Texture segmentation by frequency-sensitive elliptical competitive learning

In this paper, a new learning algorithm is proposed with the purpose of texture segmentation. The algorithm is a competitive clustering scheme with two specific features: elliptical clustering is accomplished by incorporating the Mahalanobis distance measure into the learning rules and under-utilization of smaller clusters is avoided by incorporating a frequency-sensitive term. In the paper, an efficient learning rule that incorporates these features is elaborated. In the experimental section, several experiments demonstrate the usefulness of the proposed technique for the segmentation of textured images. On the compositions of textured images, Gabor filters were applied to generate texture features. The segmentation performance is compared to k-means clustering with and without the use of the Mahalanobis distance and to the ordinary competitive learning scheme. It is demonstrated that the proposed algorithm outperforms the others. A fuzzy version of the technique is introduced, and experimentally compared with fuzzy versions of the k-means and competitive clustering algorithms. The same conclusions as for the hard clustering case hold.     

Data clustering with size constraints

Data clustering is an important and frequently used unsupervised learning method. Recent research has demonstrated that incorporating instance-level background information to traditional clustering algorithms can increase the clustering performance. In this paper, we extend traditional clustering by introducing additional prior knowledge such as the size of each cluster. We propose a heuristic algorithm to transform size constrained clustering problems into integer linear programming problems. Experiments on both synthetic and UCI datasets demonstrate that our proposed approach can utilize cluster size constraints and lead to the improvement of clustering accuracy.     

Hybrid robust approach for TSK fuzzy modeling with outliers

This study proposes a hybrid robust approach for constructing Takagi–Sugeno–Kang (TSK) fuzzy models with outliers. The approach consists of a robust fuzzy C-regression model (RFCRM) clustering algorithm in the coarse-tuning phase and an annealing robust back-propagation (ARBP) learning algorithm in the fine-tuning phase. The RFCRM clustering algorithm is modified from the fuzzy C-regression models (FCRM) clustering algorithm by incorporating a robust mechanism and considering input data distribution and robust similarity measure into the FCRM clustering algorithm. Due to the use of robust mechanisms and the consideration of input data distribution, the fuzzy subspaces and the parameters of functions in the consequent parts are simultaneously identified by the proposed RFCRM clustering algorithm and the obtained model will not be significantly affected by outliers. Furthermore, the robust similarity measure is used in the clustering process to reduce the redundant clusters. Consequently, the RFCRM clustering algorithm can generate a better initialization for the TSK fuzzy models in the coarse-tuning phase. Then, an ARBP algorithm is employed to obtain a more precise model in the fine-tuning phase. From our simulation results, it is clearly evident that the proposed robust TSK fuzzy model approach is superior to existing approaches in learning speed and in approximation accuracy.     

知识迁移的极大熵聚类算法及其在纹理图像分割中的应用

本文研究了一种新型的基于知识迁移的极大熵聚类技术。拟解决两大挑战性问题:1）如何从源域中选择合适的知识对目标域进行迁移学习以最终强化目标域的聚类性能;2）若存在源域聚类数与目标域聚类数不一致的情况时,该如何进行迁移聚类。为此提出一种全新的迁移聚类机制,即基于聚类中心的中心匹配迁移机制。进一步将该机制与经典极大熵聚类算法相融合提出了基于知识迁移的极大熵聚类算法（KT-MEC）。实验表明,在不同迁移场景下的纹理图像分割应用中,KT-MEC算法较很多现有聚类算法具有更高的精确度和抗噪性。     

Clustering semantically heterogeneous distributed aggregate databases

Databases developed independently in a common open distributed environment may be heterogeneous with respect to both data schema and the embedded semantics. Managing schema and semantic heterogeneities brings considerable challenges to learning from distributed data and to support applications involving cooperation between different organisations. In this paper, we are concerned mainly with heterogeneous databases that hold aggregates on a set of attributes, which are often the result of materialised views of native large-scale distributed databases. A model-based clustering algorithm is proposed to construct a mixture model where each component corresponds to a cluster which is used to capture the contextual heterogeneity among databases from different populations. Schema heterogeneity, which can be recast as incomplete information, is handled within the clustering process using Expectation-Maximisation estimation and integration is carried out within a clustering iteration. Our proposed algorithm resolves the schema heterogeneity as part of the clustering process, thus avoiding transformation of the data into a unified schema. Results of algorithm evaluation on classification, scalability and reliability, using both real and synthetic data, demonstrate that our algorithm can achieve good performance by incorporating all of the information from available heterogeneous data. Our clustering approach has great potential for scalable knowledge discovery from semantically heterogeneous databases and for applications in an open distributed environment, such as the Semantic Web.     

一种基于萤火虫算法的模糊聚类方法

针对模糊C-均值聚类对初始值敏感、容易陷入局部最优的缺陷,提出了一种基于萤火虫算法的模糊聚类方法。该方法结合萤火虫算法良好的全局寻优能力和模糊C-均值算法的较强的局部搜索特性,用萤火虫算法优化搜索FCM的聚类中心,利用FCM进行聚类,有效地克服了模糊C-均值聚类的不足,同时增强了萤火虫算法的局部搜索能力。实验结果表明,该算法具有很好的全局寻优能力和较快的收敛速度,能有效地收敛于全局最优解,具有较好的聚类效果。     

基于多示例的K-means聚类学习算法

多示例学习是继监督学习、非监督学习、强化学习后的又一机器学习框架。将多示例学习和非监督学习结合起来,在传统非监督聚类算法K-means的基础上提出MIK-means算法,该算法利用混合Hausdorff距离作为相似测度来实现数据聚类。实验表明,该方法能够有效揭示多示例数据集的内在结构,与K-means算法相比具有更好的聚类效果。     

自适应图学习诱导的子空间聚类

子空间聚类是机器学习领域的热门研究课题。它根据数据的潜在子空间对数据进行聚类。受多视图学习中协同训练算法的启发,提出一个自适应图学习诱导的子空间聚类算法,该算法首先将单视图数据多视图化,再利用不同视图的信息迭代更新图正则化项,得到更能反映聚类性能的块对角关联矩阵,从而更准确地描述数据聚类结果。在四个标准数据集上与其他聚类算法进行对比实验,实验结果显示该方法具有更好的聚类性能。     

Music Clustering With Features From Different Information Sources

Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying “similar” artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.      

Unsupervised feature selection using clustering ensembles and population based incremental learning algorithm

This paper describes a novel feature selection algorithm for unsupervised clustering, that combines the clustering ensembles method and the population based incremental learning algorithm. The main idea of the proposed unsupervised feature selection algorithm is to search for a subset of all features such that the clustering algorithm trained on this feature subset can achieve the most similar clustering solution to the one obtained by an ensemble learning algorithm. In particular, a clustering solution is firstly achieved by a clustering ensembles method, then the population based incremental learning algorithm is adopted to find the feature subset that best fits the obtained clustering solution. One advantage of the proposed unsupervised feature selection algorithm is that it is dimensionality-unbiased. In addition, the proposed unsupervised feature selection algorithm leverages the consensus across multiple clustering solutions. Experimental results on several real data sets demonstrate that the proposed unsupervised feature selection algorithm is often able to obtain a better feature subset when compared with other existing unsupervised feature selection algorithms.     

基于竞争学习的K质心组合聚类算法

K-Means算法的聚类结果对初始簇的选择非常敏感,通常获得的是局部最优解而非全局最优解.为此,在K-Means聚类算法基础上,引入组合聚类和竞争学习概念,提出一种基于竞争学习的K质心组合聚类算法CLK-Centroid.该算法采用竞争学习策略计算簇的质心,以适应噪声数据和分布异常数据的要求,使用组合聚类策略提高聚类的...     

多阈值图像分割的模糊粒子群优化算法

把粒子群算法应用到多阈值图像分割中,结合已有的模糊C-均值聚类法提出了一种基于模糊技术的粒子群优化多阈值图像分割算法。FCM聚类算法是一种局部搜索算法,对初始值较为敏感,容易陷入局部极小值而不能得到全局最优解。PSO算法是一种基于群体的具有全局寻优能力的优化方法。将FCM聚类算法和PSO算法结合起来,将FCM聚类算法的聚类准则函数作为PSO算法中的粒子适应度函数。仿真实验表明新算法在最大熵评判准则下能够得到最优阈值。     

基于粗糙集与差分免疫模糊聚类算法的图像分割

提出了基于粗糙集模糊聚类与差分免疫克隆聚类的图像分割算法。该算法在差分免疫克隆聚类算法的基础上,通过引入粗糙集模糊聚类,将差分免疫克隆聚类算法中的硬聚类变成模糊聚类,从而获得更丰富的聚类信息。具体来说,由于粗糙集的优势是处理不确定的数据,因此,加入粗糙集模糊聚类后更有利于算法解决不确定性问题。通过对9幅图像分割实验结果与4种算法的对比,验证了该算法在聚类性能稳定性方面的优越性,结果还同时证明了该算法具有更高的分割正确率和更好的分割结果。     

Suppressed possibilistic c-means clustering algorithm

The possibilistic c-means (PCM) clustering algorithm always suffers from a coincident clustering problem since it relaxes the probabilistic constraint in the fuzzy c-means (FCM) clustering algorithm. In this paper, to overcome the shortcoming of the PCM, a novel suppressed possibilistic c-means (S-PCM) clustering algorithm by introducing a suppressed competitive learning strategy into the PCM so as to improve the between-cluster relationships is proposed. Specifically, in the updating process the new algorithm searches for the biggest typicality which is regarded as winner by a competitive mechanism. Then it suppresses the non-winner typicalities with a suppressed rate which is used to control the learning strength. Moreover, the parameter setting problems of the suppressed rate and the penalty parameter in the S-PCM are also discussed in detail. In addition, the suppressed competitive learning strategy is still introduced into the possibilistic Gustafson–Kessel (PGK) clustering algorithm and a novel suppressed possibilistic Gustafson–Kessel (S-PGK) clustering model is proposed, which is more applicable to the ellipsoidal data clustering. Finally, experiments on several synthetic and real datasets with noise injection demonstrate the effectiveness of the proposed algorithms.     

基于结合空间信息的FCM聚类的分水岭图像分割

提出了一种分水岭变换和结合空间信息的FCM聚类相结合的图像分割方法。方法采用基于图论的结合区域特征信息和空间信息的距离度量,以分水岭变换得到的图像分割小区域为节点构建一个连通加权图,通过计算图上不同节点之间的最短路径来度量不同区域之间的相似程度,从而实现过分割小区域的合并。该方法综合考虑了区域的特征之间的差异和空间位置的差异,与传统的FCM聚类方法在特征空间进行聚类相比,具有较强的噪声抑制能力。图像分割的实验结果证明了该算法的可行性和有效性。     

具备跨源域学习能力的模糊聚类算法研究

针对传统迁移学习聚类算法因单一源域到单一目标域且两者类别数必须一致的约束而达不到良好的聚类效果的问题,本文提出了一种跨源域学习的聚类算法,该算法具有三大优点：1) 该算法不仅扩大源域数目且取消了源域类别数的限定,算法可以自适应选择源域进行学习,因此算法的迁移学习能够得到较大的提升;2)由于算法所利用的源域知识不会暴露原数据,因此算法具有良好的源域数据隐私保护性;3)通过调节平衡参数可以使算法退化为传统的聚类算法,因此该算法的聚类性能是有所保障的。通过在模拟数据集和真实数据集上的实验,验证了文中算法较之现有迁移学习聚类算法具有更好的迁移能力,且聚类性能及鲁棒性也有较大的提升。     

A reinforcement learning approach to online clustering

A general technique is proposed for embedding online clustering algorithms based on competitive learning in a reinforcement learning framework. The basic idea is that the clustering system can be viewed as a reinforcement learning system that learns through reinforcements to follow the clustering strategy we wish to implement. In this sense, the reinforcement guided competitive learning (RGCL) algorithm is proposed that constitutes a reinforcement-based adaptation of learning vector quantization (LVQ) with enhanced clustering capabilities. In addition, we suggest extensions of RGCL and LVQ that are characterized by the property of sustained exploration and significantly improve the performance of those algorithms, as indicated by experimental tests on well-known data sets.     

基于PSO的模糊聚类算法

提出了一种基于模糊C-均值算法和粒子群算法的混合聚类算法。该算法结合PSO的全局搜索和FCM局部搜索的特点,将PSO优化聚类结果作为后续FCM算法的初始值,有效地克服了FCM对初始值敏感、易陷入局部最优和PSO算法局部搜索较弱的问题,同时增强了跳出局部最优的能力。实验表明,新算法得到的目标函数值更小,并能减小分类错误率,聚类效果优于单一使用FCM或PSO。     

一种新的带模糊权的粗糙聚类算法

针对粗糙聚类算法缺乏对数据比例变换的鲁棒性的问题，在粗糙聚类的框架下融合模糊聚类的思想，将临界区域中对象的模糊隶属度作为它们对于聚类中心调整的作用权值，得到一种带有模糊权的粗糙聚类算法（fuzzy weighing rough clustering algorithm, FWRCA）．实验表明，该算法不仅对于数据的比例变化具有鲁棒性，且在一定程度上克服了粗糙C均值聚类算法对划分阈值ε的敏感性，在性能上优于传统粗糙C均值聚类算法(如RCMCA)，可应用于水电工程科学等以原型模型为研究手段并有大量需做比例变换的观测数据的领域．     

Spectral clustering based on similarity and dissimilarity criterion

The clustering assumption is to maximize the within-cluster similarity and simultaneously to minimize the between-cluster similarity for a given unlabeled dataset. This paper deals with a new spectral clustering algorithm based on a similarity and dissimilarity criterion by incorporating a dissimilarity criterion into the normalized cut criterion. The within-cluster similarity and the between-cluster dissimilarity can be enhanced to result in good clustering performance. Experimental results on toy and real-world datasets show that the new spectral clustering algorithm has a promising performance.