检索结果-内蒙古大学图书馆

HLS-Based Large Scale Self-Organizing Feature Maps

IEEE ACCESS 2024年 12卷 142459-142474页

作者： Porrmann, Florian Hagemeyer, Jens Porrmann, Mario Bielefeld Univ Cognitron & Sensor Syst Grp CITEC D-33615 Bielefeld Germany Osnabruck Univ Inst Comp Sci Comp Engn Grp D-49090 Osnabruck Germany

The Self-Organizing Map (SOM) algorithm is a clustering algorithm used in a wide variety of application domains. Over the last few decades, it has been accelerated using various hardware architectures, including FPGAs, CPUs, and GPUs. This publication presents an High-Level Synthesis-based implementation that utilizes multiple processing elements to realize a high-performance system architecture. An extensive design space exploration was conducted to evaluate the performance range of the architecture. For this, vector dimensions ranging from 8 up to 512 and map sizes from 16x 16 to 512x512 were used. The evaluation was performed using two different AMD/Xilinx UltraScale+ FPGA systems, the VCU128 PCIe-based accelerator card and the ZCU106 stand-alone evaluation kit. From the achieved results, it can be seen that the performance scales nearly linearly for a given vector dimension when the map size is increased. In addition, the energy efficiency for both FPGAs was analyzed, revealing that while the ZCU106 is less powerful in terms of raw compute power, it requires up to 4x less power and, depending on the configuration, can be 2x more energy efficient compared to the VCU128. One of the main reasons for this is that it does not require a dedicated host system but utilizes its internal ARM cores. Finally, a comparison against state-of-the-art SOM implementations was conducted. The proposed design achieves a speed-up of up to 458.7, 1,630.4 , and 4.9 compared to other CPU, GPU, and FPGA realizations, respectively.

关键词： Neurons Computer architecture clustering algorithms Training Graphics processing units Statistical analysis Space exploration Heterogeneous networks Field programmable gate array hardware acceleration machine learning reconfigurable architectures reconfigurable computing heterogeneous computing heterogeneous architectures self-organizing feature maps optimization design space exploration heterogeneous architectures self-organizing feature maps optimization design space exploration

来源：评论

学校读者我要写书评

暂无评论

Genetic-Based Two Granularity Ordering Methods for Multiple Workflow Scheduling

引用

IEEE ACCESS 2024年 12卷 1747-1760页

作者： Li, Feng Tan, Wen Jun Seok, Moon Gi Cai, Wentong Nanyang Technol Univ Sch Comp Sci & Engn Singapore 6397982 Singapore Dongguk Univ Dept Comp Sci & Engn Seoul 04620 South Korea

In cloud computing, multiple workflow scheduling is important to optimize resource allocation and utilization for concurrent execution of diverse workflows across different applications. While previous research has focused on clustering-based resource allocation to reduce communication overheads by grouping tasks, it often overlooks the significance of task execution ordering, limiting overall performance optimization. To address this limitation, we propose two genetic-based approaches, considering task and cluster-level characteristics, to introduce novel ordering techniques for multi-workflow scheduling under cluster-based resource allocation. By comparing two granularity ordering methods, we offer valuable insights for efficient task management in multi-workflow environments. Our experiments demonstrate that the proposed approaches, especially the task granularity-based ordering method, outperform existing primary clustering methods, particularly for scenarios involving a large number of workflows or highly parallel workflows.

关键词： Task analysis Costs Scheduling Resource management Optimization clustering algorithms Quality of service Cloud computing multi-workflow multi-objective optimization task ordering cluster ordering

来源：评论

学校读者我要写书评

暂无评论

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第3期70卷 2039-2075页

作者： Ahn, Junhyung Elmahdy, Adel Mohajer, Soheil Suh, Changho Korea Adv Inst Sci & Technol KAIST Sch Elect Engn Daejeon 34141 South Korea Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA

We study a matrix completion problem which leverages a hierarchical structure of social similarity graphs as side information in the context of recommender systems. We assume that users are categorized into clusters, each of which comprises sub-clusters (or what we call "groups"). We consider a hierarchical stochastic block model that well respects practically-relevant social graphs and follows a low-rank rating matrix model. Under this setting, we characterize the information-theoretic limit on the number of observed matrix entries (i.e., optimal sample complexity) as a function of the quality of graph side information (to be detailed) by proving sharp upper and lower bounds on the sample complexity. One important consequence of this result is that leveraging the hierarchical structure of similarity graphs yields a substantial gain in sample complexity relative to the one that simply identifies different groups without resorting to the relational structure across them. Another implication of the result is when the graph information is rich, the optimal sample complexity is proportional to the number of clusters, while it nearly stays constant as the number of groups in a cluster increases. We empirically demonstrate through extensive experiments that the proposed algorithm achieves the optimal sample complexity.

关键词： Complexity theory Collaborative filtering clustering algorithms Recommender systems Sparse matrices Filtering Information theory matrix completion problem graph side information

来源：评论

学校读者我要写书评

暂无评论

Distributed Nash Equilibrium Seeking for Constrained Multicluster Games of Second-Order Nonlinear Multiagent Systems

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2024年第11期69卷 7855-7862页

作者： Deng, Zhenhua Chen, Tao Cent South Univ Sch Automat Changsha 410075 Peoples R China

This article investigates multicluster games (MCGs) of multiagent systems, where the players are subject to nonlinear inequality constraints. In contrast to existing MCGs, our problem involves the second-order nonlinear dynamics of players. Due to the second-order nonlinear dynamics, existing Nash equilibrium (NE) seeking algorithms cannot deal with our problem. Also, the second-order nonlinear dynamics and the nonlinear inequality constraints make it difficult to design and analyze distributed algorithms for our problem, because it is hard for the players to satisfy the inequality constraints as a result of the second-order dynamics and the inequality constraints must be satisfied by the NE of the MCGs. In order to control these heterogeneous second-order nonlinear players to autonomously seek the NE of the MCGs, we design a distributed algorithm via gradient descent and state feedback. With the help of Lyapunov stability theory, we analyze the convergence of the algorithm. Under the algorithm, the second-order players globally converge to the NE. Finally, the simulation example of electricity market games verifies the effectiveness of the algorithm.

关键词： Heuristic algorithms Games Nonlinear dynamical systems Cost function clustering algorithms Resource management Multi-agent systems Cyber-physical systems multicluster games (MCGs) Nash equilibrium (NE) second-order nonlinear multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Deep-Layer clustering to Identify Permission Usage Patterns of Android App Categories

引用

IEEE ACCESS 2022年 10卷 24240-24254页

作者： Namrud, Zakeya Kpodjedo, Segla Bali, Ahmed Talhi, Chamseddine Ecole Technol Super ETS Dept Software Engn & IT Montreal PQ H3C 1K3 Canada

With the increasing usage of smartphones in banks, medical services and m-commerce, and the uploading of applications from unofficial sources, security has become a major concern for smartphone users. Malicious apps can steal passwords, leak details, and generally cause havoc with users' accounts. Current anti-virus programs rely on static signatures that need to be changed periodically and cannot identify zero-day malware. The Android permission system is the central security mechanism that regulates the execution of application tasks. Although recent advances in research have provided various approaches and detection methods for finding malware apps, the available literature lacks a full analysis of this subject. We fill this gap by: 1) Systematically and automatically building a large dataset of malware and benign apps, which we have made available to the community. Our dataset has around 16K apps and 118 features. 2) We offer a novel approach for automatically identifying permission usage patterns, which are groupings of permissions that developers frequently utilise together. The approach combines SOM and K-means clustering algorithms to classify permissions according to app usage categories. The results demonstrate that the proposed methodology is able to detect most of the consistent and coherent permission usage patterns across a wide variety of application categories. To assess our strategy, we add the identified patterns as features to our dataset and then apply an SVM classifier for malware detection. Our results indicate that the identified patterns improve the performance of the classifier.

关键词： Malware Security Smart phones Internet clustering algorithms Support vector machines Self-organizing feature maps Android permissions android malware empirical study supervised and unsupervised machine learning self organizing map (SOM)

来源：评论

学校读者我要写书评

暂无评论

Sparse Projection Matrix Approximation and Its Applications

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 351-355页

作者： Zhai, Zheng Wu, Mingxin Xu, Jialu Li, Xiaohui Beijing Normal Univ Fac Arts & Sci Dept Stat Zhuhai 519088 Peoples R China Yantai Univ Sch Math & Informat Sci Yantai 264032 Peoples R China

This letter introduces a sparse regularized projection matrix approximation (SPMA) model to recover cluster structures from affinity matrices. The model is formulated as a projection approximation problem with an entry-wise sparsity penalty to encourage sparse solutions. We propose two algorithms to solve this problem: one involves direct optimization on the Stiefel manifold using the Cayley transformation, while the other employs the Alternating Direction Method of Multipliers (ADMM). Numerical experiments on synthetic and real-world datasets demonstrate that our regularized projection matrix approximation approach significantly outperforms state-of-the-art methods in clustering accuracy and performance.

关键词： Sparse matrices Manifolds Approximation algorithms Signal processing algorithms Optimization Convex functions Matrix decomposition Human activity recognition Eigenvalues and eigenfunctions clustering algorithms ADMM clustering regularisation Stiefel manifold sparse projection matrix approximation

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Cluster-Based Energy Management System Using Deep Reinforcement Learning Without Affecting Prosumer Comfort: V2X Technologies and Peer-to-Peer Energy Trading

引用

IEEE ACCESS 2024年 12卷 31551-31575页

作者： Yavuz, Mete Kivanc, Omer Cihan Istanbul Okan Univ Dept Elect & Elect Engn TR-34959 Istanbul Turkiye

The concept of Prosumer has enabled consumers to actively participate in Peer-to-Peer (P2P) energy trading, particularly as Renewable Energy Source (RES)s and Electric Vehicle (EV)s have become more accessible and cost-effective. In addition to the P2P energy trading, prosumers benefit from the relatively high energy capacity of EVs through the integration of Vehicle-to-X (V2X) technologies, such as Vehicle-to-Home (V2H), Vehicle-to-Load (V2L), and Vehicle-to-Grid (V2G). Optimization of an Energy Management System (EMS) is required to allocate the required energy efficiently within the cluster, due to the complex pricing and energy exchange mechanism of P2P energy trading and multiple EVs with V2X technologies. In this paper, Deep Reinforcement Learning (DRL) based EMS optimization method is proposed to optimize the pricing and energy exchanging mechanisms of the P2P energy trading without affecting the comfort of prosumers. The proposed EMS is applied to a small-scale cluster-based environment, including multiple (6) prosumers, P2P energy trading with novel hybrid pricing and energy exchanging mechanisms, and V2X technologies (V2H, V2L, and V2G) to reduce the overall energy costs and increase the Self-Sufficiency Ratio (SSR)s. Multi Double Deep Q-Network (DDQN) agents based DRL algorithm is implemented and the environment is formulated as a Markov Decision Process (MDP) to optimize the decision-making process. Numerical results show that the proposed EMS reduces the overall energy costs by 19.18%, increases the SSRs by 9.39%, and achieves an overall 65.87% SSR. Additionally, numerical results indicates that model-free DRL, such as DDQN agent based Deep Q-Network (DQN) Reinforcement Learning (RL) algorithm, promise to eliminate the energy management complexities with multiple uncertainties.

关键词： Costs Optimization Energy management Vehicle-to-grid clustering algorithms Heuristic algorithms Vehicle-to-everything Peer-to-peer computing Energy exchange Reinforcement learning Deep reinforcement learning Smart grids Energy management system peer-to-peer energy trading vehicle-to-home multi-agent reinforcement learning deep reinforcement learning smart grids

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Mean Shift

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第10期46卷 6688-6698页

作者： Yamasaki, Ryoya Tanaka, Toshiyuki Hitotsubashi Univ Hitotsubashi Inst Adv Study Tokyo 1868601 Japan Kyoto Univ Grad Sch Informat Dept Informat Kyoto 6068501 Japan

The mean shift (MS) algorithm seeks a mode of the kernel density estimate (KDE). This study presents a convergence guarantee of the mode estimate sequence generated by the MS algorithm and an evaluation of the convergence rate, under fairly mild conditions, with the help of the argument concerning the Lojasiewicz inequality. Our findings extend existing ones covering analytic kernels and the Epanechnikov kernel. Those are significant in that they cover the biweight kernel, which is optimal among non-negative kernels in terms of the asymptotic statistical efficiency for the KDE-based mode estimation.

关键词： Kernel Convergence Heuristic algorithms Estimation clustering algorithms Optimization Bandwidth Biweight kernel convergence convergence rate mean shift Lojasiewicz inequality

来源：评论

学校读者我要写书评

暂无评论

Health Feature Extraction and Efficient Sorting of Second-Life Lithium-Ion Batteries

引用

IEEE TRANSACTIONS ON ENERGY CONVERSION 2024年第2期39卷 1373-1382页

作者： Zhou, Zhongkai Duan, Bin Kang, Yongzhe Shang, Yunlong Zhang, Qi Zhang, Chenghui Qingdao Univ Sch Automat Qingdao 266071 Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China

Efficient sorting has always been a difficult problem for a large number of second-life batteries. In this article, a sorting method is developed for second-life batteries based on ordering points to identify the clustering structure (OPTICS) algorithm. A three-dimensional vector is created as health feature to map the aging degree of second-life batteries, including capacity feature, direct current resistance and polarization resistance. The vector can be accurately extracted from a partial charging curve to reduce testing time. Then, the OPTICS algorithm is presented to cluster the second-life batteries with a good consistency of aging degree and screen out some outliers. Specifically, a distance graph is used to determine the input parameters of the algorithm and the number of clusters in advance, which essentially improves the accuracy of clustering. 110 second-life batteries are divided into two clusters and outliers, and the clustering results show that the proposed method can significantly improve the aging consistency of second-life batteries. The standard deviations of capacity and polarization resistance are reduced by up to about two and five times compared with other algorithms.

关键词： Batteries clustering algorithms Resistance Aging Feature extraction Sorting Integrated circuits Second-life battery health feature battery sorting ordering points to identify the clustering structure

来源：评论

学校读者我要写书评

暂无评论

Delay-Constrained Client Selection for Heterogeneous Federated Learning in Intelligent Transportation Systems

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第1期11卷 1042-1054页

作者： Zhang, Weiwen Chen, Yanxi Jiang, Yifeng Liu, Jianqi Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China

Federated learning has been claimed as a solution in intelligent transportation systems, which allows for the implementation of distributed machine learning while ensuring privacy and data security. However, federated learning suffers from training inefficiency in practical deployment due to the heterogeneity of the participating clients. In this paper, we investigate how to optimize client selection to improve the training efficiency of traffic flow prediction, by considering the number of clients involved in training. We first formulate a constrained optimization problem on client selection, which aims to maximize the number of clients while meeting the training deadlines. We then transform the optimization problem into a two-dimensional unbounded knapsack problem (2UKP). Subsequently, we propose a K-means and Dynamic Programming (KDP) algorithm to solve the 2UKP. Specifically, we cluster the clients based on their computational capacity and geographic distance to the server by K-means and adopt dynamic programming to obtain the set of the selected clients. We evaluate the performance of the proposed KDP algorithm on Caltrans Performance Measurement System (PeMS) dataset and Highways England dataset. Comprehensive experimental results show that our proposed KDP algorithm can obtain up to 56% improvement in the number of clients within a given deadline compared to random and greedy strategies, achieving prediction accuracy of up to 20% improvement under the PeMS dataset and 15% improvement under the Highways England dataset. Moreover, the proposed KDP with 30% as the straggler ratio can still outperform the baseline FedGRU.

关键词： Training Federated learning Servers Computational modeling clustering algorithms Prediction algorithms Optimization Client selection dynamic programming federated learning heterogeneity intelligent transportation system

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：