检索结果-内蒙古大学图书馆

A Spectral clustering-Based Multi-Source Mating Selection Strategy in Evolutionary Multi-Objective Optimization

IEEE ACCESS 2019年 7卷 131851-131864页

作者： Wang, Shuai Zhang, Hu Zhang, Yi Zhou, Aimin Wu, Peng Changzhou Univ Sch Mech Engn Changzhou 213164 Peoples R China Beijing Electromech Engn Inst Sci & Technol Complex Syst Control & Intelligent Beijing 100074 Peoples R China East China Normal Univ Sch Comp Sci & Technol Shanghai Key Lab Multidimens Informat Proc Shanghai 200062 Peoples R China

In evolutionary multi-objective optimization, it has been illuminated that guide search with neighboring solutions improve the quality of new trial solutions and accelerate algorithms convergence by the regularity property of the continuous multi-objective optimization problems (MOPs). Very recently, clustering learning-based mating strategies have been popular for establishing reproduction operators with neighboring solutions. However, the existing mating strategies may be more reasonable with the full consideration and utilization of the regularity property. The current mating restrictions excessively emphasize algorithm convergence and ignore population diversity. In addition, the selected clustering algorithms in mating restrictions are not conducive for solving MOPs, which have complex Pareto sets (PSs) and nor Pareto fronts (PFs). To solve above problems and address both the algorithm convergence and the population diversity of multi-objective evolutionary algorithms (MOEAs), the spectral clustering based multi-source mating selection strategy (SMMS) is designed to detect regularity properties and balance population diversity while accelerating algorithm convergence. Consequently, a spectral clustering based multi-source mating selection multi-objective evolutionary algorithms is proposed, teamed SMMEA. SMMEA is applied to a number of test suites with a complex PS or PF, and compared with six state-of-the-art MOEAs. The results demonstrate that the proposed algorithm outperforms over the other approaches.

关键词： algorithm convergence clustering algorithm evolutionary algorithm mating restriction strategy multi-objective optimization population diversity

来源：评论

学校读者我要写书评

暂无评论

Detection of spectrum hole from n-number of primary users using machine learning algorithms

引用

JOURNAL OF ENGINEERING-JOE 2020年第5期2020卷 175-188页

作者： Venkateshkumar, Udayamoorthy Ramakrishnan, Srinivansan Sri Krishna Coll Technol Dept ECE Coimbatore 641042 Tamil Nadu India Dr Mahalingam Coll Engn & Technol Dept IT Pollachi 642003 Tamil Nadu India

A method for detecting spectrum holes based on the n-number of primary users (PU's) in a cognitive radio environment, using a cooperative spectrum sensing model is proposed in this study. The fusion centre, senses the n-number of PUs. When the number of PUs is >200, the probability of detection decreases, while the probability of a false alarm increases. The authors use the random forest (RF) algorithm to classify a customised dataset of 600 training samples. Further, they compare the RF algorithm and the k-means clustering algorithm, using test datasets with a minimum of ten PUs and a maximum of 500 PUs. Five different signal features are considered as the attributes in the proposed model. The maximum probability of detection is achieved using the k-means clustering algorithm in the case of 200 PUs and is 99.17%, while the false alarm probability is 0.8%. The receiver operating characteristic curves indicated that probability of detecting a spectrum hole in the case of the dataset with 500 PUs is 97.67% with the signal to noise ratio ranging from 10 to -12 dB. The accuracy can be increased if the number of clusters formed is increased, depending on the number of test samples.

关键词： cognitive radio signal detection radio spectrum management probability learning (artificial intelligence) spectrum hole primary users machine learning algorithms PU cognitive radio environment spectrum sensing model detection decreases false alarm increases random forest algorithm RF algorithm clustering algorithm 500 PUs maximum probability 200 PUs false alarm probability noise figure -12 0 dB to 10 0 dB

来源：评论

学校读者我要写书评

暂无评论

Analysis of Five clustering algorithms in Quantitative Method Research 25

Analysis of Five Clustering Algorithms in Quantitative Metho...

引用

25th Annual International Conference on Management Science and Engineering

作者： Huang Fu Hou Hai-yan Hu Zhi-gang Wang Ya-jie Dalian Univ Technol Inst Sci Studies & S&T Management WISE Lab Dalian 116024 Peoples R China

ISBN: (纸本)9781538684719

In the course of research using quantitative methods, cluster analysis is often used for scientific research. However, we often face some complicated clustering algorithms during the analysis process. Choosing the right clustering algorithm is a very necessary research issue. Therefore, based on the characteristics of adjacency matrix data, we analyze the commonly used clustering algorithms in scientometrics. Firstly, we analyze the procedure of clustering. Then, the characteristics of several common clustering algorithms are summarized. Third, based on the validity and correctness of clustering, the effect of clustering algorithms are discussed. Finally, we implement the algorithm by MATLAB, and make an empirical analysis of three data sets cases. According to the characteristics of clustering algorithm, the correctness of clustering and the validity of clustering, we choose the clustering algorithm suitable for our use.

关键词： clustering algorithm Quantitative methods Cluster validity Correctness

来源：评论

学校读者我要写书评

暂无评论

Unity in Togetherness: A Review on clustering algorithms in Vehicular Ad-Hoc Networks 2

Unity in Togetherness: A Review on Clustering Algorithms in ...

引用

2nd International Conference on Intelligent Circuits and Systems (ICICS)

作者： Kaur, Arshdeep Sindhwani, Manoj Arora, Sandeep Kumar Lovely Profess Univ Sch Elect & Elect Engn Phagwara India

ISBN: (纸本)9781538664834

This paper presents a novel review of various clustering algorithms used in the vehicular ad hoc networks (VANET). VANET is an emerging technology sharing a plethora of applications providing safety and contentment to the vehicle users. It is a vital part of Intelligent Transport Systems (ITS) which provides coherent and well organized communication between the vehicles like sending warning messages to avoid the accidents and fatal conditions. Peculiar traffic conditions and the dynamic topology of the network can be challenging for the timely delivery of the messages. Though VANETs presents a unique range of challenges for routing, on the other hand it equally presents solutions via clustering algorithms. clustering can be useful in maintaining the stability and reliability of an ad-hoc network that results in performance enhancement. clustering is basically a key technology in VANET that outperform the MANET clustering algorithms like 0lowest ID algorithm, maximum degree algorithm etc. that does not perform well on the pitch of VANET. Adding to the merit of vehicular ad-hoc networks, they have a good hand in accident avoidance, congestion detection, information dissemination etc. This paper is a reviewed comparative study of various clustering algorithms researched in recent years hence making it an easy task to examine the best algorithm for clustering in a particular situation.

关键词： Vehicular ad-hoc networks (VANET) clustering cluster head clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of a global batch clustering with gradient descent and initial parameters in colour image classification

引用

IET IMAGE PROCESSING 2019年第1期13卷 161-174页

作者： Li, Peilin Lee, Sang-Heon Park, Jae-Sam Univ South Australia Sch Engn Mawson Lakes 5095 Australia Incheon Natl Univ Dept Elect Engn Incheon 22012 South Korea

This study addresses two issues from batch clustering using K-means algorithm in colour image classification application. One of the major issues is the drifting phenomenon in the batch clustering due to the stochastic nature of the clustering procedure. Also in literature, the initial parameter is important to direct the clustering algorithm converge to the proper local solution. In this study, a new algorithm is proposed to address these two issues in application. Recently, a research found that the principal component analysis (PCA) result directly indicates the membership of the clusters in K-means algorithm. Hence using this, the first part of the proposed algorithm shows the possibility to estimate the initial parameters accurately for K-means with a hierarchical manner of PCA solution. In addition, a gradient descent approach is used for the global batch clustering to reduce the drifting and hence speed up convergence in the refining stage. All necessary proofs and justifications are also provided. The evaluation study has shown that the proposed algorithm performs better than the original K-means clustering algorithms with various initial parameter estimation processes.

关键词： gradient methods parameter estimation image classification image colour analysis pattern clustering principal component analysis colour image classification application drifting phenomenon clustering procedure gradient descent approach global batch clustering initial parameter estimation processes clustering algorithm K-means algorithm PCA

来源：评论

学校读者我要写书评

暂无评论

Evaluation Design and Improvement on Higher Vocational College Teaching Evaluation System

Evaluation Design and Improvement on Higher Vocational Colle...

引用

作者： Guanli Huang Minjie Liu Hongli Zhou Office of Quality Management Beijing Polytechnic School of Automotive Engineering Beijing Polytechnic

In this paper, a large number of higher vocational college teaching data norm extraction with the appropriate model design and improvement. So as to improve the effectiveness of data analysis, it provides powerful classroom analysis support for classroom teaching evaluation in higher vocational *** concept of overall distribution is used to describe the overall data state by presenting the distribution diagram. The big data simulation analysis results can provide reference or basis for the construction of normal model resources of classroom teaching quality of teachers in vocational colleges as a whole.

关键词： clustering algorithm Teaching evaluation Constant Modulus Evaluation data analysis

来源：评论

学校读者我要写书评

暂无评论

Study on Composition Analysis and Identification of Ancient Glass Products

Study on Composition Analysis and Identification of Ancient ...

引用

作者： Nian Yang Xi'an Jiaotong University

Glass is the precious material evidence of the early trade of the ancient Silk Road, but the ancient glass is easily weathered by the influence of burial, and its composition ratio changes, which affects the correct judgment of its category. The study of the composition analysis and identification of ancient glass products is of great help to understand the social culture and foreign trade civilization at that time. This paper mainly studies the composition analysis and identification of ancient glassware, to evaluate, predict and classify the ancient glassware, this paper establishes a comprehensive evaluation model, using the chi-square test, K-means clustering model, decision tree model, Lasso regression and grey correlation degree test. It helps archaeologists to analyze and predict the correlation between the weathering degree of cultural relics and their attributes and chemical composition content, and according to the existing classification standards of cultural relics.A labelled subclassification scheme is formulated to identify the types of unknown cultural relics. At the same time, the correlation between the chemical components of different types of cultural relics was analyzed.

关键词： Ancient glass relics correlation analysis clustering algorithm decision tree

来源：评论

学校读者我要写书评

暂无评论

A Framework of Topological Interference Management and clustering for D2D Networks

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2019年第11期67卷 7856-7871页

作者： Doumiati, Salam Assaad, Mohamad Artail, Hassan Ali Amer Univ Beirut Dept Elect & Comp Engn Beirut 11072020 Lebanon CentraleSupelec TCL Chair 5G L2S UMR8506 F-91190 Gif Sur Yvette France

In this paper, we develop a joint clustering and topological interference management (TIM) framework for a device-to-device (D2D) network. This scheme divides the whole network into multiple groups, each served on a different frequency, and the interference within each group is managed by TIM, based only on the connectivity pattern and not on the instantaneous channel state information (CSI). To this end, we model TIM as a low-rank-matrix-completion problem (LRMC) problem and solve it using a novel and low-complex scheme based on semidefinite programming (SDP). As for the clustering part, we develop a clustering algorithm that is suited for the LRMC approach to solve TIM while building on the SDP relaxation of the maximum-k-cut algorithm, and extending it to account for each cluster's capacity. This clustering problem turns out to be a capacitated maximum-k-cut problem, for which we derive a relatively tight upper bound, that helps in determining the performance guarantee of many clustering algorithms. Simulation results show that the joint clustering-TIM can help, in some cases, improve the system degrees-of-freedom (DoF), especially in large D2D networks. Our proposed scheme also reduces the computation time of the LRMC-based TIM approach.

关键词： Topological interference management clustering algorithm D2D communication resource optimization interference cancellation

来源：评论

学校读者我要写书评

暂无评论

Insights on strategic air taxi network infrastructure locations using an iterative constrained clustering approach

引用

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW 2019年 128卷 470-505页

作者： Rajendran, Suchithra Zack, Joshua Univ Missouri Dept Ind & Mfg Syst Engn Columbia MO 65211 USA Univ Missouri Dept Mkt Columbia MO 65211 USA

Expected to launch globally in the forthcoming years, air taxis are brand-new aviation ridesharing services that will be provided by international logistic pioneers. This study is one of the first to estimate the demand for such a service and provide recommendations on the potential location of facilities to support this network operations. We adopt a two-phase approach: phase-1 estimates the demand for air taxi services by taking a subset of the regular taxi customers who are likely to avail this service, and phase-2 proposes a constrained clustering approach, with multimodal transportation-based warm start technique, to identify potential sites for locating infrastructures based on the estimated demand. We test the feasibility of the proposed approach using millions of real-life New York City taxi records. Results indicate that large facilities with a capacity of nearly 150 landings/hour have to be established in JFK International Airport and South Central Park, while smaller stops are required in World Trade Center, Washington Square and Allerton Ballfields. In addition, we evaluate the impact of the commuter's "willingness to fly" rate, demand fulfillment rate and time-cost tradeoffs. Our analysis shows that the percentage of time savings and "willingness to fly" rate did not significantly impact location decisions and the number of sites, while it is necessary to conduct an intense market study to determine on-road travel limits. Insights provided in this study can act as a decision support tool for any logistics company that is interested in venturing into the air taxi market.

关键词： Air taxi Soaring service Operating hubs Location decisions clustering algorithm Decision support tool

来源：评论

学校读者我要写书评

暂无评论

A Method for Quickly Establishing Personas 1

引用

1st International Conference on Artificial Intelligence in HCI (AI-HCI) Held as Part of the 22nd International Conference on Human-Computer Interaction (HCII)

作者： Hou, Wen-jun Yan, Xiang-yuan Liu, Jia-xin Beijing Univ Posts & Telecommun Sch Digital Media & Design Arts Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Network Syst & Network Culture Beijing 100876 Peoples R China

ISBN: (数字)9783030503345

ISBN: (纸本)9783030503338;9783030503345

The use of personas can help teams better understand the characteristics of users, which leads to more accurately discovery the problems and real pain points that users face. At present, there are two main ways to establish personas. One is to generate personas qualitatively or quantitatively through interviews, questionnaires, etc. These processes are related to the experiences of analysts and the statistical methods used, usually resulting in different conclusions and spending much time. The other is that the technical teams directly obtain the users' operation data on the products and use algorithm models to automatically generate personas. But this method is only suitable for mature products or existing functions, while the questionnaire method has nothing to do with mature products and functions. In this paper, we present persona segmentation through K-Means and PAM clustering algorithms in machine learning for questionnaire data, including mixed data, as an objective, quick, low-cost method for establishing personas. The method consists of four steps: first, design questionnaire. Second, transform the multi variables caused by multiple choice questions into a single variable. K-Means clustering algorithm is used for the continuous data of multi variables. The rule-based clustering method is used for the classified data. Then, cluster the processed data by PAM. The fourth step is to create personas, which are labeled in this paper. In the end, we demonstrate that the method is appropriate to create useful personas by machine evaluation and expert evaluation.

关键词： Personas Questionnaire clustering algorithm Machine learning Label

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：