We present a new online algorithm for detecting overlapping communities. The main ingredients are a modification of an online k-means algorithm and a new approach to modelling overlap in communities. An evaluation on large benchmark graphs shows that the quality of discovered communities compares favourably to several methods in the recent literature, while the running time is significantly imp...

In Forensic Analysis thousands of files are usually examined. Data in those files consists of unstructured text analyzing it by examiners is very difficult. Algorithms for clustering documents can facilitate the discovery of new and useful knowledge from the documents under analysis. Cluster analysis itself is not one specific algorithm but the general task to be solved. It can be achieved by v...

This paper proposes a genetic weighted K-means algorithm called GWKMA, which is a hybridization of a genetic algorithm (GA) and a weighted K-means algorithm (WKMA). GWKMA encodes each individual by a partitioning table which uniquely determines a clustering, and employs three genetic operators (selection, crossover, mutation) and a WKMA operator. The superiority of the GWKMA over the WKMA and o...

Abstarct— In this paper we have presented a proposed a three step framework,starting with finding the initial clusters and then initalizing initial cluster centers and finially partitioning data into most optimal clusters.we have employed some the most effiecient algorithms like Dbscan and K-Means(XK-Means) and we have tested our approach on iris data set. Keywords— exploratory vector;centroids...

Clustering of relational data has so far received a lot less attention than classification of such data. In this paper we investigate a simple approach based on randomized propositionalization, which allows for applying standard clustering algorithms like KMeans to multi-relational data. We describe how random rules are generated and then turned into boolean-valued features. Clustering generall...

We present a simultaneous generalization of the well-known Karhunen-Loéve (PCA) and k-means algorithms. The basic idea lies in approximating the data with k affine subspaces of a given dimension n. In the case n = 0 we obtain the classical k-means, while for k = 1 we obtain PCA algorithm. Moreover, by our approach we can obtain clusters with different dimensionality which describe the structure...

The k-means algorithm is a widely used clustering technique. Here we will examine the performance of multiple implementations of the k-means algorithm in different settings. Our discussion will touch on the implementation of the algorithm in both python and C, and will also mention a 3rd party package for the k-means algorithm that is also written in C but provides python bindings. We will then...

Global gas flaring is difficult to sense, a tremendous source of wasted revenue, and causes ecological problems. We use satellite sensors to predict gas flares’ sizes. We tested regression and classification algorithms, along with anomaly detection using k-means, and found that linear regression and 2-class SVM are almost as good as the full-tilt sensor model produced by the National Oceanic At...

As we know, kmeans method is a very effective algorithm of clustering. Its most powerful feature is the scalability and simplicity. However, the most disadvantage is that we must know the number of clusters in the first place, which is usually a difficult problem in practice. In this paper, we propose a new approach– peak-searching clustering– to realize clustering without given the number of c...

1 Department of Computer Applications, Rayapati Venkata Ranga Rao and Jagarlamudi Chadramouli College of Engineering, Guntur, India 2 Jawaharlal Nehru Technological University, Kakinada, India 3 Department of Statistics, Acharya Nagarjuna University, Guntur, India, 4 Endocrine and Diabetes Centre, Andhra Pradesh, India [email protected], [email protected], [email protected], sridhar...