Identifying clusters or clustering is an important aspect of data analysis. It is the task of grouping a set of objects in such a way those objects in the same group/cluster are more similar in some sense or another. It is a main task of exploratory data mining, and a common technique for statistical data analysis This paper proposed an improved version of K-Means algorithm, namely Persistent K-Means, which alters the convergence method of K-Means algorithm to provide more accurate clustering results than the K-means algorithm and its variants by increasing the clusters’ coherence. Persistent K-Means uses an iterative approach to discover the best result for consecutive iterations of KMeans algorithm.

Data clustering is the process of partitioning a set of data objects into meaning clusters or groups. Due to the vast usage of clustering algorithms in many fields, a lot of research is still going on to find the best and efficient clustering algorithm to partition the data items. K-means is simple and easy to implement, but it suffers from initialization of cluster center and hence trapped in local optimum. In this paper, a new hybrid data clustering approach which combines the modified krill herd and K-means algorithms, named as K-MKH, is proposed. K-MKH algorithm utilizes the power of quick convergence behaviour of K-means and efficient global exploration of Krill Herd and random phenomenon of Levy flight method. The Krill-herd algorithm is modified by incorporating Levy flight into it to improve the global exploration. The proposed algorithm is tested on artificial and real life datasets. The simulation results are compared with other methods such as K-means, Particle Swarm Optimization (PSO), Original Krill Herd (KH), hybrid K-means and KH. Also the proposed algorithm is compared with other evolutionary algorithms such as hybrid modified cohort intelligence and K-means (K-MCI), Simulated Annealing (SA), Ant Colony Optimization (ACO), Genetic Algorithm (GA), Tabu Search (TS), Honey Bee Mating Optimization (HBMO) and K-means++. The comparison shows that the proposed algorithm improves the clustering results and has high convergence speed.

Foreground-background image segmentation has been an important research problem. It is one of the main tasks in the field of computer vision whose purpose is detecting variations in image sequences. It provides candidate objects for further attentional selection, e. g., in video surveillance. In this paper, we introduce an automatic and efficient Foreground-background segmentation. The proposed method starts with the detection of visually salient image regions with a saliency map that uses Fourier transform and a Gaussian filter. Then, each point in the maps classifies as salient or non-salient using a binary threshold. Next, a hole filling operator is applied for filling holes in the achieved image, and the area-opening method is used for removing small objects from the image. For better separation of the foreground and background, dilation and erosion operators are also used. Erosion and dilation operators are applied for shrinking and expanding the achieved region. Afterward, the foreground and background samples are achieved. Because the number of these data is large, K-means clustering is used as a sampling technique to restrict computational efforts in the region of interest. K cluster centers for each region are set for training of Support Vector Machine (SVM). SVM, as a powerful binary classifier, is used to segment the interest area from the background. The proposed method is applied on a benchmark dataset consisting of 1000 images and experimental results demonstrate the supremacy of the proposed method to some other foreground-background segmentation methods in terms of ER, VI, GCE, and PRI.