Standard

Addressing design preferences via auto-associative connectionist models : Application in sustainable architectural Façade design. / Chatzikonstantinou, Ioannis; Sariyildiz, Sevil.

In: Automation in Construction, Vol. 83, 2017, p. 108-120.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

BibTeX

@article{e57b50451c9246459659b7a34c55cb0c,
title = "Addressing design preferences via auto-associative connectionist models: Application in sustainable architectural Fa{\cc}ade design",
abstract = "Truly successful designs are characterized by both satisfaction of design goals and the presence of desirable physical features. Experienced design professionals are able to exercise their cognition to satisfy both aspects to a high degree. However, complex design tasks represent challenges for human cognition, and as such computational decision support systems emerge as a relevant topic. We present a computational decision support framework for treating preferences related to physical design features. The proposed framework is based on autoassociative machine learning models that inductively learn relationships between design features characterizing highly performing designs. The knowledge matter to be learned is derived through multi-objective stochastic optimization. The resulting auto-associative models are excited with a preference vector containing a favorable composition of design features. The models are able to alleviate those relationships that result in shortcomings of performance. The model thus outputs well performing design solution, where preferences pertaining to physical features are also satisfied, to the extent possible. The paper focuses on the applicability of the proposed approach in architectural design, as an exceptional example of complex design, discusses methods to evaluate model performance, and validates the proposed method through an application focusing on the design of a sustainable fa{\cc}ade.",
keywords = "Decision Support, Auto-associative model, Preferences, Cognition, Architecture, Energy, Daylight, Facade design",
author = "Ioannis Chatzikonstantinou and Sevil Sariyildiz",
year = "2017",
doi = "10.1016/j.autcon.2017.08.007",
language = "English",
volume = "83",
pages = "108--120",
journal = "Automation in Construction",
issn = "0926-5805",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Addressing design preferences via auto-associative connectionist models

T2 - Automation in Construction

AU - Chatzikonstantinou, Ioannis

AU - Sariyildiz, Sevil

PY - 2017

Y1 - 2017

N2 - Truly successful designs are characterized by both satisfaction of design goals and the presence of desirable physical features. Experienced design professionals are able to exercise their cognition to satisfy both aspects to a high degree. However, complex design tasks represent challenges for human cognition, and as such computational decision support systems emerge as a relevant topic. We present a computational decision support framework for treating preferences related to physical design features. The proposed framework is based on autoassociative machine learning models that inductively learn relationships between design features characterizing highly performing designs. The knowledge matter to be learned is derived through multi-objective stochastic optimization. The resulting auto-associative models are excited with a preference vector containing a favorable composition of design features. The models are able to alleviate those relationships that result in shortcomings of performance. The model thus outputs well performing design solution, where preferences pertaining to physical features are also satisfied, to the extent possible. The paper focuses on the applicability of the proposed approach in architectural design, as an exceptional example of complex design, discusses methods to evaluate model performance, and validates the proposed method through an application focusing on the design of a sustainable façade.

AB - Truly successful designs are characterized by both satisfaction of design goals and the presence of desirable physical features. Experienced design professionals are able to exercise their cognition to satisfy both aspects to a high degree. However, complex design tasks represent challenges for human cognition, and as such computational decision support systems emerge as a relevant topic. We present a computational decision support framework for treating preferences related to physical design features. The proposed framework is based on autoassociative machine learning models that inductively learn relationships between design features characterizing highly performing designs. The knowledge matter to be learned is derived through multi-objective stochastic optimization. The resulting auto-associative models are excited with a preference vector containing a favorable composition of design features. The models are able to alleviate those relationships that result in shortcomings of performance. The model thus outputs well performing design solution, where preferences pertaining to physical features are also satisfied, to the extent possible. The paper focuses on the applicability of the proposed approach in architectural design, as an exceptional example of complex design, discusses methods to evaluate model performance, and validates the proposed method through an application focusing on the design of a sustainable façade.

KW - Decision Support

KW - Auto-associative model

KW - Preferences

KW - Cognition

KW - Architecture

KW - Energy

KW - Daylight

KW - Facade design

U2 - 10.1016/j.autcon.2017.08.007

DO - 10.1016/j.autcon.2017.08.007

M3 - Article

VL - 83

SP - 108

EP - 120

JO - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

ER -

ID: 51431272