检索结果-南通市图书馆

An anchor-based spectral clustering method

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2018年第11期19卷 1385-1396页

作者： Qin ZHANG Guo-qiang ZHONG Jun-yu DONG Department of Computer Science and Technology Ocean University of China Science and Information College Qingdao Agricultural University

Spectral clustering is one of the most popular and important clustering methods in pattern recognition,machine learning, and data mining. However, its high computational complexity limits it in applications involving truly large-scale datasets. For a clustering problem with n samples, it needs to compute the eigenvectors of the graph Laplacian with O(n^3) time complexity. To address this problem, we propose a novel method called anchor-based spectral clustering(ASC) by employing anchor points of data. Specifically, m(m≤n) anchor points are selected from the dataset, which can basically maintain the intrinsic(manifold) structure of the original data. Then a mapping matrix between the original data and the anchors is constructed. More importantly, it is proved that this data-anchor mapping matrix essentially preserves the clustering structure of the data. Based on this mapping matrix, it is easy to approximate the spectral embedding of the original data. The proposed method scales linearly relative to the size of the data but with low degradation of the clustering performance. The proposed method, ASC,is compared to the classical spectral clustering and two state-of-the-art accelerating methods, i.e., power iteration clustering and landmark-based spectral clustering, on 10 real-world applications under three evaluation metrics.Experimental results show that ASC is consistently faster than the classical spectral clustering with comparable clustering performance, and at least comparable with or better than the state-of-the-art methods on both effectiveness and efficiency.

关键词： clustering Spectral clustering Graph Laplacian Anchors

Location-and Relation-Based clustering on Privacy-Preserving Social Networks

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2018年第4期23卷 453-462页

作者： Dan Yin Yiran Shen College of Computer Science and Technology Harbin Engineering University

Graph clustering has a long-standing problem in that it is difficult to identify all the groups of vertices that are cohesively connected along their internal edges but only sparsely connected along their external edges. Apart from structural information in social networks, the quality of the location-information clustering has been improved by identifying clusters in the graph that are closely connected and spatially compact. However, in real-world scenarios, the location information of some users may be unavailable for privacy reasons, which renders existing solutions ineffective. In this paper, we investigate the clustering problem of privacy-preserving social networks, and propose an algorithm that uses a prediction-and-clustering approach. First, the location of each invisible user is predicted with a probability distribution. Then, each user is iteratively assigned to different clusters. The experimental results verify the effectiveness and efficiency of our method, and our proposed algorithm exhibits high scalability on large social networks.

关键词： clustering location prediction privacy-preserving social networks

SOM approach for clustering customers using credit card transactions

在线全文

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2019年第3期12卷 372-388页

作者： Seda Yanık Abdelrahman Elmorsy Istanbul Technical University IstanbulTurkey

Purpose–The purpose of this paper is to generate customer clusters using self-organizing map(SOM)approach,a machine learning technique with a big data set of credit card consumptions.The authors aim to use the consumption patterns of the customers in a period of three months deducted from the credit card transactions,specifically the consumption categories(e.***.food,entertainment,etc.).Design/methodology/approach–The authors use a big data set of almost 40,000 credit card transactions to cluster customers.To deal with the size of the data set and the eliminated the required parametric assumptions the authors use a machine learning technique,SOMs.The variables used are grouped into three as demographical variables,categorical consumption variables and summary consumption variables.The variables are first converted to factors using principal component analysis.Then,the number of clusters is specified by k-means clustering trials.Then,clustering with SOM is conducted by only including the demographical variables and allvariables.Then,a comparisonis made and the significance of the variablesis examined by analysis of variance.Findings–The appropriate number of clusters is found to be 8 using k-means clusters.Then,the differences in categorical consumption levels are investigated between the clusters.However,they have been found to be insignificant,whereas the summary consumption variables are found to be significant between the clusters,as well as the demographical variables.Originality/value–The originality of the study is to incorporate the credit card consumption variables of customers to cluster the bank customers.The authors use a big data set and dealt with it with a machine learning technique to deduct the consumption patterns to generate the clusters.Credit card transactions generate a vast amount of data to deduce valuable information.It is mainly used to detect fraud in the literature.To the best of the authors’knowledge,consumption patterns obtained from credit card transaction are first used for clustering

关键词： PCA clustering Self-organizing maps k-means Credit card transactions

Research on D2D Co-localization Algorithm Based on clustering Filtering

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2020年第8期17卷 121-132页

作者： Jiawen Zhang Fuxing Yang Zhongliang Deng Xiao Fu Jiazhi Han School of Automation Beijing University of Posts and TelecommunicationsBeijing 100876China School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

Nowadays, most positioning systems carry out locational calculation based on the accurate location information of some devices in the network. However there is a deviation in the locational information of the part of the device, we need to reduce it in order to obtain higher positioning accuracy. In this paper, we proposed a new centralized D2D(Device-to-Device) co-location algorithm. This algorithm uses DBSACN(Density-Based Spatial clustering of Applications with Noise) clustering to reduce the deviation of device location information. Numerical results show that the positioning accuracy of the centralized D2D co-localization algorithm is improved by 62.7% compared with the SPAWN algorithm, which positioning performance superior to the traditional co-localization algorithm.

关键词： co-location D2D clustering DBSACN

clustering and Mixed Integer Linear Programming for Rebalancing Problem of Dockless Sharing Bicycles

在线全文

学校读者我要写书评

暂无评论

Clustering and Mixed Integer Linear Programming for Rebalanc...

作者： Dildar Ahmed（迪达）东南大学

学位级别：硕士

Bike sharing systems without docking stations have got much popularity and rapidly growing in today’s era and becoming an integral part of green Transportation systems but in parallel,it raises severe management and rebalancing issues,which are becoming a challenge in their development and sustainability.Bicycles availability and shortages are in direct relation with the user satisfaction level.A uniform distribution of bicycle inventories over a network of zones to achieve optimal inventories with minimum cost is mainly focussed in this study.Rebalancing problem of dockless sharing bicycle’s systems is addressed in two stages.In the first stage,the randomly scattered bicycles positions are traced out in an area where rebalancing activity will take place and then further divided them into several groups or clusters of either surplus or deficit ones through the clustering technique of K-means clustering algorithm which is a distance-based algorithmic approach that minimizes the distance of bicycles and assigned bicycle to cluster.These clustering and collection mechanism will develop the supply and demand level in each zone which could be thoroughly manipulated before starting the main truck rebalancing operation among zones.In the 2

关键词： clustering K-means algorithm vehicle routing problem Pick-up and delivery

A Comprehensive Approach for the clustering of Similar-Performance Cells for the Design of a Lithium-Ion Battery Module for Electric Vehicles

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Engineering 2019年第4期5卷 795-802页

作者： Wei Li Siqi Chen Xiongbin Peng Mi Xiao Liang Gao Akhil Garg Nengsheng Bao State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Key Lab of Mechatronic Systems Intelligent Integration Technology Ministry of EducationShantou UniversityShantou 515063China

An energy-storage system comprised of lithium-ion battery modules is considered to be a core component of new energy vehicles,as it provides the main power source for the transmission system.However,manufacturing defects in battery modules lead to variations in performance among the cells used in series or parallel configuration.This variation results in incomplete charge and discharge of batteries and non-uniform temperature distribution,which further lead to reduction of cycle life and battery capacity over time.To solve this problem,this work uses experimental and numerical methods to conduct a comprehensive investigation on the clustering of battery cells with similar performance in order to produce a battery module with improved electrochemical performance.Experiments were first performed by dismantling battery modules for the measurement of performance parameters.The kmeans clustering and support vector clustering(SVC)algorithms were then employed to produce battery modules composed of 12 cells each.Experimental verification of the results obtained from the clustering analysis was performed by measuring the temperature rise in the cells over a certain period,while air cooling was provided.It was found that the SVC-clustered battery module in Category 3 exhibited the best performance,with a maximum observed temperature of 32℃.By contrast,the maximum observed temperatures of the other battery modules were higher,at 40℃for Category 1(manufacturer),36℃for Category 2(manufacturer),and 35℃for Category 4(k-means-clustered battery module).

关键词： clustering algorithm Battery module Equalization Electric vehicle

An energy-degree evaluation metric for clustering purposes in mobile ad hoc networks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Modeling, Simulation, and Scientific Computing 2019年第2期10卷 114-132页

作者： Khalil Amine MOAD6 Research Team MASI LaboratoryE3S Research Centre Mohammadia School of Engineering Mohammed V University of RabatMorocco

Network clustering is the process of partitioning a network into a number of virtual entities mastered by certain nodes,called cluster centers that are responsible for collecting and maintaining topology information and managing the routing processes.In ad hoc networking,clustering has been introduced to deal with the dynamic topology by providing a temporarily stable network core.clustering process mainly depends on the metric upon which the selection of cluster centers is performed.A wide range of clustering metrics were introduced in the literature based on network issues including mobility and connectivity degree,giving rise to a variety of clustering schemes.Although clustering provides energy consumption reduction,residual energy has not received enough attention and few studies have addressed the clustering on the basis of this feature.This paper discusses the current clustering metrics and proposes an energy-degree evaluation metric with mobility consideration taking into account the nodes residual energy and the network connectivity as two main keys of clustering.

关键词： Ad hoc networks clustering dominating set energy aware mobility

A Novel clustering Technique for Efficient clustering of Big Data in Hadoop Ecosystem

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2019年第4期2卷 240-247页

作者： Sunil Kumar Maninder Singh Directorate of Livestock Farms Guru Angad Dev Veterinary and Animal Sciences UniversityLudhiana 141001India Department of Computer Science Punjabi UniversityPunjab 147002India

Big data analytics and data mining are techniques used to analyze data and to extract hidden information.Traditional approaches to analysis and extraction do not work well for big data because this data is complex and of very high volume. A major data mining technique known as data clustering groups the data into clusters and makes it easy to extract information from these clusters. However, existing clustering algorithms, such as k-means and hierarchical, are not efficient as the quality of the clusters they produce is compromised. Therefore, there is a need to design an efficient and highly scalable clustering algorithm. In this paper, we put forward a new clustering algorithm called hybrid clustering in order to overcome the disadvantages of existing clustering algorithms. We compare the new hybrid algorithm with existing algorithms on the bases of precision, recall, F-measure, execution time, and accuracy of results. From the experimental results, it is clear that the proposed hybrid clustering algorithm is more accurate, and has better precision, recall, and F-measure values.

关键词： clustering Hadoop big data k-means hierarchical

High-throughput fat quantifications of hematoxylin-eosin stained liver histopathological images based on pixel-wise clustering

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2017年第9期60卷 109-120页

作者： Peng SHI Junru CHEN Jinke LIN Lurong ZHANG College of Mathematics and Computer Science Fujian Normal University College of Horticulture Fujian Agriculture and Forestry University Central Laboratory First Affiliated Hospital Fujian Medical University Department of Radiation Oncology UF Shands Cancer Center

Besides diagnosis of fatty liver disease(FLD) using multiple medical imaging techniques in clinic,accurate fat quantification of liver tissue slice, especially the fat droplets measurement, is still a critical indicator in related pathological researches. Stained by hematoxylin-eosin(HE), different tissue components with different colors need to be identified and measured manually in conventional approaches. Automated liver fat quantification of HE stained images remains challenging because forms and distributions of fat are extremely irregular with no clear boundaries, especially in conducting high-throughput analysis which demands quick processing and higher accuracy for the reference of pathologists. To solve this problem, we propose an automated liver fat quantifications pipeline of HE stained images based on pixel-wise clustering, which firstly extracts high-relevant pixel-level features with color mode transformation, then locates boundaries between nuclei, fat and other components by clustering image pixels in an unsupervised mode, and finally identifies indicative fat droplets based on a set of morphological criteria. The pipeline was verified in analysis of multifold fatty liver treatment assays, with experimental results showing high accuracy and adaptability in fat droplets quantification despite data variance. Quantitative indicators provide a reliable evidence for relevant pathological researches or therapy selection, in which number and average area of indicative fat droplets increased sharply in severe and moderate-grade FLD respectively. Those indicators might be utilized as surrogate biomarkers for further researches.

关键词： fatty liver disease liver histopathological images hematoxylin-eosin staining liver fat quantifica tion image segmentation clustering