Large graph analysis is one of the significant applications of distributed computing frameworks. The distributed computing applications are solved by developing programs over different types of established distributed...
详细信息
ISBN:
(纸本)9781479954964
Large graph analysis is one of the significant applications of distributed computing frameworks. The distributed computing applications are solved by developing programs over different types of established distributed computing frameworks. Since graph analysis and prediction is one of the new trend in data analytics, designing the problems on an in-memory cluster framework which consumes graph data-sets have a significant role in distributed computing. Traditional disk-based distributed computing framework like hadoop will confine only to a specific group of problems in data analytics. The importance of utilizing the memory of the cluster apart from the disk-based storage space contributes a significant role in reducing the latency and increasing the speedup. The whole work describes the significance of spark-framework in solving graph related problems in a distributed approach using page ranking algorithm and proteome-protein annotation method in Scala.
Community detection and centrality analysis in social networks are identified as pertinent research topics in the field of social network analysis. Community detection focuses on identifying the subgraphs (communities...
详细信息
ISBN:
(纸本)9783030588113;9783030588106
Community detection and centrality analysis in social networks are identified as pertinent research topics in the field of social network analysis. Community detection focuses on identifying the subgraphs (communities) which have dense connections within it as compared to outside of it, whereas centrality analysis focuses on identifying significant nodes in a social network based on different aspects of importance. A number of research works have focused on identifying community structure in large-scale network. However, very less effort has been emphasized on quantifying the influence of the communities. In this paper, group of nodes that are likely to form communities are first uncovered and then they are quantified based on the influencing ability in the network. Identifying exact boundaries of communities are quite challenging in large scale network. The major contribution in this paper is to develop a model termed as FRC-FGSN (Fuzzy Rough Communities in Fuzzy Granular Social Network), to identify the communities with the help of fuzzy and rough set theory. The proposed model is based on a idea that, the degree of belongingness a node in a community may not be binary but can be models through fuzzy membership. The second contribution is to quantifying the influence of the community using eigenvector centrality. In order to improve the scalability, several steps in the proposed model have been implemented using map-reduce programming paradigm in a cluster-computing framework like Hadoop. Comparative analysis of FRC-FGSN with other parallel algorithms as available in the literature has been presented to demonstrate the scalability and effectiveness of the algorithm.
Reaction-diffusion (RD) models are widely used to study the spatio-temporal evolution of pattern formation during development. Nonlinear RD models are often analytically intractable, and require numerical solution met...
详细信息
ISBN:
(纸本)9781538649756
Reaction-diffusion (RD) models are widely used to study the spatio-temporal evolution of pattern formation during development. Nonlinear RD models are often analytically intractable, and require numerical solution methods. Interrogation of RD models for a large physiological range of parameters covers many orders of magnitude, establishing situations where solutions are stiff and solvers fail to provide accurate results to the time-dependent problem. The spatial dependence of these parameters, and the nonlinearity of the underlying dynamics, impose additional challenges. We developed an efficient approach for simulating stiff RD models of pattern formation and we used supercomputer clusters to carry out a large screen of spatially varying parameters. The proposed approach generated data for screening of RD systems within a reasonable amount of time (a few days), which scales down further if additional cluster nodes are available. The approaches outlined herein are applicable to any systems biology problem requiring numerical approximation of RD equations with spatially non-uniform properties and stiff nonlinear reactions.
The stabilization of nonlinear systems depend strongly on the initial state and the parameters of the systems. The initial state and the parameters with which the system Is stabilized can be distinguished by the geome...
详细信息
ISBN:
(纸本)9780780394452
The stabilization of nonlinear systems depend strongly on the initial state and the parameters of the systems. The initial state and the parameters with which the system Is stabilized can be distinguished by the geometrical structure. It is, however, difficult and sometimes impossible to analyze the structure analytically. Therefore it comes important to show and analyze the structure of the parameters and initial states numerically and visually. In this paper, we present a method to draw and visualize such region and structure in the three dimensional space. In general, the projection of the original high-dimensional space to the lower dimension one is required for using visual analysis. Thus, it is convenient that the viewpoint can be moved, without time loss, in the direction where analyst would like to see. As often as the viewpoint moves, the recomputation as quick as possible is required to realize the quick motion of viewpoint. It is, however, obvious that lots of computation and time are taken to draw the region. Therefore, high performance calculators are needed to realize the real-time drawing. In order to overcome this problem, FPGA and cluster-computing is used in this paper. Then it is demonstrated by illustrative examples that FPGA and cluster-computing shows high performance to draw the region of the parameters and initial state in 3D with which z(n+1) = Z(n)(2) + C can be stabilized, that is Mandelbrot and Julia sets, respectively.
Multi-objective genetic algorithms (MOGAs) are finding increasing popularity as researchers realize their potential for obtaining good solutions to mining problems in large databases. Parallel multi-objective genetic ...
详细信息
Multi-objective genetic algorithms (MOGAs) are finding increasing popularity as researchers realize their potential for obtaining good solutions to mining problems in large databases. Parallel multi-objective genetic algorithms (pMOGAs) attempts to reduce the processing time needed for computing the fitness functions and to reach an acceptable solution. We propose two different master slave models of pMOGA. Our proposed models exploit both data parallelism by distributing the data being mined across various processors, and control parallelism by distributing the population of individuals across all available processors. These models are implemented through a clustercomputing environment and we measure the speed up of pMOGA over its sequential counterpart.
The aim of the human neuroscanning project (HNSP) is to build an atlas of a human brain at cellular level. The database was obtained by a variety of image modalities and in particular histological sections of a prepar...
详细信息
The aim of the human neuroscanning project (HNSP) is to build an atlas of a human brain at cellular level. The database was obtained by a variety of image modalities and in particular histological sections of a prepared brain. As the preparation leads to linear and non-linear deformations of the tissue, reconstructing the essential information out of deformed images is a key problem within the HNSP Our approach of correcting these deformations is based on an elastic matching of the images. Therefore, a parallel implementation was used, since the problem in general is computational expensive and for very large scale digital images a huge amount of data has to be processed. As these requirements are in the range of today's grand challenges, a large PC-cluster was used to provide the performance demands. The measurements and results presented here were obtained on a cluster of 48 Dual SNIP platforms connected via a Myrinet network. (C) 2001 Elsevier Science B.V. All rights reserved.
暂无评论