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 620

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

_id	caadria2022_42
id	caadria2022_42
authors	Chen, Jielin and Stouffs, Rudi
year	2022
title	Robust Attributed Adjacency Graph Extraction Using Floor Plan Images
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 385-394
doi	https://doi.org/10.52842/conf.caadria.2022.2.385
summary	Architectural design solutions are intrinsically structured information with a broad range of interdependent scopes. Compared to conventional 2D Euclidean data such as orthographic drawings and perspectives, non-Euclidean data (e.g., attributed adjacency graphs) can be more effective and accurate for representing 3D architectural design information, which can be useful for numerous design tasks such as spatial analysis and reasoning, and practical applications such as floor plan parsing and generation. Thus, getting access to a matching attributed adjacency graph dataset of architectural design becomes a necessity. However, the task of conveniently acquiring attributed adjacency graphs from existing architectural design solutions still remains an open challenge. To this end, this project leverages state-of-the-art image segmentation techniques using an ensemble learning scheme and proposes an end-to-end framework to efficiently extract attributed adjacency graphs from floor plan images with diverse styles and varied levels of complexity, aiming at addressing generalization issues of existing approaches. The proposed graph extraction framework can be used as an innovative tool for advancing design research infrastructure, with which we construct a large-scale attributed adjacency graph dataset of architectural design using floor plan images retrieved in bulk. We have open sourced our code and dataset.
keywords	attributed adjacency graph, floor plan segmentation, ensemble learning, architectural dataset, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_153
id	ecaade2022_153
authors	Zhong, Ximing, Fricker, Pia, Yu, Fujia, Tan, Chuheng and Pan, Yuzhe
year	2022
title	A Discussion on an Urban Layout Workflow Utilizing Generative Adversarial Network (GAN) - With a focus on automatized labeling and dataset acquisition
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 2, Ghent, 13-16 September 2022, pp. 583–592
doi	https://doi.org/10.52842/conf.ecaade.2022.2.583
summary	Deep Learning (DL) has recently gained widespread attention in the automation of urban layout processes. This study proposes a rule-based and Generative Adversarial Network (GAN) workflow to automatically select and label urban datasets to train customized GAN models for the generation of urban layout proposals. The developed workflow automatically collects and labels urban typology samples from open-source maps. Furthermore, it controls the results of the GAN process with labels and provides real-time urban layout suggestions based on a co-design process. The conducted case study shows that the average value of the GAN results, trained from an automatically generated dataset, meets the site's requirements. The developed co-design strategy allows the architect to control the GAN process and perform iterations on urban layouts. The research addresses the research gap in GAN applications in the field of urban design and planning. Many studies have demonstrated that training the (GAN) model by labeling enables machines to learn urban morphological features and urban layout logic. However, two research gaps remain: (1) The manual filtering of GAN urban sample datasets to fit site-specific design requirements is very time-consuming. (2) Without a suitable data labeling method, it is difficult to manage the GAN process in such a manner to facilitate the meeting of overriding design requirements.
keywords	Deep Learning, Generative Adversarial Network (GAN), Urban Layout Process, Automatic Dataset Construction, Co-design
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_272
id	caadria2022_272
authors	Dong, Zhiyong
year	2022
title	Perceiving Fabric Immersed in Time, an Exploration of Urban Cognitive Capabilities of Neural Networks
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 263-272
doi	https://doi.org/10.52842/conf.caadria.2022.1.263
summary	City develops gradually with the lapse of time. Cities, as a ‚container‚, are injected new urban elements along the trajectory of the times and the progress of human civilization, constructing the historical structures involved past, present and future. Thus, the cultural information of each era is preserved in the urban fabric together and urban fabric features are complex and rich, which are difficult to capture in traditional design methods. In this paper, we try to use Generative Adversarial Networks (GAN), one of the neural network algorithms, to explore the inner rules of complex urban morphological features and realize the perception of the urban fabric. Neural networks are innovatively applied to the larger and more complex city generation in this experiment. First, we collect European urban fabric as the dataset, then label data to facilitate machine training, use GAN to learn the feature of the dataset by adjusting parameters, and analyze the effect of the generated results. The automatic feature learning capability of the neural networks is used to summarize the inherent patterns and rules in urban development which is difficult for human to discover.
keywords	Deep Learning, Generative Adversarial Networks, Generative Design, Morphology Cognition, Urban Fabric, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_352
id	caadria2022_352
authors	Duran, Ayca, Iseri, Orcun Koral, Meral Akgul, Cagla, Kalkan, Sinan and Gursel Dino, Ipek
year	2022
title	Compiling Open Datasets to Improve Urban Building Energy Models with Occupancy and Layout Data
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 669-678
doi	https://doi.org/10.52842/conf.caadria.2022.2.669
summary	Urban building energy modelling (UBEM) has great potential for assessing the energy performance of the existing building stock and exploring various actions targeting energy efficiency. However, the precision and completeness of UBEM models can be challenged due to the lack of available and reliable datasets related to building occupant and layout information. This study presents an approach that aims to augment UBEM with open-data sources. Data collected from open data sources are integrated into UBEM in three steps. Step (1) involves the generation of occupant profiles from census data collected from governmental institutions. Step (2) relates to the automated generation of building plan layouts by extracting data on building area and number of rooms from an online real-estate website. Results of Steps (1) and (2) are incorporated into Step (3) to generate residential units with layouts and corresponding occupant profiles. Finally, we make a comparative analysis between data-augmented and standard UBEM based on building energy use and occupant thermal comfort. The initial results point to the importance of detailed, precise energy models for reliable performance analysis of buildings at the urban scale. 0864108000
keywords	urban building energy modelling, occupancy, residential building stock, unit layout Information, open-source datasets, energy demand, indoor thermal comfort, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ascaad2022_063
id	ascaad2022_063
authors	Ozman, Gizem; Selcuk, Semra
year	2022
title	Generating Mass Housing Plans through GANs: A case in TOKI, Turkey
source	Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, pp. 17-29
summary	Nowadays, Machine Learning (ML) is frequently used in almost all disciplines having an intersection with technology. Recently, architects are using existing plan data sets in architecture through Deep Learning (DL) algorithms of big data to achieve generative and non-existent plan models by using ML. Especially, Generative Adversarial Neural Networks (GANs), one of the deep learning algorithms, have been in use in the creation of generative models for architectural studies. Within the scope of this paper, architectural drawings were generated by using GANs. This generation method allows for the training of spatial layout planning to networks and for the generation of plans that do not exist in the dataset. Architectural drawings of TOKI (Housing Development Administration of the Republic of Türkiye) mass housing projects were used as datasets. In line with studies already carried out, this study attempts to create a method for further processing of the research. In this study, the differences between the plan typologies generated with raster images and the reality relations in visual productions between graph-based plan layout productions were evaluated. In this context, 157 plan datasets were obtained by multiplying plans which were spatially correlated with the RGB settings of 21 plan typologies. As a result of this research, it has been determined that the spatial layout planning of the HouseGAN algorithm provides TOK?'s current plan typologies of generation together with bubble diagrams. HouseGAN was trained using its dataset and the outputs obtained were realistic background images.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	cdrf2022_488
id	cdrf2022_488
authors	Tomás Vivanco, Juan Eduardo Ojeda, Philip Yuan
year	2022
title	Regression-Based Inductive Reconstruction of Shell Auxetic Structures
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_42
summary	This article presents the design process for generating a shell-like structure from an activated bent auxetic surface through an inductive process based on applying deep learning algorithms to predict a numeric value of geometrical features. The process developed under the Material Intelligence Workflow applied to the development of (1) a computational simulation of the mechanical and physical behaviour of an activated auxetic surface, (2) the generation of a geometrical dataset composed of six geometric features with 3,000 values each, (3) the construction and training of a regression Deep Neuronal Network (DNN) model, (4) the prediction of the geometric feature of the auxetic surface's pattern distance, and (5) the reconstruction of a new shell based on the predicted value. This process consistently reduces the computational power and simulation time to produce digital prototypes by integrating AI-based algorithms into material computation design processes.
series	cdrf
email
last changed	2024/05/29 14:03

_id	caadria2022_90
id	caadria2022_90
authors	Veloso, Pedro, Rhee, Jinmo, Bidgoli, Ardavan and Ladron de Guevara, Manuel
year	2022
title	Bubble2Floor: A Pedagogical Experience With Deep Learning for Floor Plan Generation
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 373-382
doi	https://doi.org/10.52842/conf.caadria.2022.1.373
summary	This paper reports a pedagogical experience that incorporates deep learning to design in the context of a recently created course at the Carnegie Mellon University School of Architecture. It analyses an exercise called Bubble2Floor (B2F), where students design floor plans for a multi-story row-house complex. The pipeline for B2F includes a parametric workflow to synthesise an image dataset with pairs of apartment floor plans and corresponding bubble diagrams, a modified Pix2Pix model that maps bubble diagrams to floor plan diagrams, and a computer vision workflow to translate images to the geometric model. In this pedagogical research, we provide a series of observations on challenges faced by students and how they customised different elements of B2F, to address their personal preferences and problem constraints of the housing complex as well as the obstacles from the computational workflow. Based on these observations, we conclude by emphasising the importance of training architects to be active agents in the creation of deep learning workflows and make them accessible for socially relevant and constrained design problems, such as housing.
keywords	Architectural Pedagogy, Deep Learning, Conditional GAN, Space Planning, Floor Plan, SDG 4, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_169
id	caadria2022_169
authors	Xu, Hang and Wang, Tsung-Hsien
year	2022
title	An Integrated Parametric Generation and Computational Workflow to Support Sustainable City Planning
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 535-544
doi	https://doi.org/10.52842/conf.caadria.2022.1.535
summary	To examine how efforts in the built environment can contribute to global climate change mitigation at the urban scale, urban building energy modelling (UBEM) is one of the research areas gaining increasing interest in recent years. However, limited studies systematically illustrate a comprehensive UBEM workflow for most architects and urban planners considering available public datasets, particularly at the early conceptual design phase. In current UBEM studies, major challenges arise from the lack of fine-grained measured urban data and incompatibility between software. To address these challenges and support future sustainable cities and communities, this paper proposed a streamlined computational workflow of UBEM to facilitate sustainable urban design development. Through a case study of Sheffield in the UK, this paper demonstrated an automated and standardised computational workflow that can test the decarbonisation potential in built environments by evaluating energy demand and supply scenarios at an urban scale. This workflow is envisaged to be applicable at various scales of an urban region given an appropriate geographic information system (GIS) dataset.
keywords	Parametric Design Generation, Urban Sustainability, Urban Building Energy Modelling, Building Performance Simulation, Renewable Energy, Decarbonisation, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_205
id	caadria2022_205
authors	Bielski, Jessica, Langenhan, Christoph, Ziegler, Christoph, Eisenstadt, Viktor, Dengel, Andreas and Althoff, Klaus-Dieter
year	2022
title	Quantifying the Intangible, A Tool for Retrospective Protocol Studies of Sketching During the Early Conceptual Design of Architecture
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 403-411
doi	https://doi.org/10.52842/conf.caadria.2022.1.403
summary	Sketching is a craft supporting the development of ideas and design intentions, as well as an effective tool for communication during the early architectural design stages by making them tangible. Even though sketch-based interaction is a promising approach for Computer-Aided Architectural Design (CAAD) systems, it remains a challenge for computers to recognise information in a sketch. Design protocol studies conducted to deconstruct the sketch and sketching process collect solely qualitative data so far. However, the 'metis' projects aim to create an intelligent design assistant, using an artificial neural network (ANN), in the manner of Negroponte‚s Architecture Machine. By assimilating to the user's idiosyncrasies, the system suggests further design steps to the architect to improve the design decision making process for economic growth, qualitative self-education through the dialogue and reducing stress. For training such ANN quantitative data is needed. In order to produce quantifiable results from such a study, we propose our open-source web-tool ‚Sketch Protocol Analyser‚. By correlating different parameters (i.e. video, transcript and sketch built) through the same labels and their timestamps, we create quantitative data for further use.
keywords	Design Protocol Studies, Sketching, Data Collection, Architectural Design Process, ANN, SDG 3, SDG 4, SDG 8, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_211
id	ecaade2022_211
authors	Bonafede, Andrea and Erioli, Alessio
year	2022
title	Versus Habitat - Multi agent spatial negotiation for topology-aware, large scale architectural assemblages
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 2, Ghent, 13-16 September 2022, pp. 113–122
doi	https://doi.org/10.52842/conf.ecaade.2022.2.113
summary	With the burst of automation in the AEC industry, modular design for collective living is having a reissue; as for industrial construction in the post WW2 era, the economies of a construction system trigger urban models, but an exploration of non-standard spatial models based on computational methods is still lacking. This research proposes a competition-based process for the design of large scale (urban) collective habitats as topology-aware architectural assemblages of spatial (as in including constructive elements + void) components. Two competing multi-agent systems negotiate spatial occupancy, leveraging the morphological computation capabilities of individual and combined components at increasing scales. Localized information stored in the environment by the agents is converted in architectural components, resulting in a multi- level spatial organization that transcends typical typological classification. Space syntax techniques are used to map the assemblage properties and support design inferences on spatial occupation such as potentially implementable functional programmes.
keywords	Multi-agent System, Automation, Assemblages, Stigmergy, Space Syntax
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_245
id	caadria2022_245
authors	Chai, Hua, Guo, Zhixian, Wagner, Hans Jakob, Stark, Tim, Menges, Achim and Yuan, Philip F.
year	2022
title	In-Situ Robotic Fabrication of Spatial Glulam Structures
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 41-50
doi	https://doi.org/10.52842/conf.caadria.2022.2.041
summary	While current approaches in timber construction stress the advantages of off-site prefabrication, glued laminated timber(glulam) structures is limited to the constraints of standardized, prefabricated mostly linear elements, which also lends itself only to building typologies that offer an increased level of standardization and regularity. The design freedom of timber structures is incomparable to that of reinforced concrete structures, which mostly gains from the in-situ fabrication process. An in-situ robotic timber fabrication platform allows the on-site construction of glulam structures with highly differentiated networks of beams composed of robotically assembled discrete linear elements. Based on the possibilities of such mobile robotic fabrication process, this paper explores novel architectural typologies of spatial glulam structures. The research is conducted from several aspects including joint tectonics, design method, and robotic fabrication process. A large-scale pavilion is designed and fabricated to verify the feasibility of the proposed system. This research could provide a novel mode of in-situ robotic timber fabrication and corresponding glulam structure system for timber construction.
keywords	Mobile Robot, Timber Structure, In-situ Fabrication, Computational Design, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_169
id	ecaade2022_169
authors	Chen, Ting-Chia, Tsai, Tsung-Han, Huang, Ching-Wen and Wang, Shih-Yuan
year	2022
title	Compliant Mechanism Moulding via NiChrome Wire Sintering Method
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. 281–290
doi	https://doi.org/10.52842/conf.ecaade.2022.1.281
summary	This research proposed a unique process for the rapid manufacturing of large-scale compliant mechanism components. Using the characteristics of the NiChrome wire sintering method, it aims to rapidly fabricate a large-scale compliant mechanism model at low cost. NiChrome wire sintering is a method in which NiChrome wire is wound into a target pattern and then placed in a hot-melt material (TPU powder) to be energized and moulded. The low cost, high degree of freedom and one-piece characteristic of this new method bring new possibilities for the manufacturing process of compliant mechanism components. This research applies a new fabrication method to reduce the production cost and manufacturing difficulty of large kinetic installations. In benefitting from the non-mechanical wear characteristics of compliant mechanisms, the service life of manufactured installations can be greatly prolonged as well. The new fabrication method demonstrates an efficient way to produce a large scale of kinetic structure and provides a toolkit for designers.
keywords	Nichrome Wire Sintering, Rapid Prototyping, Elastic Material, Digital Fabrication, Compliant Mechanism
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_299
id	caadria2022_299
authors	Cui, Qiang, Zhang, Huikai, Pawar, Siddharth Suhas, Yu, Chuan, Feng, Xiqiao and Qiu, Song
year	2022
title	Topology Optimization for 3D-Printable Large-Scale Metallic Hollow Structures With Self-Supporting
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 101-110
doi	https://doi.org/10.52842/conf.caadria.2022.2.101
summary	Design for Additive Manufacturing (DfAM), is a one of the most commonly used and foundational techniques used in the development of new products, and particularly those that involve large-scale metallic structures composed of hollow components. One such AM technique is Wire Arc Additive Manufacturing (WAAM), which is the application of robotic welding technology applied to Additive Manufacturing. Due to the lack of a simple method to describe the fabricating constraint of WAAM and the complex hollow morphology, which difficultly deploys topology optimization structural techniques that use WAAM. In this paper, we develop a design strategy that unifies ground-structure optimization method with generative design that considers the features of hollow components, WAAM overhang angle limits and manufacturing thickness limits. The method is unique in that the user can interact with the design results, make changes to parameters, and alter the design based on the user‚s aesthetic or specific manufacturing setup needs. We deploy the method in the design and 3D printing of an optimized Electric Vehicle Chassis and successfully test in under different loading conditions.
keywords	Topology optimization, Generative design, Self-supporting, Hollow structures, Metallic 3D printing, SDG 12
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_325
id	caadria2022_325
authors	Cui, Qinyu, Zhang, Shuyu and Huang, Yiting
year	2022
title	Retail Commercial Space Clustering Based on Post-carbon Era Context: A Case Study of Shanghai
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 515-524
doi	https://doi.org/10.52842/conf.caadria.2022.1.515
summary	In the post-carbon era, it has become a development and research trend on adjusting commercial locations to help achieve resource conservation by using big data. This paper uses multi-source urban data and machine learning to make reasonable evaluations and adjustments to commercial district planning. Many relevant factors are affecting urban commercial agglomeration, but how to select the appropriate ones among the many factors is a problem to be considered and studied, while there may be spatial differences in the strength of each influencing factor on commercial agglomeration. Therefore, this paper takes Shanghai, a city with a high economic and commercial development level in China, as an example and identifies the influencing factors through a literature review. Next, this paper uses the machine learning BORUTA algorithm of features selection to screen the influencing factors. It then uses multi-scale geographically weighted regression model (MGWR) to analyse the spatial heterogeneity of factors affecting retail spatial agglomeration. Finally, based on the background of the changing transportation modes and the unchanged social activities in the post-carbon era, the future spatial planning pattern of retail commercial space is discussed to provide particular suggestions for the future location adjustment of urban commerce.
keywords	Business District Hierarchy, Agglomeration Effect, Spatial Variability, Multi-scale Geographically Weighted Regression Model, Machine Learning, Big Data Analysis, SDG 8, SDG 12
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ascaad2022_065
id	ascaad2022_065
authors	David, Joao; Leitao, Antonio
year	2022
title	Getting a Handle on Floor Plan Analysis: Door Classification in Floor Plans and a Survey on Existing Datasets
source	Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, pp. 221-236
summary	Floor plan interpretation and reconstruction is crucial to enable the transformation of drawings to 3D models or different digital formats. It has recently taken advantage of neural-based architectures, especially in the semantic segmentation field. These techniques perform better than traditional methods, but the results depend mainly on the data used to train the networks, which is often crafted for the specific task being performed, making it hard to reuse for different purposes. In this paper, we conduct a literature survey on the existing datasets for floor plan analysis, and we explore how information regarding door placement and orientation can be recovered without having to change the initial data or model. We propose a two-step recognition method based on image segmentation followed by classification of cropped zones to allow data augmentation during training. In the process, we generate a dataset consisting of 35000 annotated door images extracted from an existing dataset.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	caadria2022_152
id	caadria2022_152
authors	Deshpande, Rutvik, Nisztuk, Maciej, Cheng, Cesar, Subramanian, Ramanathan, Chavan, Tejas, Weijenberg, Camiel and Patel, Sayjel Vijay
year	2022
title	Synthetic Machine Learning for Real-time Architectural Daylighting Prediction
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 313-322
doi	https://doi.org/10.52842/conf.caadria.2022.1.313
summary	"Synthetic Machine Learning‚ offers a revolutionary leap in real-time environmental analysis for conceptual architectural design. By integrating automatic synthetic data generation, artificial neural network (ANN) training and online deployment, Synthetic Machine Learning offers two main advantages over conventional simulation; First, it reduces the analysis time for a reference simulation from minutes to seconds; Second, it is possible to deploy ANN as a web service in an online design environment, which therein increases accessibility, significantly reducing simulation costs and setup time. The application of Synthetic Machine Learning to perform Daylight Autonomy (DA) and Spatial Daylight Autonomy (sDA) studies to maximise building daylighting for a given use, window to wall ratio, and floorplan arrangement is showcased through a preliminary demonstration work. Comparatively the use of algorithmically generated synthetic data versus real-world data is becoming ubiquitous in other disciplines, the advantages of this approach to the building design process are further discussed.
keywords	Daylight Autonomy, machine learning, building energy performance, synthetic data-sets, SDG 7, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_175
id	ecaade2022_175
authors	Di Carlo, Raffaele, Mittal, Divyae and Vesely, Ondrej
year	2022
title	Generating 3D Building Volumes for a Given Urban Context using Pix2Pix GAN
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 2, Ghent, 13-16 September 2022, pp. 287–295
doi	https://doi.org/10.52842/conf.ecaade.2022.2.287
summary	Our ability to delegate the most intellectually demanding tasks to machines improves with each passing day. Even in the fields of architecture and design, which were previously thought to be exclusive domain of human creativity and flare, we are moving the first steps towards developing models that can capture the patterns, invisible to the naked eye, embedded in the creative process. These patterns reflect ideas and traditions, imprinted in the collective mind over the course of history, that can be improved upon or serve as a cautionary tale for the new generation of designers in their work of designing an equitable, more inclusive future. Generative Adversarial Networks (GANs) give us the opportunity to turn style and design into learnable features that can be used to automatically generate blueprints and layouts. In this study, we attempt to apply this technology to urban design and to the task of generating a building footprint and volume that fits within the surrounding built environment. We do so by developing a Pix2Pix model composed of a ResNet-6 generator and a Patch discriminator, applying it to satellite views of neighborhoods from across the Netherlands, and then turning the resulting 2D generated building footprint into a reusable 3D model. The model is trained using the national cadastral data and TU Delft 3D BAG dataset. The results show that it is possible to predict a building shape compatible in style and height with the surroundings. Although the model can be used for different applications, we use it as an evaluation tool to compare the design alternatives fitting the desired contextual patterns.
keywords	Generative Adversarial Networks, Urban Design, Pix2Pix, Raster Vectorization, 3D Rendering
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_114
id	caadria2022_114
authors	Dong, Zhiyong, Lin, Jinru, Wang, Siqi, Xu, Yijia, Xu, Jiaqi and Liu, Xiao
year	2022
title	Where Will Romance Occur, A New Prediction Method of Urban Love Map through Deep Learning
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 213-222
doi	https://doi.org/10.52842/conf.caadria.2022.1.213
summary	Romance awakens fond memories of the city. Finding out the relationship between romantic scene and urban morphology, and providing a prediction, can potentially facilitate the better urban design and urban life. Taking the Yangtze River Delta region of China as an example, this study aims to predict the distribution of romantic locations using deep learning based on multi-source data. Specifically, we use web crawlers to extract romance-related messages and geographic locations from social media platforms, and visualize them as romance heatmap. The urban environment and building features associated with romantic information are identified by Pearson correlation analysis and annotated in the city map. Then, both city labelled maps and romance heatmaps are fed into a Generative Adversarial Networks (GAN) as the training dataset to achieve final romance distribution predictions across regions for other cities. The ideal prediction results highlight the ability of deep learning techniques to quantify experience-based decision-making strategies that can be used in further research on urban design.
keywords	Romance Heatmap, Generative Adversarial Networks, Deep Learning, Big Data Analysis, Correlation Analysis, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_222
id	ecaade2022_222
authors	Eisenstadt, Viktor, Bielski, Jessica, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2022
title	Autocompletion of Design Data in Semantic Building Models using Link Prediction and Graph Neural Networks
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. 501–510
doi	https://doi.org/10.52842/conf.ecaade.2022.1.501
summary	This paper presents an approach for AI-based autocompletion of graph-based spatial configurations using deep learning in the form of link prediction through graph neural networks. The main goal of the research presented is to estimate the probability of connections between the rooms of the spatial configuration graph at hand using the available semantic information. In the context of early design stages, deep learning-based prediction of spatial connections helps to make the design process more efficient and sustainable using the past experiences collected in a training dataset. Using the techniques of transfer learning, we adapted methods available in the modern graph-based deep learning frameworks in order to apply them for our autocompletion purposes to suggest possible further design steps. The results of training, testing, and evaluation showed very good results and justified application of these methods.
keywords	Spatial Configuration, Autocompletion, Link Prediction, Deep Learning
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ascaad2022_000
id	ascaad2022_000
authors	El-Bastawissi, Ibtihal Y.; Abdelmohsen, Sherif
year	2022
title	ASCAAD 2022: Hybrid Spaces of the Metaverse
source	Hybrid Spaces of the Metaverse - Architecture in the Age of the Metaverse: Opportunities and Potentials [10th ASCAAD Conference Proceedings] Debbieh (Lebanon) [Virtual Conference] 12-13 October 2022, 743 p.
summary	The ASCAAD 2022 theme focuses on Hybrid Spaces of the Metaverse, with the aim of unraveling the opportunities and potentials of architecture in the age of the Metaverse. Historically space was always the container of people’s activities and memories; it is the collective reflection of their life styles. Walls, floors and ceilings of architectural spaces witnessed the moments of joy and happiness, as well as moments of misery that changed human history, from the signing of the United Nations Declaration post WWII, to the first I-phone sold in the Apple store; history is written inside architectural spaces. The new era of the 4th industrial revolution, which is associated with digital transformation, will unlock new opportunities for architects, interior designers and whoever will enter the domain of the metaverse. The metaverse will not only serve as a portal to a new world, but also as an extension to new activities such as commercial, social, educational and business activities that will thrive in the new virtual realm. The metaverse will act as the natural transcendence of technological advancements carrying new potentials to the architectural profession. Active Worlds, Second Life, Roblox and Fortnite are all early versions of what we will witness in the next few years, shifting from entertainment to full commercial, official and governmental activities; all will be hosted inside virtual and hybrid spaces. A new era will start inside virtual realms; real economy will rise inside virtual architecture but without the multiple physical or structural constraints that limit physicality anymore such as gravity, and day and night cycles; no oxygen is needed anymore. But this time, human activities will not only be recorded and saved but also attended and lived in real time. Computational design will continue to thrive and even evolve into new forms aligning with new changes and challenges of the metaverse. Hybrid spaces are the spaces that will be built as a virtual extension of real spaces. They will be in connection to real spaces and reflecting their activities on a real time basis. On the other hand, pure virtual spaces will occur, trespassing time zones and geographical barriers. The importance of hybrid experiences was most realized after the pandemic lockdowns; and now is the time to invent new design methodologies and new theories as a natural transcendence of architecture profession. Hyperlinks portals replacing staircases and elevators, physically impossible structures, open budget interiors, teleportation are all new notions emerging with the new domain. Today, virtual spaces are hosted on various cloud services and registered as Non-Fungible Tokens (NFTs). They are experienced as immersed spaces using headsets or semi immersed spaces presented through laptops and/or mobile screens. With the new accelerating pace of technology, there is high possibility for integration within our neural networks to be experienced in our minds with just closing our eyes in the near future.
series	ASCAAD
email
last changed	2024/02/16 13:24

For more results click below: