Optimal application performance on a Distributed Object Based System requires class fragmentation and the development of allocation schemes to place fragments at distributed sites so data transfer is minimal. In this paper we present a horizontal fragmentation approach that uses the k-means centroid based clustering method for partitioning object instances into fragments. Our new method takes f...

We derive the finite-size dependence of the clustering coefficient of scale-free random graphs generated by the configuration model with degree distribution exponent 2 < γ < 3. Degree heterogeneity increases the presence of triangles in the network up to levels that compare to those found in many real networks even for extremely large nets. We also find that for values of γ ≈ 2, clustering is v...

ABSTRACT Clustering algorithms have become increasingly important in handling and analyzing data. Considerable work has been done in devising e ective but increasingly speci c clustering algorithms. In contrast, we have developed a generalized framework that accommodates diverse clustering algorithms in a systematic way. This framework views clustering as a general process of iterative optimiza...

Incorporating background knowledge in clustering problems has attracted wide interest. This knowledge can be represented as pairwise instance-level constraints. Existing techniques approach satisfaction of such constraints from a soft (discretionary) perspective, yet there exist scenarios for constrained clustering where satisfying as many constraints as possible. We present a new Lagrangian Co...

We derive the finite-size dependence of the clustering coefficient of scale-free random graphs generated by the configuration model with degree distribution exponent 2<γ<3. Degree heterogeneity increases the presence of triangles in the network up to levels that compare to those found in many real networks even for extremely large nets. We also find that for values of γ≈2, clustering is virtual...

Multiple instance data are sets or multi-sets of unordered elements. Using metrics or distances for sets, we propose an approach to several multiple instance learning tasks, such as clustering (unsupervised learning), classification (supervised learning), and novelty detection (semi-supervised learning). In particular, we introduce the Optimal Sub-Pattern Assignment metric to multiple instance ...

This paper proposes a semi-supervised learning method using Fuzzy clustering to solve word sense disambiguation problems. Furthermore, we reduce side effects of semi-supervised learning by ensemble learning. We set classes for labeled instances. The -th labeled instance is used as the prototype of the -th class. By using Fuzzy clustering for unlabeled instances, prototypes are moved to more sui...

This paper proposes an innovative instance similarity based evaluation metric that reduces the search map for clustering to be performed. An aggregate global score is calculated for each instance using the novel idea of Fibonacci series. The use of Fibonacci numbers is able to separate the instances effectively and, in hence, the intra-cluster similarity is increased and the intercluster simila...