Web-based multiuser 3D room layout system using interactive evolutionary computation with conjoint analysis

Ryuya Akase, Yoshihiro Okada

Research output: Contribution to conferencePaperpeer-review

10 Citations (Scopus)

Abstract

In this paper, the authors propose a web-based 3D room layout system supporting the user preferences. To simulate the furniture and office layout, 3D layout systems are commonly used. However, generating 3D room layouts is a very time-consuming task because it needs complicated manual operations and much technical knowledge. Therefore, we need any tools that help us to easily generate 3D room layouts. The authors have been developing a 3D room layout system that has the following features: 1. Analysis of user preference (Conjoint analysis). 2. Optimization of 3D room layouts based on Interactive Evolutionary Computation (IEC). Although IEC is useful for applying the user preferences to the solution, there is a problem about the tiredness of user evaluation operations of IEC process because of the large search space of solutions. To cope with this problem, the authors adopted a prediction method for shrinking the search space and employed a multiscreen interface for reducing the tiredness of each user. In this paper, the authors also justify the usefulness of the system from the experimental results.

Original languageEnglish
Pages178-187
Number of pages10
DOIs
Publication statusPublished - Aug 5 2014
Event7th International Symposium on Visual Information Communication and Interaction, VINCI 2014 - Sydney, Australia
Duration: Aug 5 2014Aug 8 2014

Other

Other7th International Symposium on Visual Information Communication and Interaction, VINCI 2014
CountryAustralia
CitySydney
Period8/5/148/8/14

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Web-based multiuser 3D room layout system using interactive evolutionary computation with conjoint analysis'. Together they form a unique fingerprint.

Cite this