paper discuss classic cluster algorithm can use segment imag recent develop activ contour imag segment model propos integr aspect classic algorithm improv activ contour model for result cvk bmean segment algorithm examin method decreas size imag domain the cvk method has been implement run parallel distribut comput chang order updat pixel possibl replac synchron communic asynchron communic subsequ parallel effici improv

J.R. Rommelse

H.X. Lin

T.F. Chan

Efficient Active Contour and K-Means Algorithms in Image Segmentation

queen mari univers london have over twenti year experi parallel comput applicat most massiv parallel system distribut array processor daps the applic which were involv includ design numer subroutin librari finit element softwar graphic tool physic organ materi medic imag comput vision more recent financi model two project relat latter describ paper name portfolio optimis financi risk assessment

Heather M. Liddell

D. Parkinson

G.S. Hodgson

P. Dzwig

Parallel Computing Applications and Financial Modelling

C.-H. Lai

Preface

from model geometri creation model analysi stage between mesh generat most manpow intens phase meshbas comput mechan simul process other hand model analysi most comput intens phase advanc comput hardwar softwar have signific reduc comput time more import trend downward with kind model envisag come which larger more complex geometri model multiphys clear trend manpow intens phase decreas signific time present way oper more like increas model complex paper address dilemma collabor compon model electron packag applic

P. Chow

Collaborating Components in Mesh-Based Electronic Packaging

algorithm often parallel base data depend analysi manual mean parallel compil some vector matrix comput matrixvector product simpl data depend structur data parallel can easili parallel for problem more complic data depend structur parallel less straightforward the data depend graph power mean design analyz parallel algorithm howev spars matrix comput parallel base sole exploit exist parallel algorithm doe alway give satisfactori result for exampl convent gaussian elimin algorithm solut tridiagon system inher sequenti algorithm special parallel comput has design after briefli review differ parallel approach power graph formal design parallel algorithm introduc this formal discuss use tridiagon system exampl its applic general matrix comput also discuss its power design parallel algorithm beyond abil data depend analysi shown mean new algorithm call acer alternat cyclic elimin reduct algorithm

Graph Transformation and Designing Parallel Sparse Matrix Algorithms beyond Data Dependence Analysis

report improv can achiev appli machin learn techniqu particular reinforc learn dynam load balanc parallel applic the applic be consid paper coars grain data intens applic such applic put high pressur interconnect hardwar synchron load balanc complex heterogen network need fast flexibl adapt load balanc algorithm view parallel applic onest coordin game framework multiag reinforc learn use recent introduc multiag explor techniqu abl improv upon classic job farm approach the improv achiev limit comput communic overhead

Johan Parent

Katja Verbeeck

Jan Lemeire

Ann Nowe

Kris Steenhaut

Erik Dirkx

Adaptive Load Balancing of Parallel Applications with Multi-Agent Reinforcement Learning on Heterogeneous Systems

difficult solv design optim problem complex system use tradit comput method becaus complex simul process usual lead largescal comput therefor distribut comput technolog base decompositioncoordin theori has receiv much attent design engin this paper studi peertop collabor optim method base distribut comput technolog order examin flexibl optim new distribut collabor optim framework propos coordin method develop use deal conflict relat variabl among suboptim problem multiag base distribut comput environ implement the implement optim agent which corba technolog use implement communic between compon optim agent discuss detail two exampl use demonstr effici comput method reliabl flexibl multiag system

Caijun Xue

Hong Nie

Qingying Qiu

Peien Feng

A Peer-to-Peer Distributed Collaborative Optimization System

About this journal

Scientific Programming provides a forum for research results in, and practical experience with, software engineering environments, tools, languages, and models of computation aimed specifically at supporting scientific and engineering computing.

Journal profile

Meet the editorial board

Chief Editor, Professor Tramontana, is based at the University of Catania and his research primarily concerns the areas of software engineering and distributed systems.

Editor spotlight

Submit to Special Issue

We currently have a number of Special Issues open for submission. Special Issues highlight emerging areas of research within a field, or provide a venue for a deeper investigation into an existing research area.

Special Issues

Author guidelines

Editorial board

Databases and indexing

Scientific Programming

This Issue is now open for submissions.
Papers are published upon acceptance, regardless of the Special Issue publication date.