检索结果-内蒙古大学图书馆

OPTIMAL ADAPTIVE k-means algorithm WITH DYNAMIC ADJUSTMENT OF LEARNING RATE

IEEE TRANSACTIONS ON NEURAL NETWORkS 1995年第1期6卷 157-169页

作者： CHINRUNGRUENG, C SEQUIN, CH Department of Electrical Engineering and Computer Sciences University of California Berkeley CA USA

Adaptive k-means clustering algorithms have been used in several artificial neural network architectures, such as radial basis function networks or feature-map classifiers, for a competitive partitioning of the input domain. This paper presents an enhancement of the traditional k-means algorithm. It approximates an optimal clustering solution with an efficient adaptive learning rate, which renders it usable even in situations where the statistics of the problem task varies slowly with time. This modification is based on the optimality criterion for the k-means partition stating that: all the regions in an optimal k-means partition have the same variations if the number of regions in the partition is large and the underlying distribution for generating input patterns Is smooth. The goal of equalizing these variations is introduced in the competitive function that assigns each new pattern vector to the ''appropriate'' region. To evaluate the optimal k-means algorithm, we first compare it to other k-means variants on several simple tutorial examples, then we evaluate it on a practical application: vector quantization of image data.

关键词： k-means algorithm image data Radial basis function networks learning rate partitions neural net architecture Optimal Self tuning

来源：评论

学校读者我要写书评

暂无评论

Data design and analysis based on cloud computing and improved k-means algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020年第4期39卷 5067-5074页

作者： Wu, Chunqiong Yu, Rongrui Yan, Bingwen Huang, Zhangshu Yu, Baoqin Yu, Yanliang Chen, Na Zhou, Xiukao Yango Univ Business Coll Fuzhou Fujian Peoples R China Fujian Univ Big Data Business Intelligence Engn Res Ctr Fuzhou Fujian Peoples R China Lanzhou Inst Technol Software Engn Inst Lanzhou Gansu Peoples R China

The IoT and Artificial intelligence, the amount of information generated on the Web site is increasing. The rise of the Hadoop distributed cloud computing platform (HDCCP) makes it possible to use multiple computing nodes for parallel computing to solve the performance problems of traditional serial algorithms. The purpose of this paper is to study data design based on cloud computing and improved k-means algorithm (kMA). This paper deeply researches Hadoop distributed cloud computing platform and clustering algorithm and other related technologies, and designs and implements a cluster analysis system (CAS) based on HP. And through an in-depth analysis of the problems existing in the kMA, an improved scheme based on the HDP is designed. The experimental environment was conFig.d with the cluster analysis system implemented. Finally, the improved kMPA was tested experimentally from four directions: convergence speed, acceleration ratio, initialization sampling rate, and accuracy rate. We can see the experimental results that the CAS based on the HDCCP designed in this paper can provide efficient and configurable cluster analysis services. In this paper, the correct rate is 90.7%.

关键词： Cloud computing k-means algorithm cluster analysis hadoop platform data design

来源：评论

学校读者我要写书评

暂无评论

Weight selection in W-k-means algorithm with an application in color image segmentation

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2011年第2期62卷 668-676页

作者： Hung, Wen-Liang Chang, Yen-Chang Lee, E. Stanley Natl Hsinchu Univ Educ Dept Appl Math Hsinchu 30013 Taiwan Kansas State Univ Dept Ind & Mfg Syst Engn Manhattan KS 66506 USA

In this paper, a weight selection procedure in the W-k-means algorithm is proposed based on the statistical variation viewpoint. This approach can solve the W-k-means algorithm's problem that the clustering quality is greatly affected by the initial value of weight. After the statistics of data, the weights of data are designed to provide more information for the character of W-k-means algorithm so as to improve the precision. Furthermore, the corresponding computational complexity is analyzed as well. We compare the clustering results of the W-k-means algorithm with the different initialization methods. Results from color image segmentation illustrate that the proposed procedure produces better segmentation than the random initialization according to Liu and Yang's (1994) evaluation function. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Coefficient of variation Color image segmentation Entropy k-means algorithm W-k-means algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast modified global k-means algorithm for incremental cluster construction

引用

PATTERN RECOGNITION 2011年第4期44卷 866-876页

作者： Bagirov, Adil M. Ugon, Julien Webb, Dean Univ Ballarat Ctr Informat & Appl Optimizat Grad Sch Informat Technol & Math Sci Ballarat Vic 3353 Australia

The k-means algorithm and its variations are known to be fast clustering algorithms. However, they are sensitive to the choice of starting points and are inefficient for solving clustering problems in large datasets. Recently, incremental approaches have been developed to resolve difficulties with the choice of starting points. The global k-means and the modified global k-means algorithms are based on such an approach. They iteratively add one cluster center at a time. Numerical experiments show that these algorithms considerably improve the k-means algorithm. However, they require storing the whole affinity matrix or computing this matrix at each iteration. This makes both algorithms time consuming and memory demanding for clustering even moderately large datasets. In this paper, a new version of the modified global k-means algorithm is proposed. We introduce an auxiliary cluster function to generate a set of starting points lying in different parts of the dataset. We exploit information gathered in previous iterations of the incremental algorithm to eliminate the need of computing or storing the whole affinity matrix and thereby to reduce computational effort and memory usage. Results of numerical experiments on six standard datasets demonstrate that the new algorithm is more efficient than the global and the modified global k-means algorithms. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Minimum sum-of-squares clustering Nonsmooth optimization k-means algorithm Global k-means algorithm

来源：评论

学校读者我要写书评

暂无评论

A fast near-optimum block truncation coding method using a truncated k-means algorithm and inter-block correlation

引用

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS 2011年第6期65卷 576-581页

作者： Yang, Yan Chen, Qiqiang Wan, Yi Lanzhou Univ Inst Signals & Informat Proc Lanzhou 730000 Peoples R China Lanzhou Jiaotong Univ Lanzhou 730070 Peoples R China

Block truncation coding (BTC) is an efficient image compression method which finds application in diverse fields. The basic problem can be viewed as a two-level quantization process. However, efficient ways for optimal threshold determination have not been discovered so far. We propose a fast BTC algorithm based on a truncated k-means algorithm, utilizing the image inter-block correlation and the fact that k-means algorithm converges very fast in this case. This produces near-optimum solution with significantly improved speed over other methods. Simulation results confirm such advantages. (C) 2010 Elsevier GmbH. All rights reserved.

关键词： Block truncation coding Quantization k-means algorithm Image content correlation

来源：评论

学校读者我要写书评

暂无评论

Comments on "Modified k-means algorithm for vector quantizer design"

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2000年第11期9卷 1964-1967页

作者： Paliwal, kk Ramasubramanian, V Griffith Univ Sch Microelect Engn Brisbane Qld 4111 Australia Tata Inst Fundamental Res Bombay 400005 Maharashtra India

Recently a modified k-means algorithm for vector quantization design has been proposed where the codevector updating step is as follows: new codevector = current codevector + scale factor (new centroid - current codevector), This algorithm uses a fixed value for the scale factor. In this paper, we propose the use of a variable scale factor which is a function of the iteration number. For the vector quantization of image data, we show that it offers faster convergence than the modified k-means algorithm with a fixed scale factor, without affecting the optimality of the codebook.

关键词： faster convergence k-means algorithm vector quantization

来源：评论

学校读者我要写书评

暂无评论

An improved k-means algorithm for underwater image background segmentation

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第14期80卷 21059-21083页

作者： Chen, Wei He, Cenyu Ji, Chunlin Zhang, Meiying Chen, Siyu Nanjing Inst Technol Coll Innovat & Entrepreneurship Ind Ctr Nanjing 211167 Peoples R China Shenzhen Kuang Chi Space Technol Co Ltd Shenzhen 518000 Peoples R China Shenzhen Kuang Chi Inst Adv Technol Shenzhen 518000 Peoples R China Tech Univ Munich Dept Elect & Comp Engn D-80333 Munich Germany

Conventional algorithms fail to obtain satisfactory background segmentation results for underwater images. In this study, an improved k-means algorithm was developed for underwater image background segmentation to address the issue of improper k value determination and minimize the impact of initial centroid position of grayscale image during the gray level quantization of the conventional k-means algorithm. A total of 100 underwater images taken by an underwater robot were sampled to test the aforementioned algorithm in respect of background segmentation validity and time cost. The k value and initial centroid position of grayscale image were optimized. The results were compared to the other three existing algorithms, including the conventional k-means algorithm, the improved Otsu algorithm, and the Canny operator edge extraction method. The experimental results showed that the improved k-means underwater background segmentation algorithm could effectively segment the background of underwater images with a low color cast, low contrast, and blurred edges. Although its cost in time was higher than that of the other three algorithms, it none the less proved more efficient than the time-consuming manual segmentation method. The algorithm proposed in this paper could potentially be used in underwater environments for underwater background segmentation.

关键词： Underwater image Image segmentation Background segmentation k-means algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on fast identification technology of forged fingerprints based on the improved k-means algorithm

引用

INTERNATIONAL JOURNAL OF BIOMETRICS 2021年第1期13卷 17-29页

作者： Ren, Zhao-ting Northwest Minzu Univ Dept Expt Teaching Lanzhou 730030 Peoples R China

In order to overcome the low accuracy of the traditional method, a fast identification method based on the improved k-mean algorithm is proposed. Spatial grid block model is constructed to extract the fingerprint texture features and then the fingerprint profile features are detected using the edge outline extraction method. The kalman fusion method is used to reconstruct fingerprint information. Using the neighbourhood distributed retrieval method, fingerprint image feature fusion is realised and the texture feature extraction model for forged fingerprints is established. The k-means clustering method is used for fingerprint feature clustering to realise fast identification of forged fingerprints. Experimental results show that the identification accuracy of this method is higher than 0.85, and the identification stability is good. The signal-to-noise ratio of fingerprint images is always between 25.3 dB and 82.3 dB, and the imaging quality is high, indicating that this method can realise fast and accurate identification of forged fingerprints.

关键词： k-means algorithm forged fingerprint fast identification feature extraction texture

来源：评论

学校读者我要写书评

暂无评论

An empirical comparison of four initialization methods for the k-means algorithm

引用

PATTERN RECOGNITION LETTERS 1999年第10期20卷 1027-1040页

作者： Peña, JM Lozano, JA Larrañaga, P Univ Basque Country Dept Comp Sci & Artificial Intelligence Intelligent Syst Grp E-20080 San Sebastian Spain

In this paper, we aim to compare empirically four initialization methods for the k-means algorithm: random, Forgy, MacQueen and kaufman. Although this algorithm is known for its robustness, it is widely reported in the literature that its performance depends upon two key points: initial clustering and instance order. We conduct a series of experiments to draw up tin terms of mean, maximum, minimum and standard deviation) the probability distribution of the square-error values of the final clusters returned by the k-means algorithm independently on any initial clustering and on any instance order when each of the four initialization methods is used. The results of our experiments illustrate that the random and the kaufman initialization methods outperform the rest of the compared methods as they make the k-means more effective and more independent on initial clustering and on instance order. In addition, we compare the convergence speed of the k-means algorithm when using each of the four initialization methods. Our results suggest that the kaufman initialization method induces to the k-means algorithm a more desirable behaviour with respect to the convergence speed than the random initialization method. (C) 1999 Elsevier Science B.V. All rights reserved.

关键词： k-means algorithm k-means initialization partitional clustering genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

IDENTIFICATION OF JUVENILE AND MATURE WOOD ZONES IN STEMS OF EUROPEAN LARCH (LARIX DECIDUA MILL.) USING A k-means algorithm

引用

WOOD RESEARCH 2012年第4期57卷 545-559页

作者： Nawrot, Marcin Pazdrowski, Witold Szymanski, Marek Jedraszak, Agnieszka Walkowiak, Ryszard Borysiak, Slawomir Poznan Univ Life Sci Dept Forest Utilisat PL-60625 Poznan Poland Poznan Univ Life Sci Dept Math & Stat Methods Lab Biometry PL-60627 Poznan Poland Poznan Univ Tech Inst Chem Technol & Engn PL-60627 Poznan Poland

The paper presents assumptions and results recorded thanks to the application of a novel method to identify juvenile and mature wood zones in stems of forest trees based on a k-means algorithm. The algorithm showed the boundary between analysed types of wood on the basis of input data based on macroscopic structure of wood, i.e. the width of the annual ring, the proportion of late wood in the annual ring and the length of the ray of the annual ring (the location of the annual ring on the ray). Analyses conducted using this method indicated that juvenile wood in 24 European larches covers from 9 to 22 annual rings located around the pith (on average 13). The applied method was verified by changing the degree of crystallinity of cellulose determined at breast height of 3 mean sample trees. Boundaries indicated by the algorithm coincided with high accuracy with places where the course of changes in values of the degree of crystallinity at successive annual rings started to be similar.

关键词： Juvenile wood k-means algorithm degree of crystallinity of cellulose Larix decidua

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：