Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 2023 Annual Modeling and Simulation Conference, ANNSIM 2023 |
| Herausgeber/-innen | Maria Julia Blas, Gonzalo Alvarez |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 496-507 |
| Seitenumfang | 12 |
| ISBN (elektronisch) | 9781713873280 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | Annual Modeling and Simulation Conference, ANNSIM 2023 - Hamilton, Kanada Dauer: 23 Mai 2023 → 26 Mai 2023 |
Abstract
A computational framework is proposed to quantify the aesthetic experience of perceiving architecture. This framework is used as the criterion for navigating a design solution space. A parametric model's solution space is represented as a set of computer-generated images. We utilize computer vision to recognize parts and the relations between parts and the whole. These values are inserted into an adaptation of Birkhoff's aesthetic measure formula, calibrated via crowdsourced hedonic response. An artificial neural network (ANN) model is trained to predict the hedonic response of images using (A) parts relations as inputs and (B) the average hedonic responses as target outputs. The prediction of the ANN is used as a fitness function for optimization. The same public evaluates the parametric model's output to compare the ANN model's effectiveness in predicting their response. The method is useful in translating formal qualities into quantities and navigating solution spaces, especially with surrogate models.
ASJC Scopus Sachgebiete
- Entscheidungswissenschaften (insg.)
- Informationssysteme und -management
- Mathematik (insg.)
- Steuerung und Optimierung
- Mathematik (insg.)
- Modellierung und Simulation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 2023 Annual Modeling and Simulation Conference, ANNSIM 2023. Hrsg. / Maria Julia Blas; Gonzalo Alvarez. Institute of Electrical and Electronics Engineers Inc., 2023. S. 496-507.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Aesthetics as a Criterion
T2 - Annual Modeling and Simulation Conference, ANNSIM 2023
AU - Sardenberg, Victor
AU - Becker, Mirco
PY - 2023
Y1 - 2023
N2 - A computational framework is proposed to quantify the aesthetic experience of perceiving architecture. This framework is used as the criterion for navigating a design solution space. A parametric model's solution space is represented as a set of computer-generated images. We utilize computer vision to recognize parts and the relations between parts and the whole. These values are inserted into an adaptation of Birkhoff's aesthetic measure formula, calibrated via crowdsourced hedonic response. An artificial neural network (ANN) model is trained to predict the hedonic response of images using (A) parts relations as inputs and (B) the average hedonic responses as target outputs. The prediction of the ANN is used as a fitness function for optimization. The same public evaluates the parametric model's output to compare the ANN model's effectiveness in predicting their response. The method is useful in translating formal qualities into quantities and navigating solution spaces, especially with surrogate models.
AB - A computational framework is proposed to quantify the aesthetic experience of perceiving architecture. This framework is used as the criterion for navigating a design solution space. A parametric model's solution space is represented as a set of computer-generated images. We utilize computer vision to recognize parts and the relations between parts and the whole. These values are inserted into an adaptation of Birkhoff's aesthetic measure formula, calibrated via crowdsourced hedonic response. An artificial neural network (ANN) model is trained to predict the hedonic response of images using (A) parts relations as inputs and (B) the average hedonic responses as target outputs. The prediction of the ANN is used as a fitness function for optimization. The same public evaluates the parametric model's output to compare the ANN model's effectiveness in predicting their response. The method is useful in translating formal qualities into quantities and navigating solution spaces, especially with surrogate models.
KW - Artificial Neural Networks
KW - Computational Aesthetics
KW - Computer Vision
UR - http://www.scopus.com/inward/record.url?scp=85165425554&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85165425554
SP - 496
EP - 507
BT - Proceedings of the 2023 Annual Modeling and Simulation Conference, ANNSIM 2023
A2 - Blas, Maria Julia
A2 - Alvarez, Gonzalo
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 May 2023 through 26 May 2023
ER -