Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 595

Reformat results as: short short into frame detailed detailed into frame

_id	caadria2021_044
id	caadria2021_044
authors	Wu, Shaoji
year	2021
title	3D Space Resilience Analysis of Commercial Complex - Beijing APM as an Example
doi	https://doi.org/10.52842/conf.caadria.2021.2.457
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 457-466
summary	Commercial complexes have played an increasingly important role in contemporary cities. Due to the occurrence of crowded people or equipment overhauls, some paths in a commercial complex may become impassable, which can be seen as disruptions to its spatial system. This paper provides a practical method to quantify the spatial resilience of a commercial complex taking Beijing APM as an example. This study can be divided into the following three steps. First, transforming the realistic spatial path system to a directed network model. Second, using topological, metric, and angular distance as edge weight to calculate the centrality and present its distribution. Third, using two disruption processes, randomized and attractor-guided strategy, evaluates the spatial networks resilience. There are three conclusions from this study. The first one is the process of disruption is non-linear, and there is a phase transition process when it reaches the critical threshold. The second one is the most efficient disruption method is the topological BC attractor-guided strategy. The last one is the resilience of a commercial complex, whose 3D spatial networks resilience is lower than the 2D spatial networks resilience by comparison with Duan and Lus (2013) study.
keywords	Resilience; Robustness; Network Secience; Commercial Complex
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ijac202119313
id	ijac202119313
authors	Saldana Ochoa, Karla; Ohlbrock, Patrick Ole; D’Acunto, Pierluigi; Moosavi, Vahid
year	2021
title	Beyond typologies, beyond optimization: Exploring novel structural forms at the interface of human and machine intelligence
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 3, 466–490
summary	This article presents a computer-aided design framework for the generation of non-standard structural forms in static equilibrium that takes advantage of the interaction between human and machine intelligence. The design framework relies on the implementation of a series of operations (generation, clustering, evaluation, selection, and regeneration) that allow to create multiple design options and to navigate in the design space according to objective and subjective criteria defined by the human designer. Through the interaction between human and machine intelligence, the machine can learn the nonlinear correlation between the design inputs and the design outputs preferred by the human designer and generate new options by itself. In addition, the machine can provide insights into the structural performance of the generated structural forms. Within the proposed framework, three main algorithms are used: Combinatorial Equilibrium Modeling for generating of structural forms in static equilibrium as design options, Self-Organizing Map for clustering the generated design options, and Gradient-Boosted Trees for classifying the design options. These algorithms are combined with the ability of human designers to evaluate non-quantifiable aspects of the design. To test the proposed framework in a real-world design scenario, the design of a stadium roof is presented as a case study.
keywords	Structural design, machine learning, topology, graphic statics, form-finding, Combinatorial Equilibrium Modeling, Self-Organizing Map, Gradient-Boosted Trees
series	journal
email
last changed	2024/04/17 14:29

_id	caadria2021_311
id	caadria2021_311
authors	Gu, Xiangshu, Tian, Shulin, Zhang, Baihui, Tong, Ziyu and Gan, Jingwen
year	2021
title	SECTIONMATRIX - Mapping Urban Form through Urban Sections
doi	https://doi.org/10.52842/conf.caadria.2021.2.599
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 599-608
summary	Most of the traditional studies on urban morphology are based on aerial views. However, the 2D plane model fails to describe the height information of buildings and the relation of buildings and the urban external space. An urban section is another map of an urban area. Through a series of continuous vertical urban slices, the city texture can be transformed into planar linear information containing height and width information. This paper proposes several indicators to describe a series of urban section slices and uses a three-dimensional coordinate mapping method Sectionmatrix to quantify and analyze the relation between the physical geometrical indicators and urban form from the section perspective. Through the case analysis of multiple residential blocks in Nanjing, China, the results showed that Sectionmatrix is convenient and efficient. Sectionmatrix relates the geometrical properties to the spatial characteristics of urban areas and provides a new way to classify, map and define building typologies. This new classification method reveals the tortuosity and complexity of residential blocks. By bridging the gap between quantity and form, the research also suggests other possible applications of Sectionmatrix as a control instrument and test framework for entire cities planning and design.
keywords	Urban Morphology; Urban Section; Sectionmatrix; Quantitative Analysis
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	sigradi2021_200
id	sigradi2021_200
authors	Karabagli, Kaan, Koc, Mustafa, Basu, Prithwish and As, Imdat
year	2021
title	A Machine Learning Approach to Translate Graph Representations into Conceptual Massing Models
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 191–202
summary	Machine learning (ML) has popular applications in domains involving image, video, text and voice. However, in architecture, image-based ML systems face challenges capturing the complexity of three-dimensional space. In this paper, we leverage a graph-based ML system that can capture the inherent topology of architectural conceptual designs and identify high-performing latent patterns within such designs. In particular, our goal is to translate architectural graph data into three-dimensional massing models. We are building on our prior ML work, where we, a. discovered latent topological features, b. composed building blocks into new designs, c. evaluated their feasibility, and d. explored Generative Adversarial (Neural) Networks (GAN)-generated design variations. We trained the ML system with architectural design data that we gathered from an online architectural design competition platform, translated them into machine-readable graph representations, and identified their essential subgraphs to develop novel compositions. In this paper, we explore how these novel designs (outputted in graph form), can be translated into three-dimensional architectural form. We present an ML approach to turn graph representations into functional volumetric massing models. The ultimate goal of the study is to develop an end-to-end pipeline to generate architectural design - from a graph representation to a fully developed conceptual proxy of a designed product. The research question is promising in automating conceptual design, and we believe the outcome can be relevant to other design disciplines as well.
keywords	Architectural design, machine learning, conceptual design, deep learning, artificial intelligence
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	cdrf2021_55
id	cdrf2021_55
authors	Shengyu Meng
year	2021
title	Exploring in the Latent Space of Design: A Method of Plausible Building Facades Images Generation, Properties Control and Model Explanation Base on StyleGAN2
doi	https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_6
source	Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)
summary	GAN has been widely applied in the research of architectural image generation. However, the quality and controllability of generated images, and the interpretability of model are still potential to be improved. In this paper, by implementing StyleGAN2 model, plausible building façade images could be generated without conditional input. In addition, by applying GANSpace to analysis the latent space, high-level properties could be controlled for both generated images and novel images outside of training set. At last, the generating and controlling process could be visualized with image embedding and PCA projection method, which could achieve unsupervised classification of generated images, and help to understand the correlation between the images and their latent vectors.
series	cdrf
email
last changed	2022/09/29 07:53

_id	ascaad2021_114
id	ascaad2021_114
authors	Houda, Maryam
year	2021
title	Materiality: Linking a Digital Material Framework with the Anthropological Hand
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 568-580
summary	While computers and digital technology have evolved over the years and are changing the way we design and construct, some have criticized the way in which human tactility and intuition with material has diminished at the cost of increasing productivity and efficiency. Although the digital culture that architecture is engaged with today has brought about complex forms that could not have been possible by hand, there is a rising question of the place of craft and a hand-brain coordination in design, and the notion of learning through making. This paper explores the benefits and limitations of digital design tools in light of physically exploring building materials and gaining tactile intuition. While digital tools investigate structural optimisation methods using a parametric design workflow, physical experiments deal with understanding the transitional state of mud and its dynamic properties. This research is interested in how information is learnt from materiality during the physical act of making and what tactile experimentation can offer that the digital space cannot. Three key areas are explored: geometry and parametric variation, material properties and morphogenic behavior, as well as structural optimization methods using density grids. Force-matter relations are investigated through exploring material parameters through digital and physical form-finding processes as a way of exploring the notion of re-introducing the hand and craft in the design process which may bring about novel ways of thinking and doing.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	ecaade2021_072
id	ecaade2021_072
authors	Jarzyna, Micha³
year	2021
title	Finding Optimal Path Planning Method for Building Navigation in BIM
doi	https://doi.org/10.52842/conf.ecaade.2021.2.031
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 31-38
summary	Building's spatial structure described in a BIM model can be used for retrieving the information required for determining the shortest path within the building. The matrix method and the visibility method are the two main ways of dividing space into prime factors. Both are widely used to find the shortest path. In order to compare the performance of both methods, several tests were carried out with various versions of the floorplan modification (room area, the surface of internal walls, distance between the entrance, and exit in a straight line and within the boundary marked by walls of the maze). The results revealed significant differences between the visibility graph and the matrix method.
keywords	BIM; Building information modeling; Facility management; FM; Routing in building
series	eCAADe
email
last changed	2022/06/07 07:52

_id	acadia21_354
id	acadia21_354
authors	Liu, Yulun; Lu, Yao; Akbarzadeh, Masoud
year	2021
title	Kerf Bending and Zipper-in Spatial Timber Tectonics
doi	https://doi.org/10.52842/conf.acadia.2021.354
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 354-361.
summary	Space frames are widely used in spatial constructions as they are lightweight, rigid, and efficient. However, when it comes to the complex and irregular spaces frames, they can be difficult to fabricate because of the uniqueness of the nodes and bars. This paper presents a novel timber space frame system that can be easily manufactured using 3-axis CNC machines, and therefore increase the ease of the design and construction of complex space frames. The form-finding of the space frame is achieved with the help of polyhedral graphic statics (PGS), and resulted form has inherent planarity which can be harnessed in the materialization of the structure. Inspired by the traditional wood tectonics kerf bending and zippers are applied when devising the connection details. The design approach and computational process of this system are described, and a test fabrication of a single node is made via 3-axis CNC milling and both physically and numerically tested. The structural performance shows its potentials for applications in large-scale spatial structures.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2021_333
id	caadria2021_333
authors	Ma, Chun Yu, Chan, Yan Yu Jennifer and Crolla, Kristof
year	2021
title	Expanding Bending-Active Bamboo Gridshell Structures' Design Solution Space Through Hybrid Assembly Systems
doi	https://doi.org/10.52842/conf.caadria.2021.1.331
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 331-340
summary	This paper discusses the development and testing of a novel design method for the low-tech construction of bending-active bamboo gridshell structures. It expands this typologys current design solution space by combining and building up on two common production methods for light-weight shell structures: 1) the lay-up method, typically used in bamboo architecture in which members are added one at a time, and 2) the flatbed method, in which a prefabricated equidistant flat grid without shear rigidity is propped up and deformed into its final doubly curved shape. The novel methodology expands the systems design solution space by incorporating singularities within the grid topology and by layering multiple separate grids. This allows for spatially radically different building geometries without loss of implementation workflow efficiency. A demonstrator design project, tested through a large-scale prototype model, is described to illustrate the possible spatially engaging architectural design opportunities presented by the novel approach.
keywords	Bending-active structures; Bamboo architecture; Shell structures; Low-tech fabrication; Form finding
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2021_191
id	caadria2021_191
authors	Shou, Xinyue, Chen, Pinyang and Zheng, Hao
year	2021
title	Predicting the Heat Map of Street Vendors from Pedestrian Flow through Machine Learning
doi	https://doi.org/10.52842/conf.caadria.2021.2.569
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 569-578
summary	Street vending is a recent policy advocated by city governments to support small and intermediate businesses in the post-pandemic period in China. Street vendors select their locations primarily based on their intuitions about the surrounding environment; they temporarily occupy popular locations that benefit their business. Taking the city of Chengdu as an example, this study aims to formulate the rules governing vendors location selection using machine learning and big data analysis techniques, thus identifying streets likely to become vital street markets. We propose a semantic segmentation method to construct heat maps that visualize and quantify the distribution of street vendors and pedestrians on public urban streets. The image-based generative adversarial network (GAN) is then trained to predict the vendors heat maps from the pedestrians heat map, finding the relationship between the locations of the vendors and the pedestrians. Our successful prediction of the vendors locations highlights machine learning techniques ability to quantify experience-based decision strategies. Moreover, suggesting potential marketing locations to vendors could help increase cities vitality.
keywords	Machine Learning; Big Data Analysis; Semantic Segmentation; Generative Adversarial Networks
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	ecaade2021_047
id	ecaade2021_047
authors	Zhang, Xiao, Yuan, Chao, Yang, Liu, Yu, Peiran, Ma, Yiwen, Qiu, Song, Guo, Zhe and Yuan, Philip F.
year	2021
title	Design and Fabrication of Formwork for Shell Structures Based on 3D-printing Technology
doi	https://doi.org/10.52842/conf.ecaade.2021.1.487
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 487-496
summary	Shell structure is a kind of structure using a small amount of materials to obtain a large-span multi-functional space. However, lots of formwork and scaffold materials are often wasted in the construction process. This paper focuses on the shell structure construction using robotic 3D printing PLA (an environmental friendly material) technology as the background. The author explores the possibility of 3D printing technology in shell construction from small scale models in different construction method, and gradually optimizes the shell template shape suitable for PLA material in full-scale construction. Finally, the research team chose the bending-active 3D printing type and completed the construction of three full-scale concrete shell molds. Under the guidance of professor Philippe Block, the research team finished the final 3D printing mold with optimized slicing and bending logic and successfully used it as the template mold to carry the tiles which proved the feasibility of this construction method.
keywords	Shell structure ; Formwork ; Geometric analysis; Form-finding; 3d printing
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2022_249
id	ecaade2022_249
authors	Carrasco Hortal, Jose, Hernandez Carretero, Sergi, Abellan Alarcon, Antonio and Bermejo Pascual, Jorge
year	2022
title	Algae, Gobiidae Fish and Insects that inspire Coastal Custodian Entities - Digital models for a real-virtual space using TouchDesigner
doi	https://doi.org/10.52842/conf.ecaade.2022.1.361
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 361–370
summary	At the beginning of the twenty-first century, a discipline at the intersection of digital art and science explores how natural and artificial species are affected, coexist, and feed back to humans based on multi-scalar hybrid models. They embody types of surveillance entities or non-human custodians, and serve as inspiration for another generation of designs produced ten years later, the case studies that are presented here. This paper explains the design and parametric fundamentals of a digital architecture installation at the University of Alicante (Spain 2021) using CNC models and the TouchDesigner programming environment. The installation contains a clan of technological-virtual hybrid species, non-human custodians, which: (a) strengthen the Proposal’s discourse on the recognition of legal identity of the Mar Menor lagoon (Southeast Spain); (b) incorporate reactive designs; (c) help raise awareness of the effect of human actions on the lagoon’s ecology and nearby streams. The viewpoint is not anthropocentric, because it adopts the perspective of the foraging fish species or the oxygen-seeking algae species, among others, in order to reveal the deterioration processes. In most cases, the result is a sort of synaesthetic conversation that interweaves light, sound, movement and data.
keywords	Human-Machine Interaction, TouchDesigner, Non-Human Custodian, Responsive Interface, Ethnography of Things
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2021_254
id	ecaade2021_254
authors	Eisenstadt, Viktor, Arora, Hardik, Ziegler, Christoph, Bielski, Jessica, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Comparative Evaluation of Tensor-based Data Representations for Deep Learning Methods in Architecture
doi	https://doi.org/10.52842/conf.ecaade.2021.1.045
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 45-54
summary	This paper presents an extended evaluation of tensor-based representations of graph-based architectural room configurations. This experiment is a continuation of examination of recognition of semantic architectural features by contemporary standard deep learning methods. The main aim of this evaluation is to investigate how the deep learning models trained using the relation tensors as data representation means perform on data not available in the training dataset. Using a straightforward classification task, stepwise modifications of the original training dataset and manually created spatial configurations were fed into the models to measure their prediction quality. We hypothesized that the modifications that influence the class label will not decrease this quality, however, this was not confirmed and most likely the latent non-class defining features make up the class for the model. Under specific circumstances, the prediction quality still remained high for the winning relation tensor type.
keywords	Deep Learning; Spatial Configuration; Semantic Building Fingerprint
series	eCAADe
email
last changed	2022/06/07 07:55

_id	ascaad2021_124
id	ascaad2021_124
authors	Eshaghi, Sarvin; Sepehr Afshar, Güzden Varinlioglu
year	2021
title	The Sericum Via: A Serious Game for Preserving Tangible and Intangible Heritage of Iran
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 306-316
summary	Efforts to preserve cultural heritage have continued throughout history, and currently use game technology. Serious games, with their audio-visual features make it possible for players to absorb and retain the often rather arid data of heritage. Furthermore, such technology facilitates the transmission of heritage globally amongst remote people, without the need to commute personally. Exploring the literature, we noted a lack of local game culture in Iran, and in the Middle East more broadly. This region is limited in terms of the existing global game industry, and the introduction of its culture to the world depends on the global market. This ascertains the paper's research problem: the need for more local games in the field to promote local historical culture. Hence, the paper aims to preserve and disseminate the tangible and intangible cultural heritage of its focus area, Iran’s Silk Roads and its caravanserais, by developing and testing a serious game named The Sericum Via. It has a non-linear narrative, engaging the player in a long journey visiting the Safavid caravanserais on the Silk Roads, using their detailed information. The game's text-based and strategic environment demands decision-making skills throughout the game and is challenging enough to make the player revisit the game frequently.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	acadia21_232
id	acadia21_232
authors	Goepel, Garvin; Crolla, Kristof
year	2021
title	Augmented Feedback
doi	https://doi.org/10.52842/conf.acadia.2021.232
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 232-237.
summary	Augmented Reality (AR) has the potential to create a paradigm shift in the production of architecture. This paper discusses the assembly and evaluation of a bamboo prototype installation aided by holographic instructions. The case study is situated within the framework of AR-driven computational design implementation methods that incorporate feedback loops between the as-built and the digital model. The prototype construction aims to contribute to the ongoing international debate on architectural applications of digital technology and computational design tools and on the impact these have on craftsmanship and architecture fabrication. The case study uses AR-aided construction techniques to augment existing bamboo craftsmanship in order to expand its practically feasible design solution space. Participating laypersons were challenged to work at the interface of technology and material culture and engage with both latest AR systems and century-old bamboo craft. This paper reflects on how AR tracking can be used to create a constant feedback loop between as-built installations and digitally designed source models and how this allows for the real-time assessment of design fidelity and deviations. The case study illustrates that this is especially advantageous when working with naturally varying materials, like bamboo, whose properties and behaviour cannot straightforwardly be accurately simulated digitally. The paper concludes by discussing how augmented feedback loops within the fabrication cycle can facilitate real-time refinement of digital simulation tools with the potential to save time, cost, and material. The augmentation of onsite available skills facilitates the democratisation of non-standard architecture design production.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ascaad2021_039
id	ascaad2021_039
authors	Heydari, Maziar; Mohammadjavad Mahdavinejad, Khosro Daneshjoo
year	2021
title	Utilizing Behavioral Agent-Based Modeling in an Automated Integrative Design Process
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 32-42
summary	Developing shift in architectural practice from previously exercised to late computational methods struggles to harmonize the concentration and consolidation between physical and humane aspects of a project or even the very thinking mechanism itself. Integrating Design workflow with the emerging simulation environment of agent-based modeling (ABM) in the complex architectural process can help us formulate a non-linear method. In this method, various complex design aspects such as humans' socio-behavioral attributes and structural complexities can be utilized to render an evolving design profile. Employing ABM in the design process enables us to evaluate complex problems using node-based tools to generate complicated simulation and exercise an adequate approach.
series	ASCAAD
email
last changed	2021/08/09 13:11

_id	caadria2021_166
id	caadria2021_166
authors	Hu, Wei
year	2021
title	The experiment of neural network on the cognition of style
doi	https://doi.org/10.52842/conf.caadria.2021.2.061
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 61-70
summary	This paper introduces a method to obtain quantified style description vector which is for computer analysis input by using image style classification task. In the experiment, 3331 architectural photos of three styles obtained by crawling and filtering were used as training data. A deep convolutional neural network was trained to map architectural images to high-dimensional feature space, and then the high-dimensional style description vector was used to output the measurement results of style cognition with fully connected neural network. Tested by test data-set of 371 architectural pictures, the accuracy rate of style cognition reached more than 80%. The neural network using architectural data training was applied to the style cognition of non-architectural objects, high accuracy rate was also achieved, it proved that this quantified style description vector did include the information about style cognition to some extent instead of simply classification. Finally, the similarities and differences between the cognitive characteristics of style of neural network and human beings are investigated.
keywords	deep neural network; style cognition experiment; eye tracker
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	ecaade2021_148
id	ecaade2021_148
authors	Mintrone, Alessandro and Erioli, Alessio
year	2021
title	Training Spaces - Fostering machine sensibility for spatial assemblages through wave function collapse and reinforcement learning
doi	https://doi.org/10.52842/conf.ecaade.2021.1.017
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 17-26
summary	This research explores the integration of Deep Reinforcement Learning (RL) and a Wave Function Collapse (WFC) algorithm for a goal-driven, open-ended generation of architectural spaces. Our approach binds RL to a distributed network of decisions, unfolding through three key steps: the definition of a set of architectural components (tiles) and their connectivity rules, the selection of the tile placement location, which is determined by the WFC, and the choice of which tile to place, which is performed by RL. The act of thinking becomes granular and embedded in an iterative process, distributed among human and non-human cognitions, which constantly negotiate their agency and authorial status. Tools become active agents capable of developing their own sensibility while controlling specific spatial conditions. Establishing an interdependency with the human, that engenders the design patterns and becomes an indispensable prerequisite for the exploration of the generated design space, exceeding human or machinic reach alone.
keywords	Reinforcement Learning; Machine Learning; Proximal Policy Optimization; Assemblages; Wave Function Collapse
series	eCAADe
email
last changed	2022/06/07 07:58

_id	sigradi2021_220
id	sigradi2021_220
authors	Pupo, Regiane, Casarin, Vanessa, Querne, Gabriel, Adriano, Larissa, Pfleger, Mariana and Perin, Venâncio
year	2021
title	The Use of Digital Fabrication as a Support to the Production of a Spatial Orientation Model at Santa Catarina Federal University
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 1199–1210
summary	The aim of this research project is to build and evaluate a model supported by digital technologies to help spatial orientation in the Federal University of Santa Catarina campus. The process explored a people-centered solution, based on Design Thinking, to answer the outlined research question regarding if a scale model supported by digital tools could help users in their wayfinding process in the campus. The methodology is defined as a non-linear process that analyzes user’s needs. Through its three main phases: immersion (problems identification), ideation (solution findings) and prototyping (desired solution materialization) the research explores digital fabrication tools as a design support. At the same time, results showed that a model supported by digital technologies and other tools such as QR Code solutions to point directions would help campus users to easily find their destination during wayfinding process.
keywords	Orientaçao especial, wayfinding, Fabricaçao digital, impressao 3D
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	ijac202119310
id	ijac202119310
authors	Schwartz, Yair; Raslan, Rokia; Korolija, Ivan; Mumovic, Dejan
year	2021
title	A decision support tool for building design: An integrated generative design, optimisation and life cycle performance approach
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 3, 401–430
summary	Building performance evaluation is generally carried out through a non-automated process, where computational models are iteratively built and simulated, and their energy demand is calculated. This study presents a computational tool that automates the generation of optimal building designs in respect of their Life Cycle Carbon Footprint (LCCF) and Life Cycle Costs (LCC). This is achieved by an integration of three computational concepts: (a) A designated space-allocation generative-design application, (b) Using building geometry as a parameter in NSGA-II optimization and (c) Life Cycle performance (embodied carbon and operational carbon, through the use of thermal simulations for LCCF and LCC calculation). Examining the generation of a two-storey terrace house building, located in London, UK, the study shows that a set of building parameters combinations that resulted with a pareto front of near-optimal buildings, in terms of LCCF and LCC, could be identified by using the tool. The study shows that 80% of the optimal building’s LCCF are related to the building operational stage (o= 2), while 77% of the building’s LCC is related to the initial capital investment (o= 2). Analysis further suggests that space heating is the largest contributor to the building’s emissions, while it has a relatively low impact on costs. Examining the optimal building in terms compliance requirements (the building with the best operational performance), the study demonstrated how this building performs poorly in terms of Life Cycle performance. The paper further presents an analysis of various life-cycle aspects, for example, a year-by-year performance breakdown, and an investigation into operational and embodied carbon emissions.
keywords	Generative design, genetic algorithms, thermal simulation, life cycle, carbon, LCA, NSGA-II, building performance
series	journal
email
last changed	2024/04/17 14:29

For more results click below: