Search

• We have developed a clustering algorithm for an unknown number of clusters by MOGA. • It works with continuous and categorical featured data sets. • It can work with data sets having missing values. • The final solution is selected by majority vote by all non-dominated solutions. • Context-sensitive and cluster-orient genetic operators are designed. Many clustering algorithms categorized as K -clustering algorithm require the user to predict the number of clusters (K) to do clustering. Due to lack of domain knowledge an accurate value of K is difficult to predict. The problem becomes critical when the dimensionality of data points is large; clusters differ widely in shape, size, and density; and when clusters are overlapping in nature. Determining the suitable K is an optimization problem. Automatic clustering algorithms can discover the optimal K. This paper presents an automatic clustering algorithm which is superior to K -clustering algorithm as it can discover an optimal value of K. Iterative hill-climbing algorithms like K -Means work on a single solution and converge to a local optimum solution. Here, Genetic Algorithms (GA s) find out near global optimum solutions, i.e. optimal K as well as the optimal cluster centroids. Single-objective clustering algorithms are adequate for efficiently grouping linearly separable clusters. For non-linearly separable clusters they are not so good. So for grouping non-linearly separable clusters, we apply Multi-Objective Genetic Algorithm (MOGA) by minimizing the intra-cluster distance and maximizing inter-cluster distance. Many existing MOGA based clustering algorithms are suitable for either numeric or categorical features. This paper pioneered employing MOGA for automatic clustering with mixed types of features. Statistical testing on experimental results on real-life benchmark data sets from the University of California at Irvine (UCI) machine learning repository proves the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The Multi-Robot Task Allocation (MRTA) problem has recently become a key research topic. Task allocation is the problem of mapping tasks to robots, such that the most appropriate robot is selected to perform the most fitting task, leading to all tasks being optimally accomplished. Expanding the number of tasks and robots may cause the collaboration among the robots to become tougher. Since this process requires high computational time, this paper describes a technique that reduces the size of the explored state space, by partitioning the tasks into clusters. In real-world problems, the absence of information regarding the number of clusters is ordinarily occurring. Hence, a dynamic clustering is auspicious for partitioning the tasks to an appropriate number of clusters. In this paper, we address the problem of MRTA by putting forward a new simple, automatic and efficient clustering algorithm of the robots' tasks based on a dynamic distributed particle swarm optimization, namely, ACD2PSO. Our approach is made out of two stages: stage I groups the tasks into clusters using the dynamic distributed particle swarm optimization (D2PSO) algorithm and stage II allocates the robots to the clusters. The assignment of robots to the clusters is represented as multiple traveling salesman problems (MTSP). Computational experiments were carried out to prove the effectiveness of our approach in term of clustering time, cost, and the MRTA time, compared to the distributed particle swarm optimization (dPSO) and genetic algorithm (GA). Thanks to the D2PSO algorithm, stagnation and local optima issues are avoided by adding assorted variety to the population, without losing the fast convergence of PSO. [ABSTRACT FROM AUTHOR]

Most of the proposed algorithms to solve the dynamic clustering problem are based on nature inspired meta-heuristic algorithms. In this paper a different reinforcement based optimization approach called continuous action-set learning automata (CALA) is used and a novel dynamic clustering approach called ACCALA is proposed. CALA is an optimization tool interacting with a random environment and learn the optimal action from the environment feedbacks. In this paper the dynamic clustering problem considered as a noisy optimization problem and the team of CALAs is used to solve this noisy optimization problem. To build such a team of CALAs this paper proposed a new representation of CALAs. Each automaton in this team uses its continuous action-set and defining a suitable action-set for each automaton has a great impact on the CALAs search behavior. In this paper we used the statistical property of data-sets and proposed a new method to automatically find an action-set for each automaton. The performance of ACCALA is evaluated and the results are compared with seven well-known automatic clustering techniques. Also ACCALA is used to perform automatic segmentation. The experimental results are promising and show that the proposed algorithm produced compact and well-separated clusters. [ABSTRACT FROM AUTHOR]

Highlights • Improving results by combining random and homogeneity based merge-split method. • Reducing number of empty clusters by attention to data density for selecting center. • Avoid falling into local optimum points in the proposed assimilation step. • State-of-the-art accuracies for solving automatic clustering problems. Abstract Cluster analysis has a wide application in many areas, including pattern recognition, information retrieval, and image processing. In most real-world clustering problems, the number of clusters must be predetermined. Automatic clustering is a promising solution for this challenge which automatically determines the number and structure of clusters in data. In recent years, the evolutionary algorithm due to their search mechanisms has been popular in solving automatic clustering problems. Imperialist Competitive Algorithm (ICA) is a successful evolutionary algorithm. In this paper, for the first time, Imperialist Competitive Algorithm (ICA) is used for solving automatic clustering problems, called "the automatic clustering using ICA (AC-ICA)". In the proposed algorithm, in order to increase the exploration ability, the movement of colonies toward the imperialist was changed at the assimilation step. A new method has been provided for changing the number of clusters by combining random and homogeneity based merge-split approach. Furthermore, an efficient method based on density has been proposed for reinitializing empty cluster centers. To use AC-ICA in automatic clustering, the initialization and imperialist competition steps were changed. Based on changes in these two steps, a framework was provided for changing different types of ICA to solve automatic clustering problems. Then, the basic ICA and its three recently developed types, were changed by this framework and their performances in automatic clustering were compared to AC-ICA. The examinations were done on six synthetic and ten real word data sets. The comparison of the proposed algorithm's results with basic ICA, its three recently developed types and several state-of-art automatic clustering methods, shows AC-ICA's superiority in terms of the speed of convergence to the optimal solution and quality of the obtained solution. We also applied our algorithm to a real world application (i.e., face recognition) and the achieved results were acceptable. [ABSTRACT FROM AUTHOR]

In this paper, a novel hybrid model for forecasting low dimensional numerical data is proposed which is named as ClusFuDE . The proposed method uses an improved automatic clustering approach for clustering the historical numerical data. Further fuzzy logical relationships are used to forecast the approximate values which are then defuzzified to calculate the exact forecasted values of the data. The fuzzy logical relationships are useful in modelling the fuzzy relations and help in forecasting the fuzzy time series data in a very simplified manner. The forecasted sub-optimal candidate solutions are optimized using Differential Evolution. The Differential Evolution method uses a dynamic differential crossover rate ( C r i ) for the i th solution, for identifying and discarding suboptimal candidate solutions in early stages of the iterative run. This makes the method more suitable for iterative modification of candidate solutions by using differential mutation and crossover, and suitable for global search. The proposed method is applied for forecasting, the year wise enrollments of the University of Alabama, Lahi (crop) production, monthly amount of outpatients visit in a hospital, inventory demand and population of India from years 1930–2000 and the results are consistent. We have compared our method with the recent forecasting methods available in literature and the proposed method outperforms all the existing methods in the literature. The accuracy of the proposed method is computed by calculating the Mean square error (MSE) and Mean Absolute percentage error (MAPE). The proposed method provides the lowest MSE and MAPE when compared to all other methods available in the literature. [ABSTRACT FROM AUTHOR]

Grey Wolf Optimizer has recently emerged as an efficient meta-heuristic optimization technique. It has good capability in exploitation for unimodal problems, superior exploration ability for multimodal problems, and also works fine for composite functions avoiding local minimas. This paper proposes an application of Grey Wolf Optimizer (GWO) algorithm for satellite image segmentation. The original GWO has been suitably modified to work as an automatic clustering algorithm. This algorithm has been applied on two satellite images. It is computationally efficient and its accuracy is superior in many cases in terms of Davies-Bouldin (DB) index, average inter-cluster distance and average intra-cluster distance. [ABSTRACT FROM AUTHOR]

This paper is intended to identify the optimal number of clusters automatically from an image dataset using some quantum behaved nature inspired meta-heuristic algorithms. Due to the lack of sufficient information, it is difficult to identify the appropriate number of clusters from a dataset, which has enthused the researchers to solve the problem of automatic clustering and to open up a new era of cluster analysis with the help of several natures inspired meta-heuristic algorithms. In this paper, three quantum inspired meta-heuristic techniques, viz., Quantum Inspired Particle Swarm Optimization (QIPSO), Quantum Inspired Spider Monkey Optimization (QISMO) and Quantum Inspired Ageist Spider Monkey Optimization (QIASMO), have been proposed. A comparison has been outlined between the quantum inspired algorithms with their corresponding classical counterparts. The efficiency of the quantum inspired algorithms has been established over their corresponding classical counterparts with regards to fitness, mean, standard deviation, standard errors of fitness, convergence curves (for benchmarked mathematical functions) and computational time. Finally, the results of two statistical superiority tests, viz., t- test and Friedman test have been provided to prove the superiority of the proposed methods. The superiority of the proposed methods has been established on five publicly available real life image datasets, five Berkeley image datasets of different dimensions and four benchmark mathematical functions both visually and quantitatively. • It is difficult to identify the appropriate number of clusters from a dataset. • We propose three quantum inspired meta-heuristics for automatic determination of number of clusters. • The proposed algorithms perform better than their classical counterparts. • Statistical superiority tests also prove the superiority of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In cluster analysis, a fundamental problem is to determine the best estimate of the number of clusters; this is known as the automatic clustering problem. Because of lack of prior domain knowledge, it is difficult to choose an appropriate number of clusters, especially when the data have many dimensions, when clusters differ widely in shape, size, and density, and when overlapping exists among groups. In the late 1990s, the automatic clustering problem gave rise to a new era in cluster analysis with the application of nature-inspired metaheuristics. Since then, researchers have developed several new algorithms in this field. This paper presents an up-to-date review of all major nature-inspired metaheuristic algorithms used thus far for automatic clustering. Also, the main components involved during the formulation of metaheuristics for automatic clustering are presented, such as encoding schemes, validity indices, and proximity measures. A total of 65 automatic clustering approaches are reviewed, which are based on single-solution, single-objective, and multiobjective metaheuristics, whose usage percentages are 3%, 69%, and 28%, respectively. Single-objective clustering algorithms are adequate to efficiently group linearly separable clusters. However, a strong tendency in using multiobjective algorithms is found nowadays to address non-linearly separable problems. Finally, a discussion and some emerging research directions are presented. [ABSTRACT FROM AUTHOR]

Clustering is an essential tool in data mining research and applications. It is the subject of active research in many fields of study, such as computer science, data science, statistics, pattern recognition, artificial intelligence, and machine learning. Several clustering techniques have been proposed and implemented, and most of them successfully find excellent quality or optimal clustering results in the domains mentioned earlier. However, there has been a gradual shift in the choice of clustering methods among domain experts and practitioners alike, which is precipitated by the fact that most traditional clustering algorithms still depend on the number of clusters provided a priori. These conventional clustering algorithms cannot effectively handle real-world data clustering analysis problems where the number of clusters in data objects cannot be easily identified. Also, they cannot effectively manage problems where the optimal number of clusters for a high-dimensional dataset cannot be easily determined. Therefore, there is a need for improved, flexible, and efficient clustering techniques. Recently, a variety of efficient clustering algorithms have been proposed in the literature, and these algorithms produced good results when evaluated on real-world clustering problems. This study presents an up-to-date systematic and comprehensive review of traditional and state-of-the-art clustering techniques for different domains. This survey considers clustering from a more practical perspective. It shows the outstanding role of clustering in various disciplines, such as education, marketing, medicine, biology, and bioinformatics. It also discusses the application of clustering to different fields attracting intensive efforts among the scientific community, such as big data, artificial intelligence, and robotics. This survey paper will be beneficial for both practitioners and researchers. It will serve as a good reference point for researchers and practitioners to design improved and efficient state-of-the-art clustering algorithms. • Provide an up-to-date comprehensive review of the different clustering techniques. • Highlight novel and most recent practical applications areas of clustering. • Provide a convenient research path for new researchers. • Help experts develop new algorithms for emerging challenges in the research area. [ABSTRACT FROM AUTHOR]

Abstract: Multi-objective clustering algorithms are preferred over its conventional single objective counterparts as they incorporate additional knowledge on properties of data in the from of objectives to extract the underlying clusters present in many datasets. Researchers have recently proposed some standardized multi-objective evolutionary clustering algorithms based on genetic operations, particle swarm optimization, clonal selection principles, differential evolution and simulated annealing, etc. In many cases it is observed that hybrid evolutionary algorithms provide improved performance compared to that of individual algorithm. In this paper an automatic clustering algorithm MOIMPSO (Multi-objective Immunized Particle Swarm Optimization) is proposed, which is based on a recently developed hybrid evolutionary algorithm Immunized PSO. The proposed algorithm provides suitable Pareto optimal archive for unsupervised problems by automatically evolving the cluster centers and simultaneously optimizing two objective functions. In addition the algorithm provides a single best solution from the Pareto optimal archive which mostly satisfy the users' requirement. Rigorous simulation studies on 11 benchmark datasets demonstrate the superior performance of the proposed algorithm compared to that of the standardized automatic clustering algorithms such as MOCK, MOPSO and MOCLONAL. An interesting application of the proposed algorithm has also been demonstrated to classify the normal and aggressive actions of 3D human models. [Copyright &y& Elsevier]

Abstract: To automatically extract T–S fuzzy models with enhanced performance from data is an interesting and important issue for fuzzy system modeling. In this paper, a novel methodology is proposed for this issue based on a three-step procedure. Firstly, the idea of variable length genotypes is introduced to the artificial bee colony (ABC) algorithm to derive a so-called Variable string length Artificial Bee Colony (VABC) algorithm. The VABC algorithm can be used to solve a kind of optimization problems where the length of the optimal solutions is not known as a priori. Secondly, fuzzy clustering without knowing cluster number as a priori is viewed as such kind of optimization problem. Thus, a novel version of Fuzzy C-Means clustering technique (VABC-FCM), holding powerful global search ability, is proposed based on the VABC algorithm. Use of VABC allows the encoding of variable cluster number. This makes VABC-FCM not require a priori specification of the cluster number. Finally, the proposed VABC-FCM algorithm is used to extract T–S fuzzy model from data. Such VABC-FCM based convenient T–S fuzzy model extraction methodology does not require a specification of rule number as a priori. Some artificial data sets are applied to validate the performance of the convenient T–S fuzzy model. The experimental results show that the proposed convenient T–S fuzzy model has low approximation error and high prediction accuracy with appreciate rule number. Moreover, the convenient T–S fuzzy model is used to model the characteristics of superheated steam temperature in power plant, and the results suggest the powerful performance of the proposed method. [Copyright &y& Elsevier]

Abstract: In order to find the arbitrary shape clusters and the optimal number of clusters of a dataset automatically, a new particle swarm based clustering algorithm is proposed in this paper. The algorithm involves a swarm of particles searching in the data space instead of the solution space and the selection, mutation and regeneration operators of genetic algorithm (GA) are also introduced to increase the diversity of the swarm in its evolutionary progress. Particles in the swarm work cooperatively to find the result of the clustering problem. The new algorithm is compared with the traditional PSO-based clustering algorithm and K-means algorithm on two artificial datasets and three benchmark UCI datasets. Experimental results show that the new algorithm has much potential on arbitrary shape clustering and automatic clustering problems. [Copyright &y& Elsevier]

Abstract: Business failures are depressing events which not only decimate the benefits of stakeholders but also affect the continuing development of economy and society. In order to reduce the impact of business failure, various models of business failure prediction have been developed. Although failure prediction models currently achieve a collective average accuracy of more than 85%, few persons can bear a risk of less than 100% accuracy under the present conditions of economic crisis. It is of particular interest that current failure prediction models have tended to adopt the technique of matching up failed and non-failed firms. This method, however, seems to have merely led to further complications. This paper proposes a method which directly explores the features of failed firms rather than researching pairs of failed and non-failed firms. To this end, automatic clustering techniques and feature selection techniques are employed for this study. [Copyright &y& Elsevier]

Clustering is a commonly employed approach to image segmentation. To overcome the problems of conventional algorithms such as getting trapped in local optima, in this paper, we propose an improved automatic clustering algorithm for image segmentation based on the human mental search (HMS) algorithm, a recently proposed method to solve complex optimisation problems. In contrast to most existing methods for image clustering, our approach does not require any prior knowledge about the number of clusters but rather determines the optimal number of clusters automatically. In addition, for further improved efficacy, we incorporate local search operators which are designed to make changes to the current cluster configuration. To evaluate the performance of our proposed algorithm, we perform an extensive comparison with several state-of-the-art algorithms on a benchmark set of images and using a variety of metrics including cost function, correctness of the obtained numbers of clusters, stability, as well as supervised and unsupervised segmentation criteria. The obtained results clearly indicate excellent performance compared to existing methods with our approach yielding the best result in 16 of 17 cases based on cost function evaluation, 9 of 11 cases based on number of identified clusters, 13 of 17 cases based on the unsupervised Borsotti image segmentation criterion, and 7 of 11 cases based on the supervised PRI image segmentation metric. • We propose a novel method of automatic clustering for image segmentation using the Human Mental Search (HMS) optimisation algorithm. • Our proposed algorithm does not require any basic knowledge regarding the number of clusters in the image. • For improved efficacy, a local search mechanism is integrated in the proposed approach. • The performance of our algorithm is evaluated based on a variety of metrics including supervised and unsupervised segmentation criteria. • The obtained results indicate a very competitive performance compared to existing methods. [ABSTRACT FROM AUTHOR]

Today's real-world data mostly involves incomplete, inconsistent, and/or irrelevant information that causes many drawbacks to transform it into an understandable format. In order to deal with such issues, data preprocessing is a proven discipline in data mining. One of the typical tasks in data preprocessing, feature selection aims to reduce the dimensionality in the data and thereby contributes to further processing. Feature selection is widely used to enhance the performance of a supervised learning algorithm (e.g., classification) but is rarely used in unsupervised tasks (e.g., clustering). This paper introduces a new multi-objective differential evolution approach in order to find relatively homogeneous clusters without the prior knowledge of cluster number using a smaller number of features from all available features in the data. To analyze the goodness of the introduced approach, several experiments are conducted on a various number of real-world and synthetic benchmarks using a variety of clustering approaches. From the analyzes through several different criteria, it is suggested that our method can significantly improve the clustering performance while reducing the dimensionality at the same time. [ABSTRACT FROM AUTHOR]