检索结果-内蒙古大学图书馆

clustering-Driven State Embedding for Reinforcement Learning Under Visual Distractions

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2024年第12期54卷 7382-7395页

作者： Wang, Rongrong Cheng, Yuhu Wang, Xuesong Univ Min & Technol Minist Educ Engn Res Ctr Intelligent Control Underground Space Xuzhou 221116 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China

Visual reinforcement learning (VRL) aims to optimize policies by utilizing information derived from visual sensory inputs. To tackle the challenges of high dimensionality and sample efficiency, numerous studies have leveraged self-supervised learning to encode observations into latent state representations. Though these algorithms have shown promise, they may be susceptible to task-irrelevant distractions, such as changes in background, color, and camera angles. Thus, we propose the clustering-driven state embedding for reinforcement learning (RL) under visual distractions (CSE-RL) to learn more robust state representations. The student's $t$ distribution is first utilized to model the predicted clustering assignment. In this process, the reward centers are defined by hardening the target distribution. Subsequently, the state embeddings, rewards, and their respective centers are fed into the predicted clustering assignment function for clustering. To avoid trivial solutions, the Sinkhorn-Knopp algorithm is adopted to balance observations across clusters. The proposed CSE-RL has the capacity to enhance the comprehension of inherent relationships among different states, while also filtering out irrelevant or redundant information, resulting in the creation of more efficient representations that are less prone to visual distractions. Experimental results from the distracting control suite (DCS) indicate that CSE-RL achieves comparable or even better performance compared with several state-of-the-art VRL algorithms in handling challenging visual distractions. Notably, CSE-RL exhibits remarkable improvements of 31.82% and 18.18% on DCS over baselines based on data-regularized Q (DrQ) and DrQv2 frameworks, respectively. Integrating CSE-RL into offline RL offers promising avenues for future study.

关键词： clustering algorithms Visualization Representation learning Heuristic algorithms Feature extraction Prediction algorithms Training clustering state embedding student's t distribution visual distractions visual reinforcement learning (VRL)

来源：评论

学校读者我要写书评

暂无评论

A New clustering-Based View Planning Method for Building Inspection With Drone

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第11期9卷 9781-9788页

作者： Zheng, Yongshuai Liu, Guoliang Ding, Yan Tian, Guohui Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China

With the rapid development of drone technology, the application of drones equipped with visual sensors for building inspection and surveillance has attracted much attention. View planning aims to find a set of near-optimal viewpoints for vision-related tasks to achieve the vision coverage goal. This letter proposes a new clustering-based two-step computational method using spectral clustering, local potential field method, and hyper-heuristic algorithm to find near-optimal views to cover the target building surface. In the first step, the proposed method generates candidate viewpoints based on spectral clustering and corrects the positions of candidate viewpoints based on our newly proposed local potential field method. In the second step, the optimization problem is converted into a Set Covering Problem (SCP), and the optimal viewpoint subset is solved using our proposed hyper-heuristic algorithm. Experimental results show that the proposed method is able to obtain better solutions with fewer viewpoints and higher coverage.

关键词： Planning clustering algorithms Vectors Optimization Drones Visualization Buildings Computational geometry surveillance robotic systems task planning

来源：评论

学校读者我要写书评

暂无评论

SDAC-DA: Semi-Supervised Deep Attributed clustering Using Dual Autoencoder

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第11期36卷 6989-7002页

作者： Berahmand, Kamal Bahadori, Sondos Abadeh, Maryam Nooraei Li, Yuefeng Xu, Yue Queensland Univ Technol QUT Fac Sci Sch Comp Sci Brisbane Qld 4000 Australia Islamic Azad Univ Dept Comp Engn Ilam Branch J9QJ 3Q4 Ilam Iran Islamic Azad Univ Dept Comp Engn Abadan Branch Abadan *** Iran

Attributed graph clustering aims to group nodes into disjoint categories using deep learning to represent node embeddings and has shown promising performance across various applications. However, two main challenges hinder further performance improvement. First, reliance on unsupervised methods impedes the learning of low-dimensional, clustering-specific features in the representation layer, thus impacting clustering performance. Second, the predominant use of separate approaches leads to suboptimal learned embeddings that are insufficient for subsequent clustering steps. To address these limitations, we propose a novel method called Semi-supervised Deep Attributed clustering using Dual Autoencoder (SDAC-DA). This approach enables semi-supervised deep end-to-end clustering in attributed networks, promoting high structural cohesiveness and attribute homogeneity. SDAC-DA transforms the attribute network into a dual-view network, applies a semi-supervised autoencoder layering approach to each view, and integrates dimensionality reduction matrices by considering complementary views. The resulting representation layer contains high clustering-friendly embeddings, which are optimized through a unified end-to-end clustering process for effectively identifying clusters. Extensive experiments on both synthetic and real networks demonstrate the superiority of our proposed method over seven state-of-the-art approaches.

关键词： Vectors clustering algorithms Image edge detection clustering methods Transforms Task analysis STEM Attributed network deep attributed clustering semi-supervised clustering pairwise constraints

来源：评论

学校读者我要写书评

暂无评论

Scalable and Structural Multi-View Graph clustering With Adaptive Anchor Fusion

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 4627-4639页

作者： Wang, Siwei Liu, Xinwang Liu, Suyuan Tu, Wenxuan Zhu, En Intelligent Game & Decis Lab IGDL Beijing 100091 Peoples R China Natl Univ Def Technol Sch Comp Changsha 410073 Peoples R China

Anchor graph has been recently proposed to accelerate multi-view graph clustering and widely applied in various large-scale applications. Different from capturing full instance relationships, these methods choose small portion anchors among each view, construct single-view anchor graphs and combine them into the unified graph. Despite its efficiency, we observe that: (i) Existing mechanism adopts a separable two-step procedure-anchor graph construction and individual graph fusion, which may degrade the clustering performance. (ii)These methods determine the number of selected anchors to be equal among all the views, which may destruct the data distribution diversity. A more flexible multi-view anchor graph fusion framework with diverse magnitudes is desired to enhance the representation ability. (iii) During the latter fusion process, current anchor graph fusion framework follows simple linearly-combined style while the intrinsic clustering structures are ignored. To address these issues, we propose a novel scalable and flexible anchor graph fusion framework for multi-view graph clustering method in this paper. Specially, the anchor graph construction and graph alignment are jointly optimized in our unified framework to boost clustering quality. Moreover, we present a novel structural alignment regularization to adaptively fuse multiple anchor graphs with different magnitudes. In addition, our proposed method inherits the linear complexity of existing anchor strategies respecting to the sample number, which is time-economical for large-scale data. Experiments conducted on various benchmark datasets demonstrate the superiority and effectiveness of the newly proposed anchor graph fusion framework against the existing state-of-the-arts over the clustering performance promotion and time expenditure. Our code is publicly available at https://***/wangsiwei2010/SMVAGC-SF.

关键词： Complexity theory clustering algorithms Fuses clustering methods Periodic structures Benchmark testing Aggregates Large-scale clustering multi-view graph clustering anchor graph

来源：评论

学校读者我要写书评

暂无评论

An Edge-Cloud-Aided Private High-Order Fuzzy C-Means clustering Algorithm in Smart Healthcare

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第4期21卷 1083-1092页

作者： Yu, Hang Zhang, Qingchen Yang, Laurence T. Hainan Univ Haikou 570228 Hainan Peoples R China St Francis Xavier Univ Antigonish NS B2G 2W5 Canada

Smart healthcare has emerged to provide healthcare services using data analysis techniques. Especially, clustering is playing an indispensable role in analyzing healthcare records. However, large multi-modal healthcare data imposes great challenges on clustering. Specifically, it is hard for traditional approaches to obtain desirable results for healthcare data clustering since they are not able to work for multi-modal data. This paper presents a new high-order multi-modal learning approach using multimodal deep learning and the Tucker decomposition (F- HoFCM). Furthermore, we propose an edge-cloud-aided private scheme to facilitate the clustering efficiency for its embedding in edge resources. Specifically, the computationally intensive tasks, such as parameter updating with high-order back propagation algorithm and clustering through high-order fuzzy c-means, are processed in a centralized location with cloud computing. The other tasks such as multi-modal data fusion and Tucker decomposition are performed at the edge resources. Since the feature fusion and Tucker decomposition are nonlinear operations, the cloud cannot obtain the raw data, thus protecting the privacy. Experimental results state that the presented approach produces significantly more accurate results than the existing high-order fuzzy c-means (HOFCM) on multi-modal healthcare datasets and furthermore the clustering efficiency are significantly improved by the developed edge-cloud-aided private healthcare system.

关键词： Medical services clustering algorithms Tensors Kernel Medical diagnostic imaging Deep learning Data analysis fuzzy C-means smart healthcare tensor tucker decomposition

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Hierarchical clustering and Refinement for Unsupervised Visible-Infrared Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第4期34卷 2706-2718页

作者： Pang, Zhiqi Wang, Chunyu Zhao, Lingling Liu, Yang Sharma, Gaurav Harbin Inst Technol Fac Comp Harbin 150001 Heilongjiang Peoples R China Univ Rochester Dept Elect & Comp Engn Rochester NY 14627 USA

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality image retrieval task. Compared to visible modality person re-identification that handles only the intra-modality discrepancy, VI-ReID suffers from an additional modality gap. Most existing VI-ReID methods achieve promising accuracy in a supervised setting, but the high annotation cost limits their scalability to real-world scenarios. Although a few unsupervised VI-ReID methods already exist, they typically rely on intra-modality initialization and cross-modality instance selection, despite the additional computational time required for intra-modality initialization. In this paper, we study the fully unsupervised VI-ReID problem and propose a novel cross-modality hierarchical clustering and refinement (CHCR) method by promoting modality-invariant feature learning and improving the reliability of pseudo-labels. Unlike conventional VI-ReID methods, CHCR does not rely on any manual identity annotation and intra-modality initialization. First, we design a simple and effective cross-modality clustering baseline that clusters between modalities. Then, to provide sufficient inter-modality positive sample pairs for modality-invariant feature learning, we propose a cross-modality hierarchical clustering algorithm to promote the clustering of inter-modality positive samples into the same cluster. In addition, we develop an inter-channel pseudo-label refinement algorithm to eliminate unreliable pseudo-labels by checking the clustering results of three channels in the visible modality. Extensive experiments demonstrate that CHCR outperforms state-of-the-art unsupervised methods and achieves performance competitive with many supervised methods.

关键词： Cameras clustering algorithms Training Annotations Representation learning Intellectual property Gray-scale Person re-identification cross-modality unsupervised clustering contrastive learning

来源：评论

学校读者我要写书评

暂无评论

clustering-Driven Optimization of RRH-BBU Assignment for Green Communication Networks With Big Data Analytics

引用

IEEE ACCESS 2024年 12卷 177080-177092页

作者： Ibrahim, Asmaa Elsheikh, Ahmed Mokhtar, Bassem Prat, Josep Univ Politecn Cataluna Dept Signal Theory & Commun Barcelona 08034 Spain United Arab Emirates Univ Coll Informat Technol Comp & Networks Engn Dept Abu Dhabi U Arab Emirates Cairo Univ Fac Engn Dept Math & Engn Phys Giza 12613 Egypt Alexandria Univ Fac Engn Dept Elect Engn Alexandria 21544 Egypt

The Centralized Radio Access Networks (CRAN) decentralizes data and control planes by separating the baseband unit (BBU) from the central office, enabling energy-efficient "green networks" through the shutdown of underutilized BBUs. Analyzing extensive Call Detail Records (CDR) as big data, collected by service providers, has gained traction for extracting network features and studying activities. Thus, big data analytics are deemed as potential techniques that various research proposed to analyze the CDR. This paper introduces an energy-efficient CRAN network architecture based on the CRAN framework, focused on an innovative remote radio head (RRH)-BBU assignment. The objective is twofold: minimizing power consumption by deactivating underutilized BBUs and reducing inter-BBU handover rates based on CDR insights. In literature, the problem of assigning RRH to BBU is described as hard nonlinear programming (NLP) problem (bin packing, mixed integer), different suboptimal algorithms have been proposed to offer suboptimal assignment. This study employs clustering techniques to divide the complex NLP problem into simpler optimization tasks, achieving optimal RRH-BBU assignments. The proposed algorithm's effectiveness was assessed using Milan city CDR as a case study, and its performance was validated against Milan's land use map. The results indicated a remarkable 28.8% reduction in power consumption, alongside improvements in inter-BBU handovers.

关键词： clustering algorithms Optimization Heuristic algorithms Quality of service Computer architecture Handover Resource management Power demand Urban areas Prediction algorithms 5G communication systems CRAN networks architecture temporal databases clustering optimization algorithms spatio-temporal clustering RRH BBU green communications

来源：评论

学校读者我要写书评

暂无评论

Multi-View Comprehensive Graph clustering

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3279-3288页

作者： Mei, Yanying Ren, Zhenwen Wu, Bin Yang, Tao Shao, Yanhua Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Peoples R China Southwest Univ Sci & Technol Sch Natl Def Sci & Technol Mianyang 621010 Peoples R China Wuzhou Univ Guangxi Key Lab Machine Vis & Intelligent Control Wuzhou 543002 Peoples R China

Multi-view clustering algorithms have been successfully used in different consumer electronic products, such as common digital cameras and unmanned vehicles. Currently, existing multi-view graph clustering (MVGC) methods learn the similarity of directly connected samples for clustering. However, these MVGC methods can not fully consider the indirect relation among samples and high-order relation across multi-view data. In this paper, a new multi-view comprehensive graph clustering (MCGC) method is devised, which can fully learn the similarity based on (1) first-order proximity (FOP) (i.e., the direct relation of pairwise samples);(2) second-order proximity (SOP) (i.e., the indirect relation of pairwise samples);and (3) third-order proximity (TOP) (i.e., the three-order relation of multiple views). Since the operations of these three components are iteratively carried out, the interaction between similarity learning can be encouraged and the comprehensive graph can be generated effectively for clustering. In-depth experiments on six commonly benchmark datasets show the superiority of the MCGC method.

关键词： Tensors Excavation Correlation Consumer electronics clustering methods clustering algorithms Merging Comprehensive graph learning multi-view clustering similarity learning low-rank tensor representation

来源：评论

学校读者我要写书评

暂无评论

Score, Arrange, and Cluster: A Novel clustering-Based Technique for Privacy-Preserving Data Publishing

引用

IEEE ACCESS 2024年 12卷 79861-79874页

作者： Sowmyarani, C. N. Namya, L. G. Nidhi, G. K. Ramakanth Kumar, P. RV Coll Engn Bengaluru 560059 India

Data-driven decision-making has become critical to every organization. There is a growing emphasis on adopting robust data governance frameworks for data management. This encompasses data publishing to empower stakeholders with the ability to access and analyze the published data, playing a pivotal role in decision-making. However, data publishing poses a threat to entity-specific information. Privacy-Preserving Data Publishing (PPDP) refers to publishing data while protecting the privacy of entity-specific information. K-anonymity is a well-recognized method that achieves PPDP and serves as the foundation of our proposed clustering-based data transformation algorithm, "Score, Arrange, and Cluster (SAC)". For effective data management and decision-making in organizations, it is crucial to address the varying data requirements and role-based access levels of the involved stakeholders. SAC was designed to offer only a generic data transformation with minimal data quality degradation. Hence, this work presents an enhancement to SAC that takes into account stakeholder roles and requirements, as illustrated through different scenarios. The scoring mechanism in SAC is augmented to accommodate customization or use the concepts of Genetic algorithms to enforce role-based access control. The "Cost of Degradation" (CoD) metric is used to quantify the data quality degradation. As per the experimental results, in the customization scenario, a higher attribute priority leads to lower data quality degradation, while, in the role-based access control scenario a higher access level results in a lower data quality degradation.

关键词： Data privacy Publishing Stakeholders clustering algorithms Data models Information integrity Genetic algorithms Decision making Homomorphic encryption clustering k-anonymity data privacy privacy-preserving data publishing genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based clustering and Modeling for 6G UAV-to-Ground Communication Channels

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第10期73卷 14113-14126页

作者： Zhang, Zhaolei Liu, Yu Wang, Cheng-Xiang Chang, Hengtai Bian, Ji Zhang, Jingfan Shandong Univ Sch Integrated Circuits Jinan 250101 Peoples R China Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China

Towards the sixth-generation (6G) wireless communication, unmanned aerial vehicles (UAVs) have been regarded as an indispensable part due to its flexible deployment, wide coverage, and high mobility. This also creates challenges for channel research. Scatterers are normally present in the structure of clusters during UAV communication, and cluster-based channel modeling is significant. In this paper, the variational Bayesian-Gaussian mixture model (VB-GMM) algorithm is proposed for clustering, which takes into account the time-space properties. Cluster tracking is implemented using the multipath component distance (MCD) algorithm. Intra- and inter-cluster characterization, such as the number of clusters, cluster power distribution, angular/delay offset, and angular/delay spreads, are well studied. Moreover, cluster lifetime and birth-death (B-D) properties are extracted and analyzed. Based on these cluster characteristics acquired by machine learning (ML) method, a novel UAV-to-ground communication channel model is proposed, and a four-state Markov chain is also introduced to portray the evolution of clusters. Simulation results match well with channel measurements, which verifies the practicality of the proposed model. This paper can give theoretical and technical support for the design and evaluation of UAV-to-ground communication systems.

关键词： clustering algorithms Autonomous aerial vehicles Delays Communication channels clustering methods Wireless communication Millimeter wave communication 6G channel modeling cluster characterization machine learning UAV communications

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：