检索结果-内蒙古大学图书馆

An Improved Robust Fuzzy Local Information K-Means clustering Algorithm for Diabetic Retinopathy Detection

IEEE ACCESS 2024年 12卷 78611-78623页

作者： Naz, Huma Saba, Tanzila Alamri, Faten S. Almasoud, Ahmed S. Rehman, Amjad Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 India Prince Sultan Univ Coll Comp & Informat Sci Artificial Intelligence & Data Analyt Lab Riyadh 11586 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Sci Dept Math Sci POB 84428 Riyadh 11671 Saudi Arabia

According to the International Diabetes Federation (IDF), roughly 33% of individuals affected by diabetes exhibit diagnoses encompassing diverse severity of diabetic retinopathy. In the year 2020, approximately 463 million adults within the age bracket of 20 to 79 were documented as diabetes sufferers on a global scale. Projections suggest a rise to 700 million by 2045. The proposed automated diabetic retinopathy detection methods aim to reduce the workload of ophthalmologists. The study presents the Robust Fuzzy Local Information K-Means clustering algorithm, an advanced iteration of the classical K-means clustering approach, integrating localized information parameters tailored to individual clusters. Comparative analysis is conducted between the performance of Robust Fuzzy Local Information K-Means clustering and Modified Fuzzy C Means clustering, which incorporates a median adjustment parameter to augment Fuzzy C Means for diabetic retinopathy detection. The results are evaluated on three datasets: IDRiD, Kaggle, and fundus images collected from Shiva Netralaya Center, India. Achieving a 94.4% accuracy rate and an average execution time of 17.11 seconds, the proposed algorithm aims to categorize a substantial volume of retinal images, thereby improving performance and meeting the crucial demand for prompt and precise diagnoses in diabetic retinopathy healthcare.

关键词： clustering algorithms Diabetic retinopathy Unsupervised learning Training Mathematical models Deep learning Convolutional neural networks Fuzzy systems Medical services Diabetic retinopathy detection unsupervised learning Fuzzy C Means clustering healthcare

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Continual Federated clustering via Adaptive Resonance Theory

引用

IEEE ACCESS 2024年 12卷 139692-139710页

作者： Masuyama, Naoki Nojima, Yusuke Toda, Yuichiro Loo, Chu Kiong Ishibuchi, Hisao Kubota, Naoyuki Osaka Metropolitan Univ Grad Sch Informat Dept Core Informat Sakai Osaka 5998531 Japan Okayama Univ Fac Environm Life Nat Sci & Technol Okayama 7008530 Japan Univ Malaya Fac Comp Sci & Informat Technol Dept Artificial Intelligence Kuala Lumpur 50603 Malaysia Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Peoples R China Tokyo Metropolitan Univ Grad Sch Syst Design Dept Mech Syst Engn Tokyo 1910065 Japan

With the increasing importance of data privacy protection, various privacy-preserving machine learning methods have been proposed. In the clustering domain, various algorithms with a federated learning framework (i.e., federated clustering) have been actively studied and showed high clustering performance while preserving data privacy. However, most of the base clusterers (i.e., clustering algorithms) used in existing federated clustering algorithms need to specify the number of clusters in advance. These algorithms, therefore, are unable to deal with data whose distributions are unknown or continually changing. To tackle this problem, this paper proposes a privacy-preserving continual federated clustering algorithm. In the proposed algorithm, an adaptive resonance theory-based clustering algorithm capable of continual learning is used as a base clusterer. Therefore, the proposed algorithm inherits the ability of continual learning. Experimental results with synthetic and real-world datasets show that the proposed algorithm has superior clustering performance to state-of-the-art federated clustering algorithms while realizing data privacy protection and continual learning ability. The source code is available at https://***/Masuyama-lab/FCAC.

关键词： clustering algorithms Differential privacy Servers Kernel Cryptography Protection Privacy Self-organizing feature maps Continuing education Federated learning adaptive resonance theory continual learning federated clustering local & varepsilon -differential privacy

来源：评论

学校读者我要写书评

暂无评论

An Improved Density-Based clustering Algorithm Based on Cellular Neural Networks

引用

IEEE ACCESS 2024年 12卷 138027-138046页

作者： Xu, Jiexi Ling, Bingo Wing-Kuen Liu, Qing Wei, Yiting Zhang, Zhanbin Guangdong Univ Technol Sch Informat Engn Guangzhou 510006 Peoples R China

clustering plays a major role in various disciplines including biological visual image classification. Various clustering algorithms have been introduced and developed. Among them, the density-based clustering algorithm achieves the best performance. The cellular neural network (CNN) based clustering algorithm (CNNCA) is a density-based method. It performs the clustering at a very high speed because the CNN can be implemented on a silicon chip. Nevertheless, the performance of the CNNCA is significantly degraded when facing clusters of complex structures, especially with significant density differences between clusters. In this paper, the local rules of the CNNs are modified. Moreover, the multi-spatial resolutions are employed. In particular, the values of minimum spatial resolution and the other parameters are adaptively designed. Hence, the iterative procedures can be applied to the remaining unassigned points. Furthermore, the conditional minimum distance rule is employed to assign the dispersed elements to the existing clusters. Different datasets have been utilized to evaluate the performance of our proposed method. Compared to the state-of-the-art clustering algorithms, the computer numerical simulation results show that our proposed method outperforms the existing state-of-the-art methods in higher accuracy and more robustness.

关键词： clustering algorithms Classification algorithms Convolutional neural networks Spatial resolution Partitioning algorithms Noise measurement Cellular neural networks Unsupervised learning clustering multi-spatial resolutions cellular neural networks density-based clustering algorithm unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Graph Global and Local Concept Factorization for Data clustering

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第1期35卷 803-816页

作者： Li, Ning Leng, Chengcai Cheng, Irene Basu, Anup Jiao, Licheng Northwest Univ Sch Math Xian 710127 Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China

Considering a wide range of applications of nonnegative matrix factorization (NMF), many NMF and their variants have been developed. Since previous NMF methods cannot fully describe complex inner global and local manifold structures of the data space and extract complex structural information, we propose a novel NMF method called dual-graph global and local concept factorization (DGLCF). To properly describe the inner manifold structure, DGLCF introduces the global and local structures of the data manifold and the geometric structure of the feature manifold into CF. The global manifold structure makes the model more discriminative, while the two local regularization terms simultaneously preserve the inherent geometry of data and features. Finally, we analyze convergence and the iterative update rules of DGLCF. We illustrate clustering performance by comparing it with latest algorithms on four real-world datasets.

关键词： Manifolds Linear programming Convergence clustering algorithms Data models Principal component analysis Learning systems Concept factorization (CF) global regularization image clustering local regularization

来源：评论

学校读者我要写书评

暂无评论

clustering-Based Distributed Fault-Tolerant Target Tracking for Sensors With Decreased Detection Accuracy

引用

IEEE SENSORS JOURNAL 2024年第11期24卷 18428-18443页

作者： Zhang, Yujie Zhang, Zheng Yu, Jianglong Guo, Dong Li, Qingdong Li, Xiaoduo Ren, Zhang Beihang Univ Sch Automat Sci & Elect Engn Sci & Technol Aircraft Control Lab Beijing 100191 Peoples R China China Acad Launch Vehicle Technol Beijing 100000 Peoples R China Beihang Univ Ecole Cent Pekin Beijing 100191 Peoples R China

The distributed state estimation problem of fault sensors with decreased detection accuracy is investigated. The biggest challenge is to reduce or even eliminate the influence of local state estimation of fault sensor on the fused state estimation in consensus fusion. The clustering-based distributed cubature information filter (DCIF) is proposed to deal with the challenge. To improve the accuracy of distributed state estimation, density-based spatial clustering of applications with noise (DBSCAN) clustering is used to distinguish the fault sensors with decreased detection accuracy from the normal sensors. After the normal sensors are selected by DBSCAN clustering, an improved consensus-based fusion method is designed to obtain distributed consensus estimations on the premise of keeping the communication topology of wireless sensor network (WSN) unchanged. The proposed method can delete the local state estimations of the fault sensors and realize the distributed consensus fusion. The boundedness of the estimated error is proved by the stochastic stability theory. Finally, the effectiveness of the proposed clustering-based DCIF algorithm is shown by simulation example.

关键词： Sensors Target tracking State estimation Wireless sensor networks clustering algorithms Topology Fault tolerant systems Density-based spatial clustering of applications with noise (DBSCAN) clustering fault-tolerant target tracking multiple-sensor systems sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

A clustering-based analysis method for simulating seismic damage of buildings in large cities

引用

ENGINEERING STRUCTURES 2024年 307卷

作者： Chen, Xianan Zhang, Lingxin Lin, Xuchuan Skalomenos, Konstantinos A. Chen, Zifeng China Earthquake Adm Inst Engn Mech Key Lab Earthquake Engn & Engn Vibrat Harbin Peoples R China Minist Emergency Management Key Lab Earthquake Disaster Mitigat Harbin Peoples R China Univ Birmingham Dept Civil Engn Birmingham England Univ West Attica Dept Civil Engn Hydraul Aigaleo Greece 29 Xuefu Rd Harbin 150080 Peoples R China

Earthquakes are major threats to cities. Refined simulations of urban earthquake damage are significant for disaster prevention planning, including post-earthquake emergency rescue operations. However, this approach is time-consuming and computationally demanding. This study presents a novel machine learning method for simulating seismic damage of large urban building groups, thus minimizing the computational time and resources associated with the simulation process. First, the proposed method clusters building structures based on their seismic damage index (DI) under specific ground motions. Subsequently, one structure is selected from each cluster for seismic analysis. This approach significantly reduces the number of analyzed structures. The efficiency and accuracy of this method are studied based on a parametric study that involved an improved K-means clustering algorithm and a grid-based clustering algorithm. A batch-clustering algorithm is also developed to further improve the speed of clustering and efficiency of regional seismic simulations. A large Chinese city is considered as research application example. The results indicated the following: (1) the method based on the improved K-means clustering algorithm was superior;(2) the batch-clustering algorithm significantly speeded up clustering analysis and enhanced efficiency of the seismic simulation;(3) the clustering-based simulation method demonstrated high efficiency and accuracy, with a significant decrease of 90.5% in the calculation time compared with direct nonlinear time history analysis. In addition, the average relative error of the DI was only 11.0%. Moreover, over 85.0% of the structures were estimated to be in the correct damage state.

关键词： Seismic damage simulation Urban building groups Machine learning clustering algorithms Batch clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A clustering Method for Single-Cell RNA-Seq Data Based on Automatic Weighting Penalty and Low-Rank Representation

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第3期21卷 360-371页

作者： Wang, Juan Wang, Zhenchang Yuan, Shasha Zheng, Chunhou Liu, Jinxing Shang, Junliang Qufu Normal Univ Sch Comp Sci Rizhao 276826 Peoples R China

Advances in high-throughput single-cell RNA sequencing (scRNA-seq) technology have provided more comprehensive biological information on cell expression. clustering analysis is a critical step in scRNA-seq research and provides clear knowledge of the cell identity. Unfortunately, the characteristics of scRNA-seq data and the limitations of existing technologies make clustering encounter a considerable challenge. Meanwhile, some existing methods treat different features equally and ignore differences in feature contributions, which leads to a loss of information. To overcome limitations, we introduce a weighted distance constraint into the construction of the similarity graph and combine the similarity constraint. We propose the Joint Automatic Weighting Similarity Graph and Low-rank Representation (JAGLRR) clustering method. Evaluating the contributions of each feature and assigning various weight values can increase the significance of valuable features while decreasing the interference of redundant features. The similarity constraint allows the model to generate a more symmetric affinity matrix. Benefitting from that affinity matrix, JAGLRR recovers the original linear relationship of the data more accurately and obtains more discriminative information. The results on simulated datasets and 8 real datasets show that JAGLRR outperforms 11 existing comparison methods in clustering experiments, with higher clustering accuracy and stability.

关键词： clustering methods Symmetric matrices Sparse matrices Sequential analysis RNA clustering algorithms Matrix decomposition ScRNA-seq data clustering analysis low-rank representation automatic weighting constraints

来源：评论

学校读者我要写书评

暂无评论

SM-DPC: clustering by Fast Search and Find of Density Peaks Based on SNN With Multi-Cluster Fusion Strategy

引用

IEEE ACCESS 2024年 12卷 76413-76431页

作者： Zhou, Shibo Peng, Bingbing Xu, Wenpeng Ren, Luzhen Jimei Univ Nav Coll Xiamen 361021 Peoples R China

The clustering by Fast Search and Find of Density Peaks (DPC) algorithm is a clustering method that automatically identifies clustering centers based on density and relative distance. It has several advantages, including the ability to identify arbitrarily shaped clusters and requiring few input parameters. However, the density measure used in DPC does not consider the spatial distribution characteristics of the sample points in the data set. The clustering performance is suboptimal for datasets with significant differences in cluster density. Additionally, its non-central sample point assignment method is less error-tolerant, which can result in successive assignment errors and a domino effect, ultimately leading to poor clustering accuracy. To address these shortcomings, we propose an improved DPC algorithm based on shared nearest neighbor and multi-cluster fusion (SM-DPC). The local density of sample points is redefined using K-nearest neighbors, which makes the density metric more consistent with the local structural characteristics of the dataset. A two-step allocation strategy for non-central sample points based on shared nearest neighbors is proposed to improve the accuracy of allocation of non-central sample points. A multi-cluster fusion strategy is used to correct the centroid selection bias for datasets where sample points are not uniformly distributed. The experimental results demonstrate that SM-DPC is capable of clustering datasets with arbitrary shape and density distributions effectively. Furthermore, it exhibits superior performance and broader adaptability to different types of datasets compared to DBSCAN, K-means algorithms, and other DPC optimization algorithms.

关键词： clustering algorithms Kernel Data mining Resource management Optimization Mathematical models Density measurement Nearest neighbor methods K-nearest neighbor local density multi-cluster fusion density peaks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Hyper-Multiclass Consumer Electronics Image clustering Using Contrastive Learning

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第4期70卷 7155-7162页

作者： Kiran, Ajmeera Ramesh, Janjhyam Venkata Naga Vimal, Vrince Kumar, Kishore M. Soni, Mukesh Bhushan, Shashi Ahanger, Tariq Ahamed Singh, Pavitar Parkash Singh, Rajesh MLR Inst Technol Dept Comp Sci & Engn Hyderabad 500043 India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram 522502 India Graphic Era Hill Univ Dehra Dun India Graphic Era Univ Dehra Dun 248002 India CMR Tech Campus Dept CSE Data Sci Hyderabad 501401 India Dr DY Patil Vidyapeeth Dr DY Patil Sch Sci & Technol Pune India GLA Univ Mathura Comp Engn & Applicat Dept Mathura 281406 India Prince Sattam Bin Abdulaziz Univ Dept Management Informat Syst CoBA Al Kharj 11942 Saudi Arabia Lovely Profess Univ Dept Management Phagwara 144001 India Uttaranchal Univ Uttaranchal Inst Technol Dept Elect & Commun Engn Dehra Dun 248007 India

Efficient management of image data is essential in the consumer electronics industry. Image clustering has evolved through the utilization of dimensionality reduction and representation learning techniques to extract pertinent features. However, dealing with a broad spectrum of Consumer Electronics Image categories poses challenges due to complex data distribution and cluster density. To tackle these issues, a contrastive learning-based hyper-multiclass deep image clustering approach has been introduced. This model comprises three main steps. Firstly, to accommodate the diverse range of consumer electronics images, the feature model undergoes initial training using enhanced contrastive learning to ensure uniform cluster distribution. Secondly, semantic similarity is leveraged to acquire instance semantic closest neighbor data employing a multi-perspective methodology. Lastly, instances along with their closest neighbors serve as self-supervised information to train the clustering model. Ablation and comparative analyses have demonstrated the efficacy of this approach. It effectively achieves uniform distribution of clusters within the mapped space and consistently extracts semantic nearest neighbor information. Comparative experiments were conducted on benchmark datasets, specifically the ImageNet G200 and G1000 class datasets, within the consumer electronics context. Results indicate a significant improvement in accuracy, with enhancements of 10.6% and 9.2%, respectively, surpassing the performance of existing advanced methods.

关键词： Semantics Feature extraction clustering algorithms Data models Consumer electronics Adaptation models Training Consumer electronics image image clustering deep learning hyper-multiclass analysis contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Machine Well Screening Method Based on POI Data and DBSCAN clustering Algorithm

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Gan, Xing Fan, Haiyan Yang, Moyuan Tang, Fangfang Liu, Honglu Ma, Zhijun Beijing Water Sci & Technol Inst Beijing 100048 Peoples R China Hohai Univ Coll Agr Sci & Engn Nanjing 210098 Peoples R China Beijing Engn Res Ctr Unconvent Water Resources Dev Beijing 100048 Peoples R China China Agr Univ Coll Water Resources & Civil Engn Beijing 100048 Peoples R China Beijing Water Sci & Technol Inst Beijing 100048 Peoples R China Beijing Fangshan Dist Water Affairs Bur Beijing 100048 Peoples R China

Maintaining machinery wells, key to groundwater sustainability, is vital for managing these precious resources. In keeping with the need for effective groundwater management, this study introduces a screening process leveraging the Density-Based Spatial clustering of Applications with Noise (DBSCAN) clustering algorithm and incorporating point of interest (POI) and spatial correlation assessment. Specifically, this approach was utilized in the Fangshan District, Beijing, to detect illegal water extraction wells and bolster water resource management. By integrating POI and land use categorization, we performed a water demand overlay analysis, considering public water provision and well distribution. ArcGIS spatial analysis helped us pinpoint POIs with significant water demand. The DBSCAN clustering algorithm was then employed to scrutinize potential problematic wells. The credibility and practicality of this methodology were confirmed through field studies, meeting current governance standards. The study identified 14 potential unregistered wells, of which 5 were confirmed to be unauthorized, primarily located in Shidu and Zhangfang Towns. Field checks confirmed these findings, highlighting the need for improved groundwater management and validating our method's reliability. Based on these findings, we propose additional steps to enhance groundwater extraction management. This research shows how the use of POI data and the DBSCAN algorithm can aid groundwater resource management in Fangshan District and potentially serve as a model for other regions.

关键词： Water resources Groundwater Data mining Training clustering algorithms Artificial intelligence Water pollution Water conservation Springs Resource management ArcGis density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm point of interest (POI) spatial association analysis

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：