Improvement of Subspace Clustering Based on Differential Evolution

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

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.

Nonlinear subspace clustering by functional link neural networks

In this paper, we present a test data generation algorithm of combinatorial testing based on Differential Evolution, and introduce a selection and substitution based on the degree of unfinished interaction, in order to optimize the test case selected in further. An IPO-like strategy for generating the test suite is used to reduce the dimension for differential evolutionary computation in the optimization process and improve the efficiency of the algorithm. By preliminary experiments, the main parameters in DE algorithm are chosen. And in further experiments, we implement the algorithm in some typical instances to verify its effectiveness. Compare to other well-known algorithms, the final empirical results show the competitiveness of our algorithm in test suite size and running time.

Subspace clustering using a symmetric low-rank representation

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.

Coupling Response Surface and Differential Evolution for Parameter Identification Problems

Dense community detection in multi-valued attributed networks

Differential evolution (DE) is a well-known evolutionary algorithm which has been successfully applied in many scientific and engineering fields. In most DE algorithms, the base and difference vectors for mutation are randomly selected from the current population. That is, the useful population information cannot be fully exploited to guide the search of DE through mutation. Furthermore, the selection of parents in mutation has been verified to be critical for the DE performance. Therefore, to alleviate this drawback and improve the performance of DE, a novel DE algorithm with a directional mutation based on cellular topology is proposed in this study. This proposed algorithm is named as Cellular Direction Information based DE (DE-CDI). In DE-CDI, the cellular topology is employed first to define a neighborhood for each individual of population and then the direction information based on the neighborhood is incorporated into the mutation operator. In this way, DE-CDI not only utilizes the neighborhood information to exploit the regions of better individuals and accelerate convergence, but also introduces the direction information to guide the search to the promising area. To evaluate the performance of the proposed method, DE-CDI is applied to the original DE algorithms, as well as several advanced DE variants. Experimental results demonstrate the high performance of DE-CDI for most DE algorithms studied.

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.

Differential evolution using homeostasis adaption based mutation operator and its application for software cost estimation

&lt;p&gt;Differential Evolution (DE) is an algorithm for evolutionary optimization. Clustering problems have been solved by using DE based clustering methods but these methods may fail to find clusters hidden in subspaces of high dimensional datasets. Subspace and projected clustering methods have been proposed in literature to find subspace clusters that are present in subspaces of dataset. In this paper we propose VINAYAKA, a semi-supervised projected clustering method based on DE. In this method DE optimizes a hybrid cluster validation index. Subspace Clustering Quality Estimate index (SCQE index) is used for internal cluster validation and Gini index gain is used for external cluster validation in the proposed hybrid cluster validation index. Proposed method is applied on Wisconsin breast cancer dataset.&lt;/p&gt;

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.

Differential evolution (DE) algorithm is a global optimization algorithm over continuous search space. DE also has been applied in many fields, such as artificial neural networks, chemical engineering, mechanical design, robotics, signal processing, biological information, and economics. At the same time, as a powerful evolutionary algorithm for solving global numerical optimization problems, the DE algorithm has drawn more and more attention. However, how to make a proper balance between the global and local search is a burning question and to limit the optimization performance of DE. In this paper, an improved algorithm η_CODE with a new η_Cauchy operator is proposed to enhance the global and local search ability of a well-known DE variant JADE. In order to guarantee the effective performance of the proposed operator, all the fitness values are ranked through a ranking scheme based on increasing order before a new η_Cauchy operator is conducted. The pNP individuals that have better fitness are selected and carried out Cauchy disturbance operation considering the complexity of the algorithm. The Dynamic parameter mechanism is utilized to select pNP individuals that number is also adjusted dynamically in each generation. The scale factor F and crossover probability CR are obtained with Lehmer mean without using determined parameter c in JADE, which aims to balance the exploration and exploitation of the algorithm during the running time. A total of sixty benchmark functions from CEC2014 and CEC2017 on real parameter optimization are employed to prove the validity of η_CODE for solving complex high-dimensional problems. The experiments indicate that η_CODE is better than or at least comparable with several state-of-the-art DE variants, including JADE, SinDE, TSDE, AGDE, and EFADE in the global numerical optimization problems. In order to further analyze the performance of η_CODE, we also select extra two high-powered modified algorithms called EBLSHADE and LSHADESPACMA based on LSHADE to discuss advantages and disadvantages of the proposed algorithm.

Influence of initialization on the performance of metaheuristic optimizers