Fuzzy weighted C-ordered means clustering algorithm

Advances made to the traditional clustering algorithms solves the various problems such as curse of dimensionality and sparsity of data for multiple attributes. The traditional H-K clustering algorithm can solve the randomness and apriority of the initial centers of K-means clustering algorithm. But when we apply it to high dimensional data it causes the dimensional disaster problem due to high computational complexity. All the advanced clustering algorithms like subspace and ensemble clustering algorithms improve the performance for clustering high dimension dataset from different aspects in different extent. Still these algorithms will improve the performance form a single perspective. The objective of the proposed model is to improve the performance of traditional H-K clustering and overcome the limitations such as high computational complexity and poor accuracy for high dimensional data by combining the three different approaches of clustering algorithm as subspace clustering algorithm and ensemble clustering algorithm with H-K clustering algorithm.

Analysis of Clustering Algorithms for MR Image Segmentation using IQI

Subspace clustering based on latent low rank representation with Frobenius norm minimization

Dense community detection in multi-valued attributed networks

Subspace clustering is the task of grouping objects based on mutual similarity in subspaces of the full-dimensional space.<br/>The INSCY algorithm extends the well-known density-based clustering algorithm DBSCAN. It finds dimensionality-unbiased non-redundant subspace clusters using a tree structure to speed up the processing of subspaces. Still, finding density-based clusters in all subspaces implies an exponential search space in the number of dimensions. Thus, the running time of INSCY is still measured in hours on even small datasets of 2000 points. For larger datasets, it becomes prohibitively expensive.<br/><br/>To benefit from INSCY for real-world sized datasets, we propose a novel GPU-parallel approach that runs on standard graphics cards. To utilize the many cores of the GPU, we need new algorithmic strategies that fit the computational model of the GPU. While the GPU provides a large number of threads, traditional algorithms incur diverging threads and poor memory alignment, both of which lead to idle time and poor runtime performance. In INSCY, extracting subspace regions from the SCY-tree structure and the density-based clustering of regions itself are thus unfit for the GPU. <br/><br/>Our novel GPU-friendly algorithm GPU-INSCY computes the same subspace clustering as INSCY at dramatically reduced runtimes. <br/>To achieve this, we devise a restructured SCY-tree index-structure and associated operations for the GPU, as well as a GPU-parallel density-based subspace clustering.<br/><br/>We experimentally show that GPU-INSCY scales well with the size of the dataset and the number of dimensions, and improves the running time of INSCY by a factor of several thousand for large datasets of high dimensionality.

This paper presents a new algorithm for subspace clustering for high dimensional data. It is an iterative algorithm based on the minimization of an objective function. A major weakness of subspace clustering algorithms is that almost all of them are developed based on within- class information only or by employing both within-cluster and between- clusters information. The density of cluster is lost. The new function is developed by integrating the separation and compactness of clusters. The density of cluster is introduced also in the compactness term. The experimental results confirm that the proposed algorithm gives good results on different types of images by optimizing the runtime.

The development of technology generates huge amounts of non-textual information, such as images. An efficient image annotation and retrieval system is highly desired. Clustering algorithms make it possible to represent visual features of images with finite symbols. Based on this, many statistical models, which analyze correspondence between visual features and words and discover hidden semantics, have been published. These models improve the annotation and retrieval of large image databases. However, image data usually have a large number of dimensions. Traditional clustering algorithms assign equal weights to these dimensions, and become confounded in the process of dealing with these dimensions. In this paper, we propose a top-down, subspace clustering algorithm as a solution to this problem. For a given cluster, we determine relevant features based on histogram analysis and assign greater weight to relevant features as compared to less relevant features. We have implemented four different models to link visual tokens with keywords based on the clustering results of our clustering algorithm and K-means algorithm, and evaluated performance using precision, recall and correspondence accuracy using benchmark dataset. The results show that our algorithm is better than traditional ones for automatic image annotation and retrieval.

We present a structural clustering algorithm for large-scale datasets of small labeled graphs, utilizing a frequent subgraph sampling strategy. A set of representatives provides an intuitive description of each cluster, supports the clustering process, and helps to interpret the clustering results. The projection-based nature of the clustering approach allows us to bypass dimensionality and feature extraction problems that arise in the context of graph datasets reduced to pairwise distances or feature vectors. While achieving high quality and (human) interpretable clusterings, the runtime of the algorithm only grows linearly with the number of graphs. Furthermore, the approach is easy to parallelize and therefore suitable for very large datasets. Our extensive experimental evaluation on synthetic and real world datasets demonstrates the superiority of our approach over existing structural and subspace clustering algorithms, both, from a runtime and quality point of view.

The fixed-time strategy is crucial in traffic signal control which applies signal plans to different time periods of the day. One critical step is to determine the optimal breakpoints to divide one day into periods with homogeneous traffic flow. Most existing methods are based on $k$ -means clustering algorithm and have to select the optimal number of clusters. Since direct $k$ -means and time-incorporated $k$ -means clustering will result to noncontiguous time periods, several adjustments are needed including further partitioning and re-clustering via empirically adjustment which merges short time periods into adjacent longer ones to finalize the time-of-day (TOD) partition plan. Such adjustments can make the previous optimal number of clusters selection suboptimal. This paper proposes an enhanced method to determine optimal TOD breakpoints through optimizing the process. Instead of choosing the optimal partition plan before adjustments, we propose to determine the optimum after all the adjustments. A case study based on Qingdao City in China is presented to evaluate the added value of the enhanced method. It is shown through simulation experiments that the enhanced method can avoid over-partitioning and substantially improve the traffic operational efficiency especially during high demand periods.

As one of the most widely used clustering techniques, the fuzzy k -means (FKM) assigns every data point to each cluster with a certain degree of membership. However, conventional FKM approach relies on the square data fitting term, which is sensitive to the outliers with ignoring the prior information. In this paper, we develop a novel and robust fuzzy k -means clustering algorithm, namely, joint learning of fuzzy k -means and nonnegative spectral clustering with side information. The proposed method combines fuzzy k -means and nonnegative spectral clustering into a unified model, which can further exploit the prior knowledge of data pairs such that both the quality of affinity graph and the clustering performance can be improved. In addition, for the purpose of enhancing the robustness, the adaptive loss function is adopted in the objective function, since it smoothly interpolates between l1 -norm and l2 -norm. Finally, experimental results on benchmark datasets verify the effectiveness and the superiority of our clustering method.

To better explore the underlying intrinsic structure of tensorial data, in this Letter, the authors propose a low‐rank approximation‐based tensor decomposition (LRATD) algorithm for subspace clustering. LRATD aims to seek a low‐dimensional intrinsic core tensor representation by projecting the original tensor into a subspace spanned by projection matrices. Different from traditional approaches that impose additional constraints on basis matrices to further eliminate the influence of data noise or corruption, they directly add a low‐rank regulariser on the core tensor to encourage more robust feature representation. Noticeably, they develop an accelerated proximal gradient algorithm to solve the problem of LRATD. Experimental results demonstrate the excellent performance compared with state‐of‐the‐art methods.

Sparse component analysis (SCA) is an approach for linear matrix factorization in an instantaneous mixing system when the number of sensors is fewer than the number of sources. SCA assumes that matrix source (S) contains as many zeros as possible. According to the Georgiev's proof, under some nonstrict conditions on sparsity of the sources, called k-sparse component analysis (k-SCA), we are able to estimate both mixing system (A) and sparse sources (S) uniquely. This paper studies the problem of underdetermind blind identification (UBI) in order to estimate the mixing matrix A based on subspace clustering scheme with k-SCA assumptions. Most k-SCA based algorithms have been designed when there are only at most k = m − 1 active sources in each time instant, where m is the number of sensors. First, we address the issue of multiple active sources i.e. when there are L active sources (0 ≤ L ≤ m − 1). Second, we propose an algorithm for joint or continuous subspace clustering and estimating of the channels in order to design an online scenario to estimate the mixing matrix columns and detect the number of sources as the mixture vectors are received sequentially. Third, our proposed algorithm “subspace selective search” (S3) deals with the outliers within subspace clustering process and improve the accuracy of channel estimation. Numerical simulations are reported to confirm the advantages of our UBI method.

The localization accuracy of a fingerprint-based localization system is dependent on several factors, one of which is the accuracy and efficiency at which the fingerprint database is clustered. Most highly efficient and accurate clustering algorithms have high time-dependent computational complexity (CC), which tends to limit their practical applicability. A technique that has yet to be explored is the sequential hybridization of multiple low-time CC clustering algorithms to produce a single moderate-time CC clustering algorithm with high localization accuracy. As a result, this paper proposes a clustering algorithm with a moderate time CC that is based on the sequential hybridization of the closest access point (CAP) and improved k-means clustering algorithms. The performance of the proposed sequential hybrid clustering algorithm is determined and compared to the modified affinity propagation clustering (m-APC), fuzzy c-mean (FCM), and 2-CAP algorithms presented in earlier research works using four experimentally generated and publicly available fingerprint databases. The performance metrics considered for the comparisons are the position root mean square error (RMSE) and clustering time based on big O notation. The simulation results show that the proposed sequential hybrid clustering algorithm has improved localization accuracy with position RMSEs of about 54%, 77%, and 52%, respectively, higher than those of the m-APC, FCM, and 2-CAP algorithms. In terms of clustering time, it is 99% and 79% faster than the m-APC and FCM algorithms, respectively, but 90% slower than the 2-CAP algorithm. The results have shown that it is possible to develop a clustering algorithm that has a moderate clustering time with very high localization accuracy through sequential hybridization of multiple clustering algorithms that have a low clustering time with poor localization accuracy. Doi: 10.28991/ESJ-2024-08-02-02 Full Text: PDF

Fuzzy partition based soft subspace clustering and its applications in high dimensional data

Automated operational modal analysis (AOMA) is a common standard for unsupervised, data-driven, and output-only system identification, utilizing ambient vibrations as an environmental input source. However, conventional AOMA approaches apply the -means clustering algorithm (with ) to discern possibly physical and certainly mathematical modes. That is not totally appropriate due to the intrinsic tendency of -means to produce similarly sized clusters, as well as its limitation to approximately normally distributed variables. Hence, a novel approach, based on the density-based clustering algorithm Density-Based Spatial Clustering of Applications with Noise (DBSCAN), is introduced here. Among other technical advantages, this enables to automatically detect and remove outliers. A data-driven strategy for the DBSCAN parameter selection is proposed as well, to make the whole procedure fully automated. This methodology is then validated on a case of aeronautical interest, an Airbus Helicopter H135 bearingless main rotor blade, and compared to more classic strategies for the same case study.