检索结果-内蒙古大学图书馆

AoI-Minimal clustering, Transmission and Trajectory Co-Design for UAV-Assisted WPCNs

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第1期74卷 1035-1051页

作者： Liu, Xiaoying Liu, Huihui Zheng, Kechen Liu, Jia Taleb, Tarik Shiratori, Norio ZheJiang Univ Technol Sch Comp Sci & Technol Hangzhou 310014 Zhejiang Peoples R China Natl Inst Informat Ctr Strateg Cyber Resilience Res & Dev Tokyo 1018430 Japan Ruhr Univ Bochum Fac Elect Engn & Informat Technol D-44801 Bochum Germany Chuo Univ Res & Dev Initiat Tokyo 1128551 Japan

This paper investigates the long-term average age of information (AoI)-minimal problem in an unmanned aerial vehicle (UAV)-assisted wireless-powered communication network (WPCN), which consists of a static hybrid access point (HAP), a mobile UAV, and many static sensor nodes (SNs) randomly distributed on multiple islands. The UAV first is fully charged by the HAP, and then flies to each island to charge SNs and receive data from them. Before running out the energy in battery, the UAV flies back to the HAP to offload the received data and be fully charged again. Due to the finite battery capacity of the UAV, it is impossible for the UAV to traverse all the islands to collect all the data from SNs for once flight. We are thus inspired to divide islands into multiple clusters so that the UAV could traverse all the islands in each cluster, and formulate the long-term average AoI-minimal problem by jointly optimizing the transmit power of SNs, clustering of islands, and UAV's flight trajectory. To tackle the NP-hard problem, we decouple it into two subproblems: the power allocation subproblem for SNs, and the joint clustering of islands and UAV's flight trajectory design subproblem. To solve the first subproblem, we propose a hybrid TDMA and NOMA (HTN) protocol that takes advantage of the two protocols. To solve the second subproblem, we propose a clustering-based dynamic adjustment of the shortest path (C-DASP) algorithm. Simulations verify the effectiveness and superiority of the proposed HTN protocol and C-DASP algorithm.

关键词： Autonomous aerial vehicles Trajectory Heuristic algorithms Batteries clustering algorithms Protocols Optimization Unmanned aerial vehicle wireless powered communication networks age of information trajectory design

来源：评论

学校读者我要写书评

暂无评论

Enhancing Segmentation: A Comparative Study of clustering Methods

引用

IEEE ACCESS 2025年 13卷 47418-47439页

作者： Ling, Lew Sook Weiling, Claireta Tang Multimedia Univ Fac Informat Sci & Technol Melaka 75450 Malaysia

With the increasing complexity of consumer preferences and behaviors, businesses face challenges to capture the dynamic nature of online consumer behavior, highlighting the need for advanced approaches. This study aims to enhance customer segmentation in e-marketing by analyzing and comparing various machine learning-based clustering methods, with a particular focus on unsupervised clustering techniques for predicting Customer Lifetime Value (CLV). While prior research has utilized unsupervised clustering for customer segmentation, this current study uniquely integrates K-Means++ with other clustering techniques to enhance segmentation accuracy and gain deeper insights into consumer behavior. This study adopts a structured, unsupervised clustering approach, enabling natural customer groupings without predefined labels, which is particularly suitable for customer segmentation in scenarios with limited labeled data. Several clustering techniques are investigated, including K-Means, K-Medoids, Agglomerative clustering, DBSCAN, Fuzzy C-Means, K-Means++, Mini Batch K-Means, Mean Shift, and Gaussian Mixture Models (GMM). K-Means++ demonstrated superior performance in segmentation accuracy, outperforming other techniques under various conditions. Performance is evaluated using key metrics such as the Silhouette Score and Davies-Bouldin Index. Utilizing Kaggle datasets, the analysis follows a comprehensive preprocessing protocol comprising RFM (Recency, Frequency, Monetary) analysis, outlier removal, and data normalization to ensure data integrity and facilitate systematic identification of distinct consumer segments. This research highlights the potential and significance of machine learning in refining customer segmentation processes within e-marketing, ultimately aiding businesses in optimizing their marketing effectiveness and strategic planning. While focusing primarily on a limited selection of clustering methods, the study underscores the necessity for ongoing explor

关键词： Business clustering methods Companies Consumer behavior Accuracy Systematic literature review Image segmentation clustering algorithms Internet Indexes Customer segmentation clustering RFM K-Means plus plus K-Medoids CLV prediction

来源：评论

学校读者我要写书评

暂无评论

Novel Multiple Criteria Group Decision-Making Method Based on Hesitant Fuzzy clustering Algorithm

引用

IEEE ACCESS 2025年 13卷 15572-15584页

作者： Bian, Hongya Li, Deqing Liu, Yuang Ma, Rong Zeng, Wenyi Xu, Zeshui Xiamen Inst Technol Sch Data Sci & Intelligent Engn Xiamen 361021 Peoples R China Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China Sichuan Univ Business Sch Chengdu 610064 Peoples R China

The aim of this paper is to investigate the multiple criteria group decision-making problem in which the evaluation values provided by experts construct some hesitant fuzzy numbers. We first analyze the characteristics of hesitant fuzzy number (HFN) and define the concept of feature vector of HFN. Then, applying the feature vectors of HFNs, some new similarity measures of HFNs are presented, which do not need to add elements to the HFN with fewer elements in the calculation process. Therefore, fuzzy similarity matrix is constructed, which is used to obtain a fuzzy equivalent matrix by using transitive closure method. By applying the fuzzy equivalent matrix, a novel hesitant fuzzy clustering algorithm is given. Furthermore, a new multiple criteria group decision making (MCGDM) algorithm is developed on the basis of the hesitant fuzzy clustering algorithm and the idea of ideal solution in multiple criteria decision making theory. To illustrate the effectiveness and feasibility of the developed MCGDM method, a numerical example is given and analyzed in detail. The results illustrate that the proposed method can provide more reasonable and credible rankings comparing with existing methods owing to keeping original data during computation.

关键词： Fuzzy sets Vectors clustering algorithms Hafnium Fuzzy set theory Probabilistic logic Q measurement MCDM Linguistics Urban areas Hesitant fuzzy number feature vector of HFN hesitant fuzzy clustering algorithm multiple criteria group decision making

来源：评论

学校读者我要写书评

暂无评论

Nonconvex Low-Rank Tensor Representation for Multi-View Subspace clustering With Insufficient Observed Samples

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第6期37卷 3583-3597页

作者： Ding, Meng Yang, Jing-Hua Zhao, Xi-Le Zhang, Jie Ng, Michael K. Southwest Jiaotong Univ Sch Math Chengdu 611756 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Univ Elect Sci & Technol China Sch Math Sci Chengdu 611731 Peoples R China Univ Hong Kong Dept Math Hong Kong Peoples R China Hong Kong Baptist Univ Dept Math Hong Kong Peoples R China

Multi-view subspace clustering (MVSC) separates the data with multiple views into multiple clusters, and each cluster corresponds to one certain subspace. Existing tensor-based MVSC methods construct self-representation subspace coefficient matrices of all views as a tensor, and introduce the tensor nuclear norm (TNN) to capture the complementary information hidden in different views. The key assumption is that the data samples of each subspace must be sufficient for subspace representation. This work proposes a nonconvex latent transformed low-rank tensor representation framework for MVSC. To deal with the insufficient sample problem, we study the latent low-rank representation in the multi-view case to supplement underlying observed samples. Moreover, we propose to use data-driven transformed TNN (TTNN), resulting from the intrinsic structure of multi-view samples, to preserve the consensus and complementary information in the transformed domain. Meanwhile, the proposed unified nonconvex low-rank tensor representation framework can better learn the high correlation among different views. To resolve the proposed nonconvex optimization model, we propose an effective algorithm under the framework of the alternating direction method of multipliers and theoretically prove that the iteration sequences converge to the critical point. Experiments on various datasets showcase outstanding performance.

关键词： Tensors Correlation Transforms Electronic mail Sparse matrices clustering algorithms Training Symbols Reviews Optimization Multi-view subspace clustering insufficient data sampling nonconvex low-rank tensor representation transformed tensor nuclear norm convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive Non-Homogeneous Granulation-Aided Density-Based Deep Feature clustering for Far Infrared Sign Language Images

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第2期9卷 1269-1280页

作者： Paral, Pritam Ghosh, Saibal Pal, Sankar K. Chatterjee, Amitava IIEST Dept Elect Engn Sibpur 711103 Howrah India Jadavpur Univ Dept Elect Engn Kolkata 700032 India ISI Ctr Soft Comp Res Kolkata 700108 India

In image clustering applications, deep feature clustering has recently demonstrated impressive performance, which employs deep neural networks for feature learning that favors clustering exercises. In this context, density-based methods have emerged as the preferred choice for the clustering mechanism within the framework of deep feature clustering. However, as the performance of these clustering algorithms is primarily effective on the low-dimensional feature data, deep feature learning models play a crucial role here. With far infrared (FIR) thermal imaging systems working in real-world scenarios, the images captured are largely affected by blurred edges, background noise, thermal irregularities, few details, etc. In this work, we demonstrate the effectiveness of granular computing-based techniques in such scenarios, where the input data contains indiscernible image regions and vague boundary regions. We propose a novel adaptive non-homogeneous granulation (ANHG) technique here that can adaptively select the smallest possible size of granules within a purview of unequally-sized granulation, based on a segmentation assessment index. Proposed ANHG in combination with deep feature learning helps in extracting complex, indiscernible information from the image data and capturing the local intensity variation of the data. Experimental results show significant performance improvement of the density-based deep feature clustering method after the incorporation of the proposed granulation scheme.

关键词： Image segmentation Feature extraction Finite impulse response filters Cameras Sensors clustering algorithms Sign language Indexes Granular computing Temperature sensors Adaptive non-homogeneous granulation American sign language deep feature clustering density-based clustering far infrared thermal imaging granular computing

来源：评论

学校读者我要写书评

暂无评论

Graph Learning With Riemannian Optimization for Multi-View Integrative clustering

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 381-393页

作者： Khan, Aparajita Maji, Pradipta Indian Stat Inst Machine Intelligence Unit Kolkata 700108 India Indian Inst Technol Roorkee Dept Comp Sci & Engn Roorkee 247667 India Indian Stat Inst Machine Intelligence Unit Biomed Imaging & Bioinformat Lab Kolkata 700108 India

Real-world multi-view data may manifest as point-clouds, but their meaningful structure often resides on a lower dimensional manifold embedded in the higher dimensional space. Consequently, existing graph based multi-view algorithms focus primarily on extraction of the low-rank subspaces for clustering. However, simultaneous optimization of the individual graph structures, their contributions/weights along with the clustering subspaces is likely to give a more comprehensive idea of the clusters present in the data set. In this regard, the paper proposes a Riemannian manifold optimization algorithm that harnesses the geometry and structure preserving properties of symmetric positive definite (SPD) manifold and Grassmann manifold for efficient multi-view clustering. The SPD manifold is used to optimize the graph Laplacians corresponding to the individual views, while preserving their symmetricity, positive definiteness, and related properties. The Grassmann manifold, on the other hand, is used to minimize the disagreement between the joint and individual clustering subspaces. Optimization over the Grassmann manifold additionally enforces the clustering solutions to be basis invariant such that all cluster indicator matrices whose columns span the same subspace map to the same clustering solution. A gradient based line-search algorithm, which alternates between two different manifolds, is proposed to optimize the multi-view graph Laplacians and its associated subspaces. The matrix perturbation theory is used to theoretically bound the disagreement between the clustering subspaces. Extensive experiments on several multi-view benchmark and multi-omics cancer data sets establish the effectiveness of the proposed method. The proposed work demonstrates how incorporation of Riemannanian optimization into the graph learning framework can boost multi-view clustering performance.

关键词： Manifolds Optimization Laplace equations clustering algorithms Noise Geometry Perturbation methods Graph learning matrix perturbation theory multi-view clustering Riemannian optimization spectral clustering

来源：评论

学校读者我要写书评

暂无评论

Uncovering Passenger-Seeking Behavior of Vacant Taxis From Trajectory Data via Self-Supervised Deep Spectral clustering

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第4期26卷 5307-5321页

作者： Yu, Xinlian Hua, Mingzhuang Chen, Jingxu Peng, Jiankun Mao, Haijun Southeast Univ Sch Transportat Nanjing 210096 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Gen Aviat & Flight Nanjing 210095 Peoples R China

Knowledge of vacant taxis' passenger-searching behavior is of great social and economic interest to multiple applications, particularly in planning and operating on-demand mobility services. The inherent stochasticity and dynamic nature in both passenger demand and drivers' decision-making pose challenges in capturing vacant taxis movements. This study proposes a novel deep clustering framework to comprehensively uncover passenger-searching strategies from extensive trajectory data. Specifically, multiple features from vacant searching trips are extracted and analogously defined as multi-channel images, where each channel corresponds to a specific feature. A novel deep image clustering approach is then proposed, integrating a feature representation module utilizing convolutional neural networks (ConvNets), a self-expression module for affinity learning, a spectral clustering module, and a classification module for self-supervision. An effective training procedure is also presented for the proposed deep clustering framework. Experiments demonstrate the effectiveness of the proposed approach against benchmark methods. Based on the clustering results, common and specific passenger searching strategies are further revealed. Specifically, our findings highlight the importance of individual's contextual experience in explaining searching behavior and operational efficiency. Moreover, drivers cruising without clear searching strategy often exhibit lower performance, and some drivers may gamble with peers to increase their chances of picking up passengers. These results deliver important justifications for future studies and provide managerial implications to improve on-demand mobility.

关键词： Public transportation Trajectory Vehicles Logistic regression Heuristic algorithms Training Feature extraction clustering algorithms Vehicle dynamics Supervised learning Passenger-searching behavior trajectory clustering deep spectral clustering self-expression learning self-supervision

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Small-Target Detection in Sea Clutter: Spectral clustering Based on Neighborhood Density Similarity Measure

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 2988-2997页

作者： Zhang, Le Wang, Qingfei Guo, Yunfei Xu, Shuwen Wang, Lin Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China Yancheng Inst Technol Sch Elect Engn Yancheng 224051 Peoples R China

Small-target detection in sea clutter has always been difficult due to the low signal clutter ratio (SCR). Feature-based detection methods have emerged as a significant area of research in recent years, where pattern recognition methods involve the use of similarity measures. The Gaussian kernel function used in traditional spectral clustering algorithms performs well when handling nonlinear data, however, it may not effectively capture the relationships between sparsely distributed samples. Therefore, this article proposes a novel method for small-target detection in sea clutter: spectral clustering based on neighborhood density similarity measure (SC-ND) to address the aforementioned issues. It incorporates neighborhood density into the Gaussian kernel function and then uses label information to guide the construction of the similarity matrix, at which point a false alarm controllable is achieved. The similarity matrix is then spectrally decomposed to obtain a new representation of the samples, which are subsequently classified using an improved k-means algorithm. Validated on the IPIX 1993 radar dataset, the proposed method achieves a detection probability of 71.1% with an observation time of 1.024 s and a false alarm rate of 0.001. The results are better than fractal-based detector, tri-feature-based detector, and feature-based detector using three TF features.

关键词： Sea measurements Clutter Feature extraction Detectors clustering algorithms Object detection Kernel Databases Time-frequency analysis Radar clutter False alarm controllable label information neighborhood density small-target detection spectral clustering

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Vessel Trajectory clustering Based on Three-Dimensional Triangulation Division Algorithm

引用

IEEE ACCESS 2025年 13卷 51388-51405页

作者： Xu, Kai Wang, Rui Gao, Qikai Tan, Jingjing Shanghai Maritime Univ Shanghai Int Shipping Inst Shanghai 200082 Peoples R China Shanghai Maritime Univ Sch Sci Shanghai 201306 Peoples R China Daiyue Dist Transportat Bur Tai An 271000 Shandong Peoples R China Shanghai Jizhi Shipping Dev Co Ltd Shanghai 200082 Peoples R China

Automatic identification system (AIS) performs vital functions in vessel collision avoidance and maritime security. The large-scale vessel trajectory data recorded by AIS has been facilitating vessel trajectory pattern mining, of which vessel trajectory clustering is a fundamental and indispensable approach. The precise and efficient measurement of trajectory similarity serves as the cornerstone of large-scale trajectory clustering. Most ship trajectory similarity measurement algorithms have issues of high time complexity, poor robustness and inability to distinguish the trajectories in opposite directions. This paper presents an improved measurement named three-dimensional Triangulation Division (3TD), which is based on area division in three-dimensional space with time axis incorporated, to ameliorate those deficiencies. In addition, a novel vessel trajectory clustering method is proposed by combining the 3TD algorithm with DBSCAN algorithm. AIS trajectory data in Yangshan Port area has been used to make experimental dataset. Experimental results indicate that the improved method in this paper has superior performance compared with some other existing methods in terms of clustering accuracy, robustness and computational efficiencies.

关键词： Trajectory clustering algorithms Marine vehicles clustering methods Time measurement Time complexity Noise Artificial intelligence Heuristic algorithms Computational efficiency AIS area division DBSCAN trajectory similarity vessel trajectory clustering vessel trajectory pattern mining

来源：评论

学校读者我要写书评

暂无评论

Path-Based clustering Approaches for a Hybrid Slepian-Wolf Compression and Coded Caching System

引用

IEEE ACCESS 2025年 13卷 48935-48949页

作者： Rosen, Benjamin Abu-Mahfouz, Adnan M. Cheng, Ling Univ Witwatersrand Sch Elect & Informat Engn ZA-2000 Johannesburg South Africa CSIR ZA-0001 Pretoria South Africa

Combining caching with source coding, a hybrid content delivery system further facilitates the shift towards Information-Centric Networks. This is a promising technology heralded as the next phase in network design. However, finding the optimal balance between the source coding gains and the computational complexity is itself an NP-hard problem. By modelling the problem using a path-based approach, this paper outlines iterative algorithms that can be tuned to provide control over this trade-off. So too, a necessary condition of optimality is derived. This condition can be applied repeatedly to improve the performance of the results from the iterative algorithms. The Ant Colony Optimisation family of meta-heuristic algorithms is adapted to solve this problem, providing a benchmark that outperforms the Genetic Algorithm presented in prior work. The iterative algorithms have a larger time complexity than other solutions, but still converge in polynomial time. When combined with the optimality condition, they outperform all of the currently proposed algorithms that solve this problem to date. More specifically, this approach produces results that are found to fall in the 99.97th percentile on average.

关键词： Iterative methods Complexity theory Metaheuristics Entropy clustering algorithms Source coding Genetic algorithms Servers Scalability NP-hard problem Ant colony optimization clustering algorithms content distribution networks heuristic algorithms Information-Centric Networking information entropy information theory iterative algorithms mutual information source 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：