Efficient multi-view clustering networks

Applied Intelligence - In the last decade, deep learning has made remarkable progress on multi-view clustering (MvC), with existing literature adopting a broad target to guide the network learning...     

Adapting k-means for supervised clustering

k-means is traditionally viewed as an algorithm for the unsupervised clustering of a heterogeneous population into a number of more homogeneous groups of objects. However, it is not necessarily guaranteed to group the same types (classes) of objects together. In such cases, some supervision is needed to partition objects which have the same label into one cluster. This paper demonstrates how the popular k-means clustering algorithm can be profitably modified to be used as a classifier algorithm. The output field itself cannot be used in the clustering but it is used in developing a suitable metric defined on other fields. The proposed algorithm combines Simulated Annealing with the modified k-means algorithm. We apply the proposed algorithm to real data sets, and compare the output of the resultant classifier to that of C4.5.     

基于机器学习的工业互联网入侵检测综述

DBSCAN(density-based spatial clustering of applications with noise)是应用最广的密度聚类算法之一. 然而,它时间复杂度过高(O(n²)),无法处理大规模数据. 因而,对它进行加速成为一个研究热点,众多富有成效的工作不断涌现. 从加速目标上看,这些工作大体上可分为减少冗余计算和并行化两大类;就具体加速手段而言,可分为6个主要类别：基于分布式、基于采样化、基于近似模糊、基于快速近邻、基于空间划分以及基于GPU加速技术. 根据该分类,对现有工作进行了深入梳理与交叉比较,发现采用多重技术的融合加速算法优于单一加速技术;近似模糊化、并行化与分布式是当前最有效的手段;高维数据仍然难以应对. 此外,对快速化DBSCAN算法在多个领域中的应用进行了跟踪报告. 最后,对本领域未来的方向进行了展望.

     

基于萤火虫优化的加权k-means算法*

针对传统k均值算法易受初始聚类中心和异常数据的影响等缺陷,利用萤火虫优化算法全局搜索能力强、收敛速度快的优势,对k均值算法的初始聚类中心进行优化,并通过引用一种加权的欧氏距离,减少异常数据等不确定因素带来的不良影响,提出了一种基于萤火虫优化的加权k均值算法。该算法在提升聚类性能的同时,有效增强了算法的收敛速度。在实验阶段,通过UCI数据集中的几组数据对该算法进行了分类实验及有效性测试,实验结果充分表明了该算法的有效性及优越性。     

具有自适应参数的粗糙k-means聚类算法

粗糙聚类是不确定聚类算法中一种有效的聚类算法,这里通过分析粗糙k-means算法,指出了其中3个参数w_l,w_u和ε设置时存在的缺点,提出了一种自适应粗糙k-means聚类算法,该算法能进一步优化粗糙k-means的聚类效果,降低对“噪声”的敏感程度,最后通过实验验证了算法的有效性。     

Accurate,dense and shading-aware multi-view stereo reconstruction using metaheuritic optimization

Among the modern means of 3D geometry creation that exist in the literature, there are the Multi-View Stereo (MVS) reconstruction methods that received much attention from the research community and the multimedia industry. In fact, several methods showed that it is possible to recover geometry only from images with reconstruction accuracies paralleling that of excessively expensive laser scanners. The majority of these methods perform on images such as online community photo collection and estimate the surface position with its orientation by minimizing a matching cost function defined over a small local region. However, these datasets not only they are large but also contain more challenging scenes setups with different photometric effects; therefore fine-grained details of an object’s surface cannot be captured. This paper presents a robust multi-view stereo method based on metaheuristic optimization namely the Particle Swarm Optimization (PSO) in order to find the optimal depth, orientation, and surface roughness. To deal with the various shading and stereo mismatch problems caused by rough surfaces, shadows, and interreflections, we propose to use a robust matching/energy function which is a combination of two similarity measurements. Finally, our method computes individual depth maps that can be merged into compelling scene reconstructions. The proposed method is evaluated quantitatively using well-known Middlebury datasets and the obtained results show a high completeness score and comparable accuracy to those of the current top performing algorithms.

     

Consistent auto-weighted multi-view subspace clustering

Pattern Analysis and Applications - Because the data in practical applications usually satisfy the assumption of mixing subspaces and contain multiple features, multi-view subspace clustering has...     

基于参考区域的k-means文本聚类算法

k-means是目前常用的文本聚类算法,该算法的主要缺点需要人工指定聚类的最终个数k及相应的初始中心点.针对这些缺点,提出一种基于参考区域的初始化方法,自动生成k-means的初始化分区,并且在参考区域的生成过程中,设计一种求最大斜率(绝对值)的方法确定自动阈值.理论分析和实验结果表明,该改进算法能有效的提高文本聚类的精度,且具有可行的效率.     

Large-scale k-means clustering with user-centric privacy-preservation

A k-means clustering with a new privacy-preserving concept, user-centric privacy preservation, is presented. In this framework, users can conduct data mining using their private information by storing them in their local storage. After the computation, they obtain only the mining result without disclosing private information to others. In most cases, the number of parties that can join conventional privacy-preserving data mining has been assumed to be only two. In our framework, we assume large numbers of parties join the protocol; therefore, not only scalability but also asynchronism and fault-tolerance is important. Considering this, we propose a k-mean algorithm combined with a decentralized cryptographic protocol and a gossip-based protocol. The computational complexity is O(log n) with respect to the number of parties n, and experimental results show that our protocol is scalable even with one million parties.     

一种改进的粗k 均值聚类算法

Lingras提出的粗K均值聚类算法易受随机初始聚类中心和离群点的影响,可能出现一致性和无法收敛的聚类结果.对此,提出一种改进的粗K均值算法,选择潜能最大的K个对象作为初始的聚类中心,根据数据对象与聚类中心的相对距离来确定其上下近似归属,使边界区域的划分更合理.定义了广义分类正确率,该指标同时考虑了下近似集和边界区域中的对象,评价算法性能更准确.仿真实验结果表明,该算法分类正确率高,收敛速度快,能够克服离群点的不利影响.     

一种新的k-means聚类中心选取算法

在2010年提出已有的k-means聚类中心选取算法的基础上进行改进。通过计算样本间的距离求出每个样本的密度参数,选取最大密度参数值所对应的样本作为初始聚类中心。当最大密度参数值不惟一时,提出合理选取最大密度参数值的解决方案,依次求出k个初始聚类中心点,由此提出了一种新的k-means聚类中心选取算法。实验证明,提出的算法与对比算法相比具有更高的准确率。     

可验证的隐私保护k-means聚类方案

针对现有云外包隐私保护k-means聚类方案存在的效率不高,以及当云服务器不可信或遭受黑客攻击时返回不合理聚类结果的问题,提出了一种可应用于多方隐私保护场景的云外包可验证隐私保护k-means聚类方案.首先,提出了一种适用于云外包场景的改进的聚类初始化方法,从而有效提高算法的迭代效率;然后,利用乘法三元组技术来设计安全...     

一种新颖的多视点图像规正算法

在多视点图像系统中,由于场景光照或相机标定的原因,通常会导致同一对象在不同视点位置颜色外表的不一致。传统的亮度补偿算法难以有效地解决这个问题。基于Retinex颜色恒常性理论,提出了一种新颖的多视点图像规正算法,通过直方图均衡化、Retinex处理和颜色恢复手段,提取出反映物体本质特征的反射光系数来消除不一致光照的影响,在增强单视点图像对比度的同时,将视点间图像的颜色规正到一致的水平。     

Incomplete multi-view clustering with multiple imputation and ensemble clustering

Applied Intelligence - Multi-view clustering is an important and challenging task in machine learning and data mining. In the past decade, this topic attracted much attention and there have been...     

A combination of k-means clustering and entropy filtering for band selection and classification in hyperspectral images

Hyperspectral images usually have large volumes of data comprising hundreds of spectral bands. Removal of redundant bands can both reduce computational time and improve classification performance. This work proposes and analyses a band-selection method based on the k-means clustering strategy combined with a classification approach using entropy filtering. Experimental results in different terrain images show that our method can significantly reduce the number of bands while maintaining an accurate classification.     

Characterising and understanding emission sources using bivariate polar plots and k-means clustering

This paper develops the idea of bivariate polar plots as a method for source detection and characterisation. Bivariate polar plots provide a graphical method for showing the joint wind speed, wind direction dependence of air pollutant concentrations. Bivariate polar plots provide an effective graphical means of discriminating different source types and characteristics. In the current work we apply k-means clustering techniques directly to bivariate polar plots to identify and group similar features. The technique is analogous to clustering applied to back trajectories at the regional scale. When applied to data from a monitoring site with high source complexity it is shown that the technique is able to identify important clusters in ambient monitoring data that additional analysis shows to exhibit different source characteristics. Importantly, this paper links identified clusters to known emission characteristics to confirm the inferences made in the analysis. The approaches developed should have wide application to the analysis of air pollution monitoring data and have been made freely available as part of the openair R package.     

Scalable multi-view clustering with graph filtering

Neural Computing and Applications - With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years. Most existing multi-view methods operate in...     

一种k-means聚类的案例检索算法

针对CBR系统中案例检索算法存在的问题,根据k-means算法思想,将案例库进行聚类,在聚类基础上设计了一个案例检索算法。分析了样本案例的选取规则,重点论述了案例检索算法。根据实验结果表明,该方法能够有效地提高案例检索结果的召回率及案例检索效率。     

Discrete range clustering using Monte Carlo methods

For automatic obstacle avoidance guidance during rotorcraft low altitude flight a reliable model of the nearby environment is needed. Such a model may be constructed by applying surface fitting techniques to the dense range map obtained by active sensing using radars. However, for covertness passive sensing techniques using electro-optic sensors is desirable. As opposed to the dense range map obtained via active sensing, passive sensing algorithms produce reliable range at sparse locations and, therefore, surface fitting techniques to fill the gaps in the range measurement are not directly applicable. Both, for automatic guidance and as a display for aiding the pilot, these discrete ranges need to be grouped into sets which correspond to objects in the nearby environment. The focus of this paper is on using Monte Carlo methods for clustering range points into meaningful groups. We compare three different approaches and present results of application of these algorithms to an image sequence acquired by onboard cameras during a helicopter flight. Starting with an initial grouping, these algorithms are iteratively applied with a new group creation algorithm to determine the optimal number of groups and the optimal group membership. The results indicate that the simulated annealing methods do not offer any significant advantage over the basic Monte Carlo method for this discrete optimization problem