture of modern processors, we aim to significantly reduce computation time without compromising accuracy. The study investigates the implementation of parallel algorithms for various valuation methodologies, pricing models, and risk analysis. We develop a system where we calculate a user's portfolio using parallel computation. We divide a portfolio into sub-portfolios and using Python's multiprocessing module, distribute the workload across multiple cores of the CPU. The suggested method's performance is assessed across a range of portfolio sizes and contrasted with serial valuation techniques. The results show that parallel processing speeds up the calculation by 77% compared to serial mode of processing. parallel method of valuation was also found to be more efficient for large portfolio sizes. The findings contribute to the development of efficient and scalable portfolio valuation systems, enabling faster decision-making and risk management. The findings of this study accelerate the development of high-performance computing solutions for the financial industry.

关键词： Training Computational modeling Scalability High performance computing Real-time systems Stock markets Sustainable development parallel algorithms Portfolios Cost accounting

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：