检索结果-内蒙古大学图书馆

FWCEC: An Enhanced Feature Weighting Method via Causal Effect for clustering

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第2期37卷 685-697页

作者： Cao, Fuyuan Jing, Xuechun Yu, Kui Liang, Jiye Shanxi Univ Sch Comp & Informat Technol Key Lab Computat Intelligence & Chinese Informat P Minist Educ Taiyuan 030006 Shanxi Peoples R China Hefei Univ Technol Sch Comp & Informat Hefei 230009 Peoples R China

Feature weighting aims to assign different weights to features based on their importance in machine learning tasks. In clustering tasks, the existing methods learn feature importance based on the clustering results derived from the collaborative contribution of all features, which overlooks the independent effect of each feature. In fact, there are underlying causal relationships between features and the clustering results, and the features with high causal effects are always more crucial for clustering. Therefore, we propose an enhanced Feature Weighting method via Causal Effect for clustering, calculating the causal effect of each feature on the clustering results for obtaining the independent contribution of each feature. Specifically, we start by identifying the causal relationships among the features and utilizing the causal relationships to generate a reasonable treatment group. Next, we compare the changes in the data distribution between the treatment and control groups to determine the causal effect of each feature. Finally, the causal effects of features are used for enhancing the clustering-driven weight learning. Moreover, we present a theory of relative order consistency in causal effect. Experimental results demonstrate that utilizing causal effect in weight learning facilitates efficient convergence and achieves superior accuracy compared to state-of-the-art clustering algorithms.

关键词： clustering algorithms Machine learning algorithms Machine learning Partitioning algorithms Noise measurement Collaboration Linear programming Convergence Technological innovation Reviews Feature weights clustering causal effect feature importance

来源：评论

学校读者我要写书评

暂无评论

-Graph: A Graph Embedding for Interpretable Time Series clustering

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第5期37卷 2680-2694页

作者： Boniol, Paul Tiano, Donato Bonifati, Angela Palpanas, Themis Inria PSL CNRS ENS F-75005 Paris France Univ Modena I-42121 Modena Italy Lyon 1 Univ IUF LIRIS CNRS Villeurbanne F-69622 Villeurbanne France Univ Paris Cite IUF F-75006 Paris France

Time series clustering poses a significant challenge with diverse applications across domains. A prominent drawback of existing solutions lies in their limited interpretability, often confined to presenting users with centroids. In addressing this gap, our work presents k-Graph, an unsupervised method explicitly crafted to augment interpretability in time series clustering. Leveraging a graph representation of time series subsequences, k-Graph constructs multiple graph representations based on different subsequence lengths. This feature accommodates variable-length time series without requiring users to predetermine subsequence lengths. Our experimental results reveal that k-Graph outperforms current state-of-the-art time series clustering algorithms in accuracy, while providing users with meaningful explanations and interpretations of the clustering outcomes.

关键词： Time series analysis Feature extraction clustering algorithms Accuracy Heuristic algorithms clustering methods Training Shape Partitioning algorithms Directed graphs Time series clustering interpretability

来源：评论

学校读者我要写书评

暂无评论

CNCMSA-ERCP: An Innovative Energy-Efficient clustering Routing Protocol for Improving the Performance of Industrial IoT

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第9期12卷 11827-11840页

作者： Liu, Xin Cao, Qike Jin, Bo Zhou, Peng Beijing Univ Technol Beijing 100124 Peoples R China Henan Inst Sci & Technol Xinxiang 453003 Henan Peoples R China Univ Coimbra Inst Syst & Robot Dept Elect & Comp Engn P-3030290 Coimbra Portugal Portuguese Natl Acad Sci P-1600477 Lisbon Portugal Xinjiang Coll Sci & Technol Sch Informat Sci & Engn Korla 841000 Xinjiang Peoples R China Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Peoples R China

As Industry 4.0 rapidly advances, optimizing energy and performance in industrial wireless sensor networks (IWSNs) for the Industrial Internet of Things (IIoT) is critical. Addressing the NP-hard challenge of IWSN clustering, this article introduces a novel multiobjective model to balance energy consumption and enhance service quality. Based on this model, a new energy-saving cluster routing protocol called CNCMSA-ECRP was designed. The protocol comprehensively considers four key indicators: 1) total residual energy;2) average network delay;3) average network packet loss rate;and 4) average distance from cluster heads (CHs) to the base station (BS), with the goal of achieving overall optimization of network performance. The CNCMSA-ECRP protocol employs our newly proposed chaotic niching clone moth swarm algorithm (CNCMSA). The algorithm introduces chaotic mapping operators in the initialization phase and clonal and niching operators in the evolution phase, enhancing the search capability and diversity of the algorithm, as well as improving clustering efficiency and network stability. Comparative experiments with four existing advanced clustering schemes-LEACH-C, EEHCHR, OptGACHE, and ESCVAD-demonstrate that CNCMSA-ECRP achieves at least a 16.38% increase in network lifespan and significantly reduces average data transmission delay and packet loss rate by at least 1.84% and 17.76%, respectively. This research provides a novel solution to the clustering routing problem in IWSN.

关键词： clustering algorithms Wireless sensor networks Industrial Internet of Things Quality of service Optimization Energy efficiency Routing Routing protocols Energy consumption Delays Chaotic niching clone cluster routing protocol industrial wireless sensor network (IWSN) moth swarm algorithm Quality of Service (QoS)

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Hybrid Adaptive clustering for Dynamic MANETs

引用

IEEE ACCESS 2025年 13卷 51319-51331页

作者： Yilmaz, Kudret Kara, Resul Katircioglu, Ferzan Duzce Univ Duzce Vocat Sch Dept Comp Technol TR-81620 Duzce Turkiye Duzce Univ Dept Comp Engn TR-81620 Duzce Turkiye Duzce Univ Dept Mechatron Engn TR-81620 Duzce Turkiye

Mobile ad hoc network (MANET) is a wireless, mobile node network in which the nodes move randomly and operate without centralized management. In MANETs, the network structure increases the energy consumption of the nodes, which shortens the network lifetime and affects packet transmission. The process of clustering in MANETs (Mobile Ad-hoc Network) can be achieved through the division of the network into virtual groups, known as clusters. The Cluster Head (CH) of each cluster is in charge of data transmission within the cluster. In this study, a two-stage Hybrid Adaptive clustering Algorithm for Dynamics MANETs (HACADM) is proposed to improve the network performance in MANETs. In the first stage, based on the Weighted clustering Algorithm (WCA) for selecting optimal CHs, criteria such as node degree, neighborhood distance, power of battery and mobility are optimized using the Gravity Search Algorithm (GSA). In the second phase, the clustering is executed by identifying the member nodes and their roles of the selected CHs using the Enhanced Density Based Spatial clustering of Applications with Noise (Enhanced-DBSCAN) algorithm, which is one of the unsupervised learning methods. Moreover, this approach serves to reduce the load on the CHs and enhance the stability of the cluster by selecting gateway nodes for inter-cluster communication. This study represents a significant step towards optimizing energy efficiency and extending network lifetime by enhancing the adaptability of clustering processes in MANETs under dynamic network conditions. The proposed HACADM method has the potential to enhance the performance of MANETs by ensuring a more balanced load distribution compared to existing clustering approaches. The HACADM method was compared with the EE-WCA, E-MAVMMF, TSDR and MORS-ASO methods using critical performance metrics such as remaining energy, end-to-end delay, packet delivery ratio and throughput. For example, experimental results on remaining energy show tha

关键词： Ad hoc networks Mobile computing clustering algorithms Energy efficiency Energy consumption Routing Heuristic algorithms Routing protocols Mobile nodes Particle swarm optimization Adaptive clustering energy efficiency gravitational search algorithm machine learning MANET

来源：评论

学校读者我要写书评

暂无评论

Dual Completion Learning for Incomplete Multi-View clustering

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 455-467页

作者： Shen, Qiangqiang Zhang, Xuanqi Wang, Shuqin Li, Yuanman Liang, Yongsheng Chen, Yongyong Harbin Inst Technol Shenzhen Sch Elect & Informat Engn Shenzhen 518055 Guangdong Peoples R China Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON K1N 6N5 Canada Shandong Univ Aeronaut Coll Sci Binzhou 256600 Peoples R China Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Harbin Inst Technol Shenzhen Sch Comp Sci & Technol Shenzhen 518055 Guangdong Peoples R China

Incomplete Multi-View clustering (IMVC) offers a way to analyze incomplete data, facilitating the inference of unobserved and missing data points through completion techniques. However, existing IMVC methods, predominantly depending on either data completion or similarity matrix completion, failed to uncover the inherent geometric structure and potential complementary information between intra- and inter-views, causing incomplete similarity matrices to further tear apart the connections between views. To address this problem, we propose Dual Completion Learning for Incomplete Multi-view clustering (DCIMC), which elaborately designs data completion and similarity tensor completion, and fuses both of them into a unified model to effectively recover the missing samples and similarities. Concretely, in data completion, DCIMC utilizes subspace clustering to recover the missing and unknown instances directly. Meanwhile, in similarity tensor completion, DCIMC introduces the idea of tensor completion to make better use of the high-order complementary information from multi-view data. By fusing the dual completions, missing information and complementary information in each completion are fully explored by each other, reciprocally enhancing one another to boost the accuracy of our clustering algorithm. Experimental results on various datasets show the effectiveness of the proposed DCIMC. Moreover, our DCIMC also achieved superior or comparable performance in an extended comparison with recent deep learning-based multi-view clustering algorithms.

关键词： Tensors clustering algorithms Laplace equations Matrix decomposition Learning systems Matrix converters Kernel Incomplete multi-view clustering subspace clustering data completion tensor completion

来源：评论

学校读者我要写书评

暂无评论

Adaptive clustering Hierarchical PBFT Algorithm for Secure and Efficient Blockchain-Based IoT Edge Computing

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3252-3266页

作者： Zheng, Jiali Xie, Jincheng Su, Yanting Guangxi Univ Sch Comp Elect & Informat Guangxi Key Lab Multimedia Commun & Network Techno Nanning 530004 Guangxi Peoples R China

With the rapid development of the Internet of Things (IoT), the importance of data transmission security and efficiency has become increasingly significant. Traditional consensus mechanisms, particularly, the practical Byzantine fault-tolerance (PBFT) algorithm, face notable challenges in the context of blockchain-based edge computing due to scalability issues. Specifically, as the number of nodes increases, PBFT experiences high communication complexity, which leads to significant performance degradation. To tackle this challenge, this article proposes a novel consensus algorithm named adaptive clustering hierarchical-PBFT (ACH-PBFT) that employs a hierarchical cluster structure and node fault-tolerance check to enhance the security and efficiency of blockchain-based edge computing in the IoT. ACH-PBFT adaptively selects an appropriate primary node and forms multiple subnode clusters, facilitating a more scalable consensus process. The system reduces the probability of malicious nodes becoming primary nodes through mutual verification between the primary node cluster and the subcluster consensus. Experimental results indicate that the ACH-PBFT algorithm achieves a 19.83% increase in execution speed, a 23.67% improvement in throughput, and an average reduction of 23.05% in communication overhead compared with a similar double-layer PBFT algorithm lacking hierarchical clustering. In the experiments testing against malicious nodes, the ACH-PBFT algorithm exhibited an average increase of 24.73% in the probability of successfully achieving consensus. Overall, this research provides a practical and effective solution for implementing secure and efficient blockchain-based IoT edge computing using a multilayer architecture to achieve flexible deployment and efficient resource utilization in edge computing environments.

关键词： Blockchains Internet of Things clustering algorithms Edge computing Security Scalability Fault tolerant systems Fault tolerance Consensus protocol Heuristic algorithms Blockchain consensus algorithm Internet-of-Things (IoT) edge computing multilayer architecture practical Byzantine fault tolerance (PBFT)

来源：评论

学校读者我要写书评

暂无评论

Dual-Structural Bipartite Graph Learning for Multiview clustering

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年 PP卷 PP页

作者： Wei, Xiaohui Liu, Haibo Duan, Puhong Li, Shutao Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China Hunan Univ Coll Robot Changsha 410082 Peoples R China Coll Elect & Informat Engn Changsha 410082 Peoples R China

Bipartite graph (BiG) has been proven to be efficient in handling massive multiview data for clustering. However, how to regulate the structural information of view-specific anchors and view-shared BiG is still open and needs to be further studied. Hence, a novel dual-structural BiG learning (DsBiGL) method is proposed in the article. It transforms BiG learning into a joint optimization problem of IntrA-view and InteR-view subspace learning (IASL and IRSL) with the structural constraints, such as k-nearest neighbor (KNN) and low-rank. On one hand, IASL uses the KNN and view-specific low-rank constraints to enhance the discriminativeness of view-specific anchors. On the other hand, IRSL uses an adaptive weighting strategy to obtain view-shared BiG directly from multiview samples, where the KNN and view-shared low-rank constraints are adopted to encode local connectivity and cluster information between samples. Note that IASL and IRSL are integrated into a unified optimization model, which ensures the interactive enhancement of view-specific anchor representation and view-shared BiG learning. Finally, an algorithm based on iterative optimization is designed to solve the proposed DsBiGL model. Experimental results on various multiview datasets have demonstrated the superiority of DsBiGL in terms of clustering results when compared with other comparative methods.

关键词： Nearest neighbor methods Optimization Noise Learning systems Bipartite graph Accuracy Vectors clustering algorithms Iterative algorithms Electronic mail Bipartite graph (BiG) learning k-nearest neighbor (KNN) constraint low-rank constraint multiview clustering (MVC) subspace learning

来源：评论

学校读者我要写书评

暂无评论

Simple One-Step Multi-View clustering With Fast Similarity and Cluster Structure Learning

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1850-1854页

作者： Xia, Xianxian Huang, Dong Yang, Chen-Min He, Chaobo Wang, Chang-Dong South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China South China Normal Univ Sch Comp Sci Guangzhou 510635 Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Key Lab Big Data Anal & Proc Guangzhou 510006 Peoples R China

Multi-view clustering (MVC) is essential for integrating heterogeneous data from multiple sources. However, many existing approaches are hindered by high computational complexity and the separate optimization of similarity and cluster structures. In light of these challenges, this paper presents a novel anchor-based MVC method termed simple one-step multi-view clustering with fast similarity and cluster structure learning (SONIC), which models adaptive anchor learning, multi-view similarity structure learning, and discrete cluster structure learning in a joint framework. In particular, we employ the anchor-based multi-view similarity learning to capture the consensus manifold structure latent in multiple views, thereby constructing a unified bipartite graph with adaptive anchor learning and view weighting. Then we impose a low-rank constraint on the bipartite graph structure to directly reveal the desired number of clusters without additional post-processing. An efficient alternating minimization algorithm is developed to optimize the model, resulting in a computational complexity that scales linearly with the number of samples. Extensive experiments on eight benchmark datasets demonstrate the superior performance of SONIC in both clustering quality and computational efficiency.

关键词： Optimization Bipartite graph Similarity learning Linear programming Adaptation models Vectors Signal processing algorithms Laplace equations clustering algorithms Training Consensus information data clustering lare-scale clustering linear time multi-view clustering

来源：评论

学校读者我要写书评

暂无评论

Expectation Distance-Based Distributional clustering for Noise-Robustness

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第11期36卷 6099-6110页

作者： Adesunkanmi, Rahmat Kumar, Ratnesh Iowa State Univ Dept Elect & Comp Engn Ames IA 50011 USA

This paper presents a clustering technique that reduces the susceptibility to data noise by learning and clustering the data-distribution and then assigning the data to the cluster of its distribution. In the process, it reduces the impact of noise on clustering results. This method involves introducing a new distance among distributions, namely the expectation distance (denoted, ED), that goes beyond the state-of-art distribution distance of optimal mass transport, also called 2-Wasserstein (denoted, W-2): The latter essentially depends only on the marginal distributions while the former also employs the information about the joint distributions, making it more powerful. Using the ED, the paper extends the classical K-means and K-medoids clustering to those over data-distributions (rather than raw-data) and further introduces K-medoids using W-2. The paper also presents the closed-form expressions of the W-2 and ED distance measures. The implementation results of the proposed ED and the W-2 distance measures to cluster real-world weather data as well as stock data are also presented, which involves efficiently extracting and using the underlying data distributions-Gaussians for weather data versus lognormals for stock data. The results show striking performance improvement over classical clustering of raw-data, with higher accuracy realized for ED. Also, not only does the distribution-based clustering offer higher accuracy, but it also lowers the computation time due to reduced time-complexity.

关键词： Meteorology Temperature distribution Costs Precipitation Noise clustering algorithms Noise measurement expectation distance Wasserstein distance uncertain data

来源：评论

学校读者我要写书评

暂无评论

Energy-Distance-Function-Based Improved K-Means for clustering Routing Algorithm

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第22期11卷 36763-36774页

作者： Zhou, Lin Zhang, Meng Wei, Qian Jin, Yong Wang, Saidi Yan, Jiayuan Henan Univ Sch Artificial Intelligence Zhengzhou 450046 Peoples R China

In wireless sensor networks (WSNs), conventional clustering routing algorithms often lead to uneven distribution of cluster heads (CHs), resulting in imbalanced and high-energy consumption. Addressing these challenges, this study introduces a novel algorithm, termed the energy distance function-based improved K-means algorithm (EDFIKM). This algorithm synthesizes the principles of the low-energy adaptive clustering hierarchy (LEACH) with the K-means clustering methodology. Key to this approach is the formulation of an adaptive weighted energy distance function that accounts for nodes' residual energy, their proximity to cluster centers, and dynamic weights for energy and distance factors. This function strategically mitigates the randomness in CH selection. Incorporating this function into the K-means clustering process achieves a more uniform distribution of CHs and an equitable allocation of nodes across clusters. Importantly, this contributes to a balanced energy load and a reduction in overall network energy consumption. Simulation studies validate that the EDFIKM algorithm efficiently lowers network energy demands and extends the network lifespan, without adding to the time complexity.

关键词： clustering algorithms Energy consumption Wireless sensor networks Adaptation models Routing Internet of Things Energy efficiency Cluster head (CH) selection energy consumption energy distance function K-means clustering wireless sensor network (WSN)

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：