Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study

doi:10.1017/S0890060420000050

	Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study
	Huang, Weixin 1; Su, Xia 1; Wu, Mingbo 2; Yang, Lijing 1
刊名	AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING
	2020-05-01
卷号	34 期号:2 页码:233-247
关键词	Clustering color combination design experiment interactive evolutionary computation recommendation system
ISSN号	0890-0604
DOI	10.1017/S0890060420000050
通讯作者	Huang, Weixin(huangwx@tsinghua.edu.cn)
英文摘要	Design is a complicated and sophisticated process with numerous existing theories trying to describe it. To verify theories and quantitatively describe the design process, design experiment, and data analysis are crucial and inevitable. However, applying data analysis in the design experiment is tricky and design data is not fully utilized in many aspects. To explore the potential of design experiment data, this paper introduces data-driven research based on an interior design experiment, aiming to reveal the category and process of design by conducting data analysis, visualization, and recommendation. We introduce an interactive evolutionary computation (IEC) design experiment that deals with a simplified interior design task and has already been tested on 230 subjects. Using the data gathered during the experiment, we conduct data analysis and visualization involving methods including Holistic color interval and K-means clustering to show categories and processes in design. Additionally, we train a content-based recommendation system with experiment data to capture user preference and make the IEC system more efficient and intelligent. The analysis and visualization show clear design categories and capture an evident trend towards the final design outcome. The application of the recommendation system brings a prominent improvement to the IEC system. This research shows the great potential of the various data-driven methods in design research.
WOS关键词	NEXT-GENERATION ; SYSTEMS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	CAMBRIDGE UNIV PRESS
WOS记录号	WOS:000544963500009
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/162396]
专题	中国科学院地理科学与资源研究所
通讯作者	Huang, Weixin
作者单位	1.Tsinghua Univ, Sch Architecture, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Huang, Weixin,Su, Xia,Wu, Mingbo,et al. Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study[J]. AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING,2020,34(2):233-247.
APA	Huang, Weixin,Su, Xia,Wu, Mingbo,&Yang, Lijing.(2020).Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study.AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING,34(2),233-247.
MLA	Huang, Weixin,et al."Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study".AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING 34.2(2020):233-247.