Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications

Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications

Scientific workflow is a valuable tool for various complicated large-scale data processing applications. In recent years, the increasingly growing number of scientific processes available necessitates the development of recommendation techniques to provide automatic support for modelling scientific...

Full description

Bibliographic Details
Main Authors: Yiping Wen, Junjie Hou, Zhen Yuan, Dong Zhou
Format: Article
Language:English
Published: Hindawi-Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/4129063
id doaj-64059002b74447f3a31140109b0f22bb
record_format Article
spelling doaj-64059002b74447f3a31140109b0f22bb2020-11-25T02:06:32ZengHindawi-WileyComplexity1076-27871099-05262020-01-01202010.1155/2020/41290634129063Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex ApplicationsYiping Wen0Junjie Hou1Zhen Yuan2Dong Zhou3School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaScientific workflow is a valuable tool for various complicated large-scale data processing applications. In recent years, the increasingly growing number of scientific processes available necessitates the development of recommendation techniques to provide automatic support for modelling scientific workflows. In this paper, with the help of heterogeneous information network (HIN) and tags of scientific workflows, we organize scientific workflows as a HIN and propose a novel scientific workflow similarity computation method based on metapath. In addition, the density peak clustering (DPC) algorithm is introduced into the recommendation process and a scientific workflow recommendation approach named HDSWR is proposed. The effectiveness and efficiency of our approach are evaluated by extensive experiments with real-world scientific workflows.http://dx.doi.org/10.1155/2020/4129063
collection DOAJ
language English
format Article
sources DOAJ
author Yiping Wen
Junjie Hou
Zhen Yuan
Dong Zhou
spellingShingle Yiping Wen
Junjie Hou
Zhen Yuan
Dong Zhou
Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
Complexity
author_facet Yiping Wen
Junjie Hou
Zhen Yuan
Dong Zhou
author_sort Yiping Wen
title Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
title_short Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
title_full Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
title_fullStr Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
title_full_unstemmed Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
title_sort heterogeneous information network-based scientific workflow recommendation for complex applications
publisher Hindawi-Wiley
series Complexity
issn 1076-2787
1099-0526
publishDate 2020-01-01
description Scientific workflow is a valuable tool for various complicated large-scale data processing applications. In recent years, the increasingly growing number of scientific processes available necessitates the development of recommendation techniques to provide automatic support for modelling scientific workflows. In this paper, with the help of heterogeneous information network (HIN) and tags of scientific workflows, we organize scientific workflows as a HIN and propose a novel scientific workflow similarity computation method based on metapath. In addition, the density peak clustering (DPC) algorithm is introduced into the recommendation process and a scientific workflow recommendation approach named HDSWR is proposed. The effectiveness and efficiency of our approach are evaluated by extensive experiments with real-world scientific workflows.
url http://dx.doi.org/10.1155/2020/4129063
work_keys_str_mv AT yipingwen heterogeneousinformationnetworkbasedscientificworkflowrecommendationforcomplexapplications
AT junjiehou heterogeneousinformationnetworkbasedscientificworkflowrecommendationforcomplexapplications
AT zhenyuan heterogeneousinformationnetworkbasedscientificworkflowrecommendationforcomplexapplications
AT dongzhou heterogeneousinformationnetworkbasedscientificworkflowrecommendationforcomplexapplications
_version_ 1715570121744842752

Similar Items