Content mining to support design

Seifu Chonde, Soundar Rajan Tirupatikumara, Joey Storer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In this paper, we introduce a methodology that makes use of a large number of journal articles to support the design problem. In our methodology we discuss tools to determine proper content in individual citations, link the content in individual and across multiple citations to develop a network, and subsequently use network science to describe the topology and evolution of the network. We label these steps Reading, Assembly, and Interpretation, respectively. We develop a tripartite design network structure and discuss network partitioning and projection into unipartite and bipartite networks for visualization. The chemical design problem is used as a design paradigm with an open access subset of over 700,000 journal articles. In a chemotherapy case study, the most frequent drugs, uses of these drugs, and the distributions of these drugs are discussed. Network science metrics and algorithms are introduced to investigate network topology and evolution. Finally, we conclude by discussing other applications of this work.

Original languageEnglish (US)
Title of host publicationIIE Annual Conference and Expo 2015
PublisherInstitute of Industrial Engineers
Pages1672-1681
Number of pages10
ISBN (Electronic)9780983762447
StatePublished - Jan 1 2015
EventIIE Annual Conference and Expo 2015 - Nashville, United States
Duration: May 30 2015Jun 2 2015

Publication series

NameIIE Annual Conference and Expo 2015

Other

OtherIIE Annual Conference and Expo 2015
CountryUnited States
CityNashville
Period5/30/156/2/15

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Content mining to support design'. Together they form a unique fingerprint.

Cite this