检索结果-内蒙古大学图书馆

A Hybrid Composite Differential Evolution and Multiobjective Particle Swarm Optimization Evolutionary Algorithm and Its Application

引用

IEEE ACCESS 2024年 12卷 74417-74431页

作者： Shang, Jin Li, Guiying Wuxi Inst Technol Control Technol Inst Wuxi 214121 Peoples R China Heilongjiang Univ Sch Mech & Elect Engn Harbin 150080 Peoples R China

The current multi-objective particle swarm algorithms excel in convergence speed for solving complex problems but often suffer from a loss of population diversity. Conversely, composite differential evolution algorithms maintain superior solution distribution but lag in convergence efficiency. This research introduces an improved hybrid algorithm, CoDE-MOPSO, which integrates multi-objective particle swarm optimization with composite differential evolution based on clustering technology. The clustering algorithm is used for all individual clusters to analyze the distribution constructs of populations, which determines whether the new solutions come from global or local populations at a mating restriction probability. The mating restriction probability is updated at each generation. To adapt the balance between the population solution diversities and the convergence speed of the algorithm, at each generation, the control probability is adjusted by a developed adaptive strategy according to the reproduction utility of the two mechanisms of generating new solutions over the last certain generations. This research introduces the CoDE-MOPSO algorithm, designed to transcend existing multi-objective optimization methods' limitations by optimally balancing exploration and exploitation. Our approach significantly advances evolutionary multi-objective optimization, demonstrating superior performance through lower Inverse Generational Distance and higher Hypervolume metrics, indicating enhanced efficiency in solving complex MOPs across various fields. In practical scenarios like gear reducer optimization, CoDE-MOPSO showcases remarkable effectiveness, highlighting its value in engineering applications and setting a foundation for sophisticated optimization strategies that combine speed with solution quality.

关键词： Statistics Social factors Optimization Convergence clustering algorithms Particle swarm optimization Interconnected systems Pareto optimization clustering algorithm composite differential evolution gear reducer multiobjective optimization particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Rationalizing Architectural Surfaces Based on clustering of Joints

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2022年第12期28卷 4274-4288页

作者： Xiong, Weidan Cheung, Chong Mo Sander, Pedro, V Joneja, Ajay Nanyang Technol Univ Singapore 639798 Singapore Hong Kong Univ Sci & Technol Hong Kong Peoples R China

We introduce the problem of clustering the set of vertices in a given 3D mesh. The problem is motivated by the need for value engineering in architectural projects. We first derive a max-norm based metric to estimate the geometric disparity between a given pair of vertices, and characterize the problem in terms of this measure. We show that this distance can be computed by using Sequential Quadratic Programming (SQP). Next we introduce two different algorithms for clustering the set of vertices on a given mesh, respectively based on two disparity measurements: max-norm and L2-norm based metric. An equivalence is established between mesh vertices and physical joints in an architectural mesh. By replacing individual joints by their equivalent cluster representative, the number of unique joints in the facade mesh, and therefore the fabrication cost, is dramatically reduced. Finally, we present an algorithm for remeshing a given surface in order to further reduce the number of joint clusters. The framework is tested for a set of real-world architectural surfaces to illustrate the effectiveness and utility of our approach. Overall, this approach tackles the important problem reducing fabrication cost of joints without modifying the underlying connectivity that was specified by the architect.

关键词： Faces Shape clustering algorithms Geometry Measurement Steel Indexing Joints discrete equivalence joint classes conformal geometry architectural geometry

来源：评论

学校读者我要写书评

暂无评论

Improved Harris Combined With clustering Algorithm for Data Traffic Classification

引用

IEEE ACCESS 2022年 10卷 72815-72824页

作者： Liu, Qingli Li, Mengqian Cao, Na Zhang, Zhenya Yang, Guoqiang Dalian Univ Commun & Network Lab Dalian 116622 Peoples R China

Aiming at the problem that the data traffic in the intelligent wireless communication system presents complex characteristics such as burstiness and self-similarity, which leads to the low classification accuracy of the existing classification model for traffic, a data traffic classification method based on improved Harris Eagle algorithm combined with fuzzy C-means clustering is proposed. The method maps traffic samples to Harris Eagle individuals, finds the optimal position through multiple iterations of the algorithm, and uses this as the initial center point of the clustering algorithm to guide data traffic classification. The simulation shows that, compared with the traditional fuzzy clustering method, the clustering method based on the particle swarm algorithm and the gray wolf algorithm, the improved Harris Eagle combined with fuzzy clustering has better intra-class compactness and inter-class separation on the data traffic sample set. Meanwhile, the clustering accuracy and recall rate are both improved to about 90 percent.

关键词： clustering algorithms Classification algorithms Optimization Statistics Sociology Search problems Rabbits Data traffic classification fuzzy clustering Harris Hawk optimization degree of compactness within a class degree of separation between classes

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Individual Tree Segmentation in Complex Urban Scenes Based on Using Multispectral LiDAR by Deep Learning

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 6561-6576页

作者： Yang, Jian Gan, Ruilin Luo, Binhan Wang, Ao Shi, Shuo Du, Lin China Univ Geosci Sch Geog & Informat Engn Wuhan 430074 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430079 Peoples R China

Urban trees, as a characteristic element of the urban ecosystem, exert significant influences on climate supervision. Therefore, the extraction of individual trees in urban areas holds significant research value. However, the complexity of features in urban areas poses challenges to existing single tree segmentation algorithms, as they may be influenced by other nontree features. In this study, to reduce the influence of nontree categories, enhance the identification of edge features between adjacent tree crowns, and achieve precise delineation results of the single urban tree, an improved multistage method was proposed for tree points extraction and individual tree segmentation in urban scenes using multispectral LiDAR. First, the original three single-channel point clouds were preprocessed by intensity interpolation to generate a three-wavelength multispectral point cloud. Second, the Point Transformer deep learning network was employed for extracting urban tree points. Third, an improved tree mapping algorithm was introduced for individual tree segmentation in urban scenes, utilizing the extracted tree points. Finally, manual individual tree labeling and the high-resolution digital orthophoto map of the region were incorporated to measure the delineation precision of individual trees. It shows that the intersection over union of tree category in urban scene reaches 96.0%. Moreover, the F1-score for overall individual tree segmentation attains 92.8%. However, a comparison with existing algorithms reveals that the proposed method outperforms the traditional raster-based watershed method or point cloud clustering-based layer-stacking approach in the urban scene, improving the overall accuracy of single tree segmentation by 21.9% and 16.0%, respectively. These results highlight the enhanced applicability of the proposed multistage algorithm for urban scenes.

关键词： Vegetation Point cloud compression Laser radar Feature extraction Data mining Deep learning clustering algorithms Individual tree crown (ITC) segmentation multispectral LiDAR point cloud deep learning tree points extraction urban scene

来源：评论

学校读者我要写书评

暂无评论

CHEF: A Framework for Deploying Heterogeneous Models on Clusters With Heterogeneous FPGAs

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2024年第11期43卷 3937-3948页

作者： Tang, Yue Song, Yukai Elango, Naveena Priya, Sheena Ratnam Jones, Alex K. Xiong, Jinjun Zhou, Peipei Hu, Jingtong Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15261 USA Univ Buffalo Dept Comp Sci & Engn Buffalo NY 14260 USA Syracuse Univ Dept Elect Engn Syracuse NY 13244 USA Syracuse Univ Comp Sci Dept Syracuse NY 13244 USA Brown Univ Sch Engn Providence RI 02912 USA

Deep neural networks (DNNs) are rapidly evolving from streamlined single-modality single-task (SMST) to multimodality multitask (MMMT) with large variations for different layers and complex data dependencies among layers. To support such models, hardware systems also evolved to be heterogeneous. The heterogeneous system comes from the prevailing trend to integrate diverse accelerators into the system for lower latency. FPGAs have high-computation density and communication bandwidth and are configurable to be deployed with different designs of accelerators, which are widely used for various machine-learning applications. However, scaling from SMST to MMMT on heterogeneous FPGAs is challenging since MMMT has much larger layer variations, a massive number of layers, and complex data dependency among different backbones. Previous mapping algorithms are either inefficient or over-simplified which makes them impractical in general scenarios. In this work, we propose CHEF to enable efficient implementation of MMMT models in realistic heterogeneous FPGA clusters, i.e., deploying heterogeneous accelerators on heterogeneous FPGAs (A2F) and mapping the heterogeneous DNNs on the deployed heterogeneous accelerators (M2A). We propose CHEF-A2F, a two-stage accelerators-to-FPGAs deployment approach to co-optimize hardware deployment and accelerator mapping. In addition, we propose CHEF-M2A, which can support general and practical cases compared to previous mapping algorithms. To the best of our knowledge, this is the first attempt to implement MMMT models in real heterogeneous FPGA clusters. Experimental results show that the latency obtained with CHEF is near-optimal while the search time is 10 $000\times $ less than exhaustively searching the optimal solution.

关键词： Design automation Computational modeling clustering algorithms Machine learning Bandwidth Benchmark testing Market research Hardware Integrated circuit modeling Field programmable gate arrays Heterogeneous FPGA clusters multimodality multitask (MMMT)

来源：评论

学校读者我要写书评

暂无评论

Metricizing the Euclidean Space Toward Desired Distance Relations in Point Clouds

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 7304-7319页

作者： Rass, Stefan Konig, Sandra Ahmad, Shahzad Goman, Maksim Johannes Kepler Univ Linz LIT Secure & Correct Syst Lab A-4040 Linz Austria Alpen Adria Univ Klagenfurt Inst Artificial Intelligence & Cybersecur A-9020 Klagenfurt Austria Res Driven Solut Ltd Dublin D08 TX29 Ireland

We introduce the concept of an epsilon-semimetric that satisfies the same axioms as a topological metric, except for an arbitrarily small allowance to violate the triangle inequality. Under this modification, we demonstrate the possibility of taking arbitrary points in space, assigning arbitrary desired distances between them (independent of their geometric location relative to each other, that is, independent of their "features"), and constructing an epsilon-semimetric that measures exactly the desired distances in the point cloud. This results in a threat to fairness and objectiveness in applications of clustering algorithms: suppose that an adversary subjectively classifies people according to its whim or discriminatory preferences. Upon accusations of unethical behavior, the malicious data processor can plausibly deny these as follows: it designs a distance function (an epsilon-semimetric) that is (up to a fully controllable numeric "round-off-error" epsilon) equivalent to a standard distance like the Euclidean. However, this crafted distance will exactly reproduce the (malicious) results and thus confirm them while pretending objectivity and transparency, since only standard and explainable artificial intelligence was used. This demonstration works without any data poisoning. We illustrate the method on randomly chosen points with stochastically independent random classifications assigned to them. Then, we apply standard implementations of k-Means and DBSCAN on the data points, which both exactly reproduce the desired (randomly chosen) classes. We also discuss non-adversarial applications of epsilon-semimetrics, and corroborate the construction with examples and implementation in Octave.

关键词： Measurement clustering algorithms Noise Standards Classification algorithms Training Euclidean distance Adversarial machine learning trust management non-repudiation security artificial intelligence (AI) data integrity

来源：评论

学校读者我要写书评

暂无评论

Client Selection in Hierarchical Federated Learning

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第17期11卷 28480-28495页

作者： Trindade, Silvana da Fonseca, Nelson L. S. Univ Estadual Campinas Inst Comp BR-13083970 Campinas Brazil

Federated learning (FL) is a promising technique for providing distributed learning without clients disclosing their private data. In hierarchical FL (HFL), edge servers partially aggregate the parameters of their connected clients' models, improving scalability and reducing computational overhead on the central server. To speed up the convergence of the global model, only those clients with potential contributions to the model performance will participate in the model training. This article introduces a two-step client selection approach for the HFL and three novel algorithms, which consider a large set of features in this selection and the client's contributions to the model performance. Compared to the selected baseline algorithms, the proposed client selection algorithms reduce CPU utilization by more than 50%, memory usage by 80%, and energy consumption by 50%.

关键词： Servers Convergence Performance evaluation Training Computational modeling clustering algorithms Federated learning Client selection edge computing federated learning (FL) hierarchical architecture

来源：评论

学校读者我要写书评

暂无评论

Design of Clustered Phased Arrays by Means of an Innovative Power Pattern Matching-Driven Method-The Linear Array Case

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2024年第5期72卷 4185-4197页

作者： Benoni, Arianna Poli, Lorenzo Rocca, Paolo Massa, Andrea Univ Trento ELEDIA Res Ctr Dept Civil Environm & Mech Engn DICAM ELEDIA UniTN I-38123 Trento Italy Univ Trento CNIT Res Unit I-38123 Trento Italy Xidian Univ ELEDIA Res Ctr ELEDIA XIDIAN Xian 710071 Shaanxi Peoples R China Univ Elect Sci & Technol China ELEDIA Res Ctr Sch Elect Sci & Engn ELEDIA UESTC UESTC Chengdu 611731 Peoples R China Tsinghua Univ ELEDIA Res Ctr ELEDIA TSINGHUA Beijing 100084 Peoples R China Tel Aviv Univ Sch Elect Engn IL-69978 Tel Aviv Israel

The design of subarrayed phased arrays (PAs) with subarray-only amplitude and phase controls that afford arbitrary-shaped power patterns matching reference ones is addressed. Such a synthesis problem is formulated in the power pattern domain, and an innovative complex-excitations clustering method, which is based on the decomposition of the reference power pattern in a number of elementary patterns equal to the array elements, is presented. A set of representative results is reported to illustrate the features of the proposed approach as well as to assess its effectiveness in comparison with benchmark results from the state-of-the-art (SoA) excitation matching (EM)-based clustering methods.

关键词： Phased arrays Pattern matching Linear antenna arrays clustering algorithms Europe Design methodology Transmission line measurements clustered array iterative projection method (IPM) k-means algorithm linear array phased array (PA) power pattern matching (PM)

来源：评论

学校读者我要写书评

暂无评论

User Behavior Analysis Based on Stacked Autoencoder and clustering in Complex Power Grid Environment

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第12期23卷 25521-25535页

作者： Deng, Song Cai, Qingyuan Zhang, Zi Wu, Xindong Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing 210003 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210003 Peoples R China Guilin Univ Elect Technol Sch Comp Sci & Informat Secur Guilin 541004 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Hefei 230009 Peoples R China Mininglamp Technol Mininglamp Acad Sci Shanghai 200232 Peoples R China

Analyzing user behavior characteristics in a complex power grid environment is essential for user behavior planning and resource coordination optimization. Traditional user behavior analysis methods based on model-driven and causal analysis have the disadvantages of strong subjectivity and physical models that are difficult to deal with the randomness and uncertainty of user behavior in complex grid environments. In this paper, we use unsupervised learning methods to analyze user behavior in complex power grid environments, and propose user behavior analysis methods based on stacked autoencoder and clustering. We first reduce the complexity of user behavior data by proposing adaptive feature selection algorithm of user behavior based on stacked autoencoder and unsupervised learning (AFS-SAEUL). Finally, we build a user behavior analysis model based on adaptive feature selection and improved clustering (UBA-AFSIC). The model improved the performance of unsupervised classification of user behavior by fusing the adaptive generation strategy of the initial cluster centers. The simulation experiment results on two real electricity datasets and one public electric vehicle charging dataset show that compared with the existing feature selection algorithm and clustering algorithm, the algorithms proposed in this paper have higher feature selection rate and better clustering performance.

关键词： Feature extraction clustering algorithms Analytical models Power demand Correlation Power grids Load modeling Feature selection stacked autoencoder unsupervised learning power consumption behavior analysis electric vehicle charging behavior analysis

来源：评论

学校读者我要写书评

暂无评论

Predefined-Time Bipartite Time-Varying Formation Tracking Control of Networked Autonomous Surface Vehicles via Hierarchical Control Approach

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第7期73卷 9536-9545页

作者： Pan, Jiao Han, Tao Xiao, Bo Yan, Huaicheng Hubei Normal Univ Sch Elect Engn & Automat Huangshi 435002 Hubei Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

As increasingly prevalent technologies in autonomous driving, autonomous surface vehicles (ASVs) have been widely applied to accomplish different practical tasks. However, there exist a few researches that have considered both the case of cooperative and antagonistic relationships between vehicles. Therefore, we aim to develop an effective approach to tackle the predefined-time bipartite time-varying formation tracking (BTVFT) problem of networked ASVs subject to external disturbances in this article. Firstly, the predefined-time hierarchical control (PTHC) algorithm is proposed to address the aforesaid issue. More specifically, by utilizing directed signed graph, the ASVs are divided into two subgroups to form their own time-varying formation configurations on both sides of the dynamic leader and keep the same distances from the leader. More notably, the convergence time can be designed in advance according to actual demands. Then, the corresponding sufficient conditions for achieving the predefined-time BTVFT are obtained by systematic analysis and Lyapunov stability analysis. Eventually, numerical simulation experiments on Cyber-Ships II are carried out, which vividly reflect the effectiveness and feasibility of the developed control algorithm.

关键词： Formation control Convergence Protocols Sea surface clustering algorithms Vehicle dynamics Systematics Bipartite time-varying formation tracking (BTVFT) networked autonomous surface vehicles (ASVs) predefined-time hierarchical control (PTHC)

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：