检索结果-内蒙古大学图书馆

Computer parallel Rijndael algorithm optimization based on data stream decomposition

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019年第1_suppl期19卷 S307-S312页

作者： Wang, Cuiping Rizhao Vocat & Tech Coll Business Sch Rizhao 276800 Shandong Peoples R China

An order to improve the execution efficiency of Rijndael algorithm, starting from the analysis of the transformation of the core part of the Rijndael algorithm, a method based on data stream decomposition was proposed in the multi-core platform for parallel optimization of Rijndael algorithm. The main method adopted is to divide the effect of each component transformation of the wheel transform on the whole state into the effect of each component unit of the state, so that the component transformation can be carried out in parallel. The experimental results show that the average acceleration ratio of the decomposition of Rijndael algorithm based on data stream is 1.0674, and the performance is 6.74% higher than before. Therefore, the scheme of parallel optimization of Rijndael algorithm based on data flow decomposition is feasible, and the performance improvement brought by parallel optimization of Rijndael algorithm basically meets the expected requirements of the experiment.

关键词： Rijndael algorithm data stream decomposition parallel optimization computer

来源：评论

学校读者我要写书评

暂无评论

Robust Federated Averaging via Outlier Pruning

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 409-413页

作者： Uddin, Md Palash Xiang, Yong Yearwood, John Gao, Longxiang Deakin Univ Sch Informat Technol Geelong Vic 3220 Australia

Federated Averaging (FedAvg) is the baseline Federated Learning (FL) algorithm that applies the stochastic gradient descent for local model training and the arithmetic averaging of the local models' parameters for global model aggregation. Succeeding FL works commonly utilize the arithmetic averaging scheme of FedAvg for the aggregation. However, such arithmetic averaging is prone to the outlier model-updates, especially when the clients' data are non-Independent and Identically Distributed (non-IID). As such, the classical aggregation approach suffers from the dominance of the outlier updates and, consequently, causes high communication costs towards producing a decent global model. In this letter, we propose a robust aggregation strategy to alleviate the above issues. In particular, we propose first pruning the node-wise outlier updates (weights) from the local trained models and then performing the aggregation on the selected effective weights-set at each node. We provide the theoretical result of our method and conduct extensive experiments on the MNIST, CIFAR-10, and Shakespeare datasets with IID and non-IID settings, which demonstrate that our aggregation approach outperforms the state-of-the-art methods in terms of communication speedup, test-set performance and training convergence.

关键词： Training Servers Data models Arithmetic Costs Convergence Computational modeling Distributed deep learning federated learning parallel optimization robust aggregation outlier pruning

来源：评论

学校读者我要写书评

暂无评论

Fast weighted CP decomposition for context-aware recommendation with explicit and implicit feedback

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 204卷

作者： Zhao, Jianli Zheng, Shidong Huo, Huan Gong, Maoguo Zhang, Tianheng Qu, Lijun Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Ultimo Australia Xidian Univ Key Lab Intelligent Percept & Image Understanding Minist Educ Xi'an 710071 Peoples R China

As an effective method for high-dimensional information processing, tensor factorization has been widely used in context-aware recommendation. However, the multi-dimensional processing of tensor factorization usually leads to more serious data sparsity. Making full use of the data in recommendation systems, including a small amount of explicit rating data and a large amount of implicit feedback data such as clicks, plays, and purchases, can effectively alleviate this problem. Meanwhile, the processing of sparse explicit data and huge implicit feedback data makes tensor factorization face a severe challenge of computational efficiency. Therefore, this study proposes a fast tensor factorization model named FWCP that unifies explicit and implicit feedback information, which mainly studies as follows: (1) Assigning non-uniform weights to observed and unobserved values to unify explicit and implicit feedback information;(2) Memorizing intermediate data which generated by element-wise alternating least squares(ALS), and implementing parallel optimization of FWCP, which can reduce the training time of tensor factorization based on whole-data. The evaluation results on two real datasets showed that FWCP proposed in this study is superior to other context-aware recommendation algorithms.

关键词： Context-aware recommendation Tensor factorization Explicit and implicit feedback Element-wise alternating least squares parallel optimization

来源：评论

学校读者我要写书评

暂无评论

HPGA: An Improved Hybrid Genetic Algorithm with parallel Acceleration for Dynamic Flexible Job-shop Scheduling Problem 24

HPGA: An Improved Hybrid Genetic Algorithm with Parallel Acc...

引用

7th International Conference on Big Data Technologies

作者： Zou, Chenglong Huang, Zhenqi Qin, Xiulei Huang, Yonggui Liu, Yunhuai Peking Univ Sch Math Sci Beijing Peoples R China Peking Univ Chongqing Res Inst Big Data Chongqing Peoples R China

ISBN: (纸本)9798400717512

Flexible job-shop scheduling problem (FJSP) is a well-known and complex variant of the classical Job-shop scheduling Problem ( JSP), which finds significant applications in manufacturing industries where flexibility in the use of machines is crucial for enhancing production efficiency and reducing operational costs. Currently, many popular hybrid meta-heuristic algorithms which involve combining two or more metaheuristic strategies such as genetic algorithm (GA) and tabu search (TS) procedures, often leads to improved performance in terms of solution quality and computational efficiency. In this paper, we design an improved hybrid genetic algorithm with parallel acceleration (HFGA) for dynamic FJSP with new job insertion, which can further speed up the execution of each operator including selection, crossover, mutation and local search. Experimental results show that our proposed hybrid algorithm with parallel acceleration demonstrates quite superior performance.

关键词： Genetic algorithm parallel optimization Flexible job-shop scheduling

来源：评论

学校读者我要写书评

暂无评论

parallel optimization OF HYPERSPECTRAL UNMIXING BASED ON SPARSITY CONSTRAINED NONNEGATIVE MATRIX FACTORIZATION

PARALLEL OPTIMIZATION OF HYPERSPECTRAL UNMIXING BASED ON SPA...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Wu, Zebin Ye, Shun Wei, Jie Liu, Jianjun Wei, Zhihui Sun, Le NJUST Sch Comp Sci & Technol Nanjing 210094 Jiangsu Peoples R China NJUST Lianyungang Res Inst Lianyungang 222006 Peoples R China Jiangsu Key Lab Spectral Imaging & Intelligent Se Nanjing 210094 Peoples R China

ISBN: (纸本)9781479911141

Hyperspectral unmixing is a typical problem of blind source separation, which can be solved by nonnegative matrix factorization (NMF). Sparsity based NMF will increase the efficiency of unmixing, but its computational complexity limits the possibility of utilizing it in time-critical applications. In this paper, method of parallel hyperspectral unmixing based on sparsity constrained nonnegative matrix factorization on Graphics Processing Units (CSNMF-GPU) is investigated and compared in terms of both accuracy and speed. The realization of the proposed method using Compute Unified Device Architecture (CUDA) on GPU are described and evaluated. The experimental results comparing with the serial implementations based on both simulated and real hyperspectral data demonstrate the effectiveness of the proposed parallel optimization approach.

关键词： hyperspectral unmixing parallel optimization sparsity nonegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Replicable Self-Documenting Experiments with Arbitrary Search Spaces and Algorithms

Replicable Self-Documenting Experiments with Arbitrary Searc...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Weise, Thomas Wu, Zhize Hefei Univ Inst Appl Optimizat Sch Artificial Intelligence & Big Data Hefei Anhui Peoples R China

ISBN: (纸本)9798400701207

We introduce moptipy, a toolbox for implementing, experimenting with, and applying optimization algorithms. It features mechanisms for executing fully reproducible experiments. Our seeding procedure for random number generators makes our experiments deterministic. Our system creates self-documenting log files that store the algorithm setup, the system configuration, the random seed, the final solutions, and the progress of the optimization algorithm over time. The parallelization and distribution of experiments works on most operating systems and requires no additional synchronization, inter-process-communication, or libraries. moptipy supports both single- and multi-objective optimization with arbitrary search spaces. Time measurements and computational budgets can be based both on wall clock time and objective function evaluations. moptipy is also an educational platform with comprehensive documentation and an accompanying free electronic book introducing the basic concepts of metaheuristics, discussing the implemented algorithms, and showing their performance on basis of actual experimental results.

关键词： metaheuristics software Python reproducibility parallel optimization distributed optimization

来源：评论

学校读者我要写书评

暂无评论

Exploiting Interference in Joint Radar-Communication Transmission

Exploiting Interference in Joint Radar-Communication Transmi...

引用

IEEE Conference on Global Communications (IEEE GLOBECOM) - Intelligent Communications for Shared Prosperity

作者： Zhang, Jianjun Liu, Fan Masouros, Christos Huang, Yongming Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen Peoples R China UCL Dept Elect & Elect Engn London England Southeast Univ Natl Mobile Commun Res Lab Nanjing Peoples R China

ISBN: (纸本)9798350310900

By sharing the same hardware platform, spectral resource as well as transmit waveform, dual-functional radar-communication (DFRC) based integrated sensing and communication (ISAC) framework has been envisioned as a key technology for future wireless networks. Most DFRC beamforming works focus on block-level precoding, which fails to exploit constructive interference. To tackle this issue, we propose symbol-level joint radar sensing and communication beamforming algorithms in this paper. First, we formulate the problem of joint radar-communication beamforming based on symbol-level precoding (SLP) by incorporating constructive interference into SLP, so as to improve the energy efficiency. To address the formulated problem, we tailor a highly parallelizable iterative algorithm, which is shown to converge to stationary points. To achieve better performance, we further propose an efficient recursive optimization algorithm. In particular, the recursive algorithm monotonously improves the performance of interest as the recursive procedure proceeds.

关键词： Integrated sensing and communication symbollevel precoding parallel optimization recursive design

来源：评论

学校读者我要写书评

暂无评论

A parallel-optimized iterated greedy algorithm for blocking hybrid flow shop scheduling problem 35

A parallel-optimized iterated greedy algorithm for blocking ...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Wang, Yong Wang, Yuting Li, Chengshuai Zhang, Chenyao Wang, Yuhang Liaocheng Univ Sch Comp Sci Liaocheng Shandong Peoples R China

ISBN: (纸本)9798350334722

We study the blocking hybrid flow shop scheduling problem (BHFSP) aiming at maximum completion time in this paper, which has practical implications in the manufacturing industry. A parallel-optimized iterated greedy (POIG) algorithm is presented to optimize the objective of minimizing the maximum completion time. The whole POIG algorithm adopts a parallel scheme to increase the solution diversity. First, the NEH and MME heuristics are used to initialize the two solutions;subsequently, to strengthen the performance of the POIG and make machine blocking timeless, two permutation-based local perturbation strategies are proposed;using simulated annealing (SA) algorithm to increase the solution diversity. The proposed algorithm is tested against other algorithms on 100 instance sets of different scales. The final simulation experiments show that the POIG performs better than other comparison algorithms, and it can be considered as an effective solution to the BHFSP.

关键词： Blocking parallel optimization iterated greedy algorithm hybrid flow shop scheduling problem makespan

来源：评论

学校读者我要写书评

暂无评论

PESA: Prioritized experience replay for parallel hybrid evolutionary and swarm algorithms-Application to nuclear fuel

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2022年第10期54卷 3864-3877页

作者： Radaideh, Majdi I. Shirvan, Koroush MIT Dept Nucl Sci & Engn Cambridge MA 02139 USA

We propose a new approach called PESA (Prioritized replay Evolutionary and Swarm Algorithms) combining prioritized replay of reinforcement learning with hybrid evolutionary algorithms. PESA hy-bridizes different evolutionary and swarm algorithms such as particle swarm optimization, evolution strategies, simulated annealing, and differential evolution, with a modular approach to account for other algorithms. PESA hybridizes three algorithms by storing their solutions in a shared replay memory, then applying prioritized replay to redistribute data between the integral algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly to improve PESA exploitation close to the end of evolution. PESA features in balancing exploration and exploitation during search and the parallel computing result in an agnostic excellent performance over a wide range of experiments and problems presented in this work. PESA also shows very good scalability with number of processors in solving an expensive problem of optimizing nuclear fuel in nuclear power plants. PESA's competitive performance and modularity over all experiments allow it to join the family of evolutionary algorithms as a new hybrid algorithm;unleashing the power of parallel computing for expensive optimization.(c) 2022 Korean Nuclear Society, Published by Elsevier Korea LLC. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Hybrid evolutionary algorithms Reinforcement learning parallel optimization Priortized experience replay Nuclear fuel optimization

来源：评论

学校读者我要写书评

暂无评论

Scanline-based fast algorithm and pipelined hardware design of rate-distortion optimized quantization for AVS3

Scanline-based fast algorithm and pipelined hardware design ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Zhao, Jiachen Yang, Fan Huang, Xiaofeng Xiang, Gwoqing Zhang, Peng Zhao, Liping Yan, Wei Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Sch Comp Sci Beijing Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou Peoples R China Hangzhou Dianzi Univ Sch Commun Engn Hangzhou Peoples R China Shaoxing Univ Dept Comp Sci & Engn Shaoxing Peoples R China

ISBN: (纸本)9781665491303

The third generation AVS video coding standard (AVS3) is developed by the China AVS working group, and it achieves a 50% bitrate saving compared to the previous AVS2 standard by adopting several efficient coding tools. Ratedistortion optimized quantization (RDOQ) is one of the effective tools, which decides the optimal quantized coefficient level based on rate-distortion cost. The huge computation complexity and strong data dependency in RDOQ impede the realtime applications, where there is no hardware video encoder supporting RDOQ. To resolve this problem, we propose a zigzag scanline-based fast algorithm and pipelined hardware design for AVS3 RDOQ. Firstly, we introduce an approach to decrease computation and then propose a fully parallel coefficient level decision method where the context is correlated to the current position. Secondly, a zig-zag scanline-based algorithm is proposed to decide the last non-zero pixel position, where the scanlines can be paralleled. Finally, its corresponding hardware architecture design is proposed. Experimental results show that the proposed hardware architecture can support a throughput of 4K@30fps with negligible performance loss when working at 200MHz.

关键词： AVS3 rate-distortion optimized quantization (RDOQ) zig-zag parallel optimization video coding

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：