A review of the use of examples for automating architectural design tasks

Sönmez, Nizam Onur

doi:10.1016/j.cad.2017.10.005

Cited by 49 publications

(33 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning models were used to automatically learn features and classifiers at once by error backpropagation, adjusting the layers' importance depending on the problem. Then, similarity analysis techniques were used to construct an efficient case retrieval system based on the feeding samples [19].…”

Section: Literature Reviewmentioning

confidence: 99%

Urban Morphological Feature Extraction and Multi-Dimensional Similarity Analysis Based on Deep Learning Approaches

Cai

Guo²,

Zhang

et al. 2021

Sustainability

View full text Add to dashboard Cite

The study of urban morphology contributes to the evolution of cities and sustainable development. Urban morphological feature extraction and similarity analysis represents a practical framework in many studies to interpret and introduce the current built environment to aid in proposing novel designs. In conventional methods, morphological features are represented based on qualitative descriptions, symbolical interpretation, or manually selected indicators. However, these methods could cause subjective bias and limit the generalizability. This study proposes a hybrid data-driven approach to support quantitative morphological descriptions and multi-dimensional similarity analysis for urban design decision-making and to further morphology-related studies using information abundance via a deep-learning approach. We constructed a dataset of 3817 residential plots with geometrical and related infrastructure information. A deep convolutional neural network, GoogLeNet, was implemented with the plots’ figure–ground images, by quantifying the morphological features into 2048-dimensional feature vectors. We conducted a similarity analysis of the plots by calculating the Euclidean distance between the high-dimensional feature vectors. Then, a comparison study was performed by retrieving cases based on the plot shape and plots with buildings separately. The proposed method considers the overall characteristics of the urban morphology and social infrastructure situations for similarity analysis. This method is flexible and effective. The proposed framework indicates the feasibility and potential of integrating task-oriented information to introduce custom and adequate references via deep learning methods, which could support decision making and association studies on morphology with urban consequences. This work could serve as a basis for further typo-morphology studies and other morphology-related ecological, social, and economic studies for sustainable built environments.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Urban Morphological Feature Extraction and Multi-Dimensional Similarity Analysis Based on Deep Learning Approaches

Cai

Guo²,

Zhang

et al. 2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…Various approa-ches have been developed to use representations of architectural examples for artificially tackling architectural design tasks. One of the methods that can be used in this process is Shape Grammar (SG) formalism, which comprises a set of shape rules that can be applied consecutively to modify design representations (Sönmez, 2018). SG studies can be categorized into two groups: analytical and original variants (Duarte, 2005).…”

Section: Literature Reviewmentioning

confidence: 99%

A Grammar Based Methodology to Support the Adaptive Reuse of Historic Buildings: The Case Study of the Sobrado Building Type

Paulino

Napolitano

Ligler

et al. 2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The historical center of São Luís is host to a diverse historic and urban ensemble, reminiscent of the 18th and 19th centuries. The architectural typology which can be found there illustrates the strong influence drawn from the Portuguese style known as Pombalino, developed during the reconstruction process of Lisbon after the 1755 earthquake. Due to the historical relevance of these buildings which encapsulate this period in time, it is important to preserve and maintain the buildings located in this region. Adaptive reuse projects have an important role to play in preserving architectural ensembles like this. The first part of the adaptive process is to document and understand the original configuration of the building with the aim of maintaining the elements with historical relevance. Therefore, this project proposes the use of a shape grammar approach to analyze floor plans, aiming to further contribute to adaptive reuse projects for ‘Sobrado’ buildings. The process focuses specifically on a case study building and aims to document and identify the specific placement of elements in the floor plan in an effort to provide a deeper understanding of future adaptive reuse.

show abstract

“…The aim is to share and re-use design knowledge by capturing and storing design intent, rationale and history in a computer-based system (Baxter et al , 2008). These systems are capable of retaining the cases as readymade integrated solutions, especially for repetitive building types, by making the design process more effective by facilitating the retrieval of precedents and make knowledge available for inexperienced designers and students (Sönmez, 2018). Some of these systems (such as Archie III) are capable of facilitating double-loop learning (Love et al , 2016) by incorporating lessons learnt during the post-occupancy evaluation surveys which normally would not reach designers of the project (Gross et al , 1994).…”

Section: Literature Reviewmentioning

confidence: 99%

“…The evolution of digital design as a unique field of design knowledge, supported by new technologies, provided new insights into the design re-use process Oxman (2010). Computer vision and BIM can provide large, semantically labelled design repositories for the built environment (Sönmez, 2018). For example, Hua (2014) developed a commercial CBR software: TRAMMA programme, which is capable of storing and retrieving the 3D models of buildings to facilitate CBR use along with BIM during building design.…”

Section: Literature Reviewmentioning

confidence: 99%

“…An average designer, whether consciously or subconsciously, draws from an ensemble of internal and external previously designed artefacts or components (Fruchter and Demian, 2002; Gunduz and Yetisir, 2016). Designers retrieve existing solutions that historically solved similar problems, examine such existing design solutions and reflect on how they could be applied to the current design problem under scrutiny (Sönmez, 2018) through various means, to ultimately adopt, adapt with major or minor revisions or even reject the proposed solutions (Maher and Pu, 1997; Yu et al , 2012). Design scholars refer this process as “design re-use”.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design re-use: critical application of healthcare building design evidence

Wanigarathna

Sherratt

Price

et al. 2019

ECAM

View full text Add to dashboard Cite

Purpose The re-use of good design solutions is a key source of evidence and knowledge in the design of healthcare buildings. However, due to the unique nature of healthcare built environments, the critical application of this evidence is of paramount importance. The purpose of this paper is to investigate the features of such critical application and identify the aspects that need to be considered during the re-use of good designs. Design/methodology/approach Data from three case studies of hospital designs in the UK were used to explore the processes behind the adaption and re-use of design solutions during the design of healthcare buildings. Data were thematically analysed to distinguish the aspects that should be carefully compared and contrasted during design re-use. Findings Existing designs of healthcare buildings should be captured and evaluated along with: patient demographics, care models of the hospital, other local departmental needs and facility operational aspects in order to ensure the effectiveness of re-use. In addition, properly introducing the design to the users is also a part of successful design re-use. Research limitations/implications The findings of this research were integrated into a framework to support healthcare designers on the effective re-use of good designs. This data-driven framework could be validated further with design practitioners. Further, this research relied on memory recall of the interviewees and the accuracy and completeness of documentary records. Practical implications This research provides details of how healthcare built environment designs are embedded in project-unique circumstances. The results could therefore be used to develop meaningful and informative evaluation mechanisms for new and re-used healthcare building design features. Originality/value This research extends the understanding of the critical application of healthcare design evidence, by explaining how healthcare design solutions should be evaluated during the design process.

show abstract

A review of the use of examples for automating architectural design tasks

Cited by 49 publications

References 80 publications

Urban Morphological Feature Extraction and Multi-Dimensional Similarity Analysis Based on Deep Learning Approaches

Urban Morphological Feature Extraction and Multi-Dimensional Similarity Analysis Based on Deep Learning Approaches

A Grammar Based Methodology to Support the Adaptive Reuse of Historic Buildings: The Case Study of the Sobrado Building Type

Design re-use: critical application of healthcare building design evidence

Contact Info

Product

Resources

About