Please use this identifier to cite or link to this item: http://hdl.handle.net/10316/42051
Title: Clustering of architectural floor plans: A comparison of shape representations
Authors: Rodrigues, Eugénio
Sousa-Rodrigues, David
Teixeira de Sampayo, Mafalda
Gaspar, Adélio Rodrigues
Gomes, Álvaro
Henggeler Antunes, Carlos
Keywords: Unsupervised clustering
Floor plan designs
Hierarchical clustering
Shape representation
Descriptors
Issue Date: Aug-2017
Publisher: Elsevier
Abstract: Generative design methods are able to produce a large number of potential solutions of architectural floor plans, which may be overwhelming for the decision-maker to cope with. Therefore, it is important to develop tools which organise the generated data in a meaningful manner. In this study, a comparative analysis of four architectural shape representations for the task of unsupervised clustering is presented. Three of the four shape representations are the Point Distance, Turning Function, and Grid-Based model approaches, which are based on known descriptors. The fourth proposed representation, Tangent Distance, calculates the distances of the contour's tangents to the shape's geometric centre. A hierarchical agglomerative clustering algorithm is used to cluster a synthetic dataset of 72 floor plans. When compared to a reference clustering, despite good perceptual results with the use of the Point Distance and Turning Function representations, the Tangent Distance descriptor (Rand index of 0.873) provides the best results. The Grid-Based descriptor presents the worst results.
Peer review: yes
URI: http://hdl.handle.net/10316/42051
DOI: 10.1016/j.autcon.2017.03.017
ISSN: 0926-5805
Publisher Version: http://www.sciencedirect.com/science/article/pii/S0926580517302601
Appears in Collections:FCTUC Eng.Mecânica - Artigos em Revistas Internacionais

Files in This Item:
File Description SizeFormat 
Rodrigues et al - 2017 - Clustering of architectural floor plans_a comparison of shape representations.pdfInternational Journal Article5.85 MBAdobe PDFView/Open


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.