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 651

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

_id	ecaade2020_193
id	ecaade2020_193
authors	Alymani, Abdulrahman, Jabi, Wassim and Corcoran, Padraig
year	2020
title	Machine Learning Methods for Clustering Architectural Precedents - Classifying the relationship between building and ground
doi	https://doi.org/10.52842/conf.ecaade.2020.1.643
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 643-652
summary	Every time an object is built, it creates a relationship with the ground. Architects have a full responsibility to design the building by taking the ground into consideration. In the field of architecture, using data mining to identify any unusual patterns or emergent architectural trends is a nascent area that has yet to be fully explored. Clustering techniques are an essential tool in this process for organising large datasets. In this paper, we propose a novel proof-of-concept workflow that enables a machine learning computer system to cluster aspects of an architect's building design style with respect to how the buildings in question relate to the ground. The experimental workflow in this paper consists of two stages. In the first stage, we use a database system to collect, organise and store several significant architectural precedents. The second stage examines the most well-known unsupervised learning algorithm clustering techniques which are: K-Means, K-Modes and Gaussian Mixture Models. Our experiments demonstrated that the K-means clustering algorithm method achieves a level of accuracy that is higher than other clustering methods. This research points to the potential of AI in helping designers identify the typological and topological characteristics of architectural solutions and place them within the most relevant architectural canons
keywords	Machine Learning; Building and Ground Relationship; Clustering Algorithms; K-means cluster Algorithms
series	eCAADe
email
last changed	2022/06/07 07:54

_id	cdrf2019_199
id	cdrf2019_199
authors	Ana Herruzo and Nikita Pashenkov
year	2020
title	Collection to Creation: Playfully Interpreting the Classics with Contemporary Tools
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_19
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
summary	This paper details an experimental project developed in an academic and pedagogical environment, aiming to bring together visual arts and computer science coursework in the creation of an interactive installation for a live event at The J. Paul Getty Museum. The result incorporates interactive visuals based on the user’s movements and facial expressions, accompanied by synthetic texts generated using machine learning algorithms trained on the museum’s art collection. Special focus is paid to how advances in computing such as Deep Learning and Natural Language Processing can contribute to deeper engagement with users and add new layers of interactivity.
series	cdrf
email
last changed	2022/09/29 07:51

_id	ecaade2020_515
id	ecaade2020_515
authors	Chadha, Kunaljit, Dubor, Alexandre, Puigpinos, Laura and Rafols, Irene
year	2020
title	Space Filling Curves for Optimising Single Point Incremental Sheet Forming using Supervised Learning Algorithms
doi	https://doi.org/10.52842/conf.ecaade.2020.1.555
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 555-562
summary	Increasing use of computational design tools have led to an increase in the demand for mass customised fabrication, rendering decades old industrial CAD-CAM protocols limiting for such fabrication processes. This bespoke demand of components has led to a unified workflow between design strategies and production techniques. Recent advances in computation have allowed us to predict and register the tolerances of fabrication before and while being fabricated. Procedural algorithms are a set of novel problem-solving methods and have been attracting considerable attention for their good performance.They follow a procedural way of iteration with an established way of behavior.In the particular case of Incremental Sheet forming (ISF), these algorithms can realize several functions such as edge detection and segmentation required for optimizing machining time and accuracy.In this context, this paper presents a methodology to optimize long-drawn-out ISF operation by using geometrical intervention informed by supervised machine learning algorithms.
keywords	Procedural Algorithms; Incremental Sheet Forming; Robotic Cold forming; Mass Customization
series	eCAADe
email
last changed	2022/06/07 07:55

_id	ecaade2023_99
id	ecaade2023_99
authors	Dervishaj, Arlind, Fonsati, Arianna, Hernández Vargas, José and Gudmundsson, Kjartan
year	2023
title	Modelling Precast Concrete for a Circular Economy in the Built Environment
doi	https://doi.org/10.52842/conf.ecaade.2023.2.177
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 177–186
summary	In recent years, there has been a growing interest in adopting circular approaches in the built environment, specifically reusing existing buildings or their components in new projects. To achieve this, drawings, laser scanning, photogrammetry and other techniques are used to capture data on buildings and their materials. Although previous studies have explored scan-to-BIM workflows, automation of 2D drawings to 3D models, and machine learning for identifying building components and materials, a significant gap remains in refining this data into the right level of information required for digital twins, to share information and for digital collaboration in designing for reuse. To address this gap, this paper proposes digital guidelines for reusing precast concrete based on the level of information need (LOIN) standard EN 17412-1:2020 and examines several CAD and BIM modelling strategies. These guidelines can be used to prepare digital templates that become digital twins of existing elements, develop information requirements for use cases, and facilitate data integration and sharing for a circular built environment.
keywords	building information modelling (BIM), circular construction, reuse, concrete
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2020_432
id	ecaade2020_432
authors	Fragkia, Vasiliki and Worre Foged, Isak
year	2020
title	Methods for the Prediction and Specification of Functionally Graded Multi-Grain Responsive Timber Composites
doi	https://doi.org/10.52842/conf.ecaade.2020.2.585
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 585-594
summary	The paper presents design-integrated methods for high-resolution specification and prediction of functionally graded wood-based thermal responsive composites, using machine learning. The objective is the development of new circular design workflow, employing robotic fabrication, in order to predict fabrication files linked to material performance and design requirements, focused on application for intrinsic responsive and adaptive architectural surfaces. Through an experimental case study, the paper explores how machine learning can form a predictive design framework where low-resolution data can solve material systems at high resolution. The experimental computational and prototyping studies show that the presented image-based machine learning method can be adopted and adapted across various stages and scales of architectural design and fabrication. This in turn allows for a design-per-requirement approach that optimizes material distribution and promotes material economy.
keywords	material specification; responsive timber composites; machine learning; robotic fabrication; building envelopes
series	eCAADe
email
last changed	2022/06/07 07:50

_id	cdrf2019_159
id	cdrf2019_159
authors	Hang Zhang and Ye Huang
year	2020
title	Machine Learning Aided 2D-3D Architectural Form Finding at High Resolution
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_15
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
summary	In the past few years, more architects and engineers start thinking about the application of machine learning algorithms in the architectural design field such as building facades generation or floor plans generation, etc. However, due to the relatively slow development of 3D machine learning algorithms, 3D architecture form exploration through machine learning is still a difficult issue for architects. As a result, most of these applications are confined to the level of 2D. Based on the state-of-the-art 2D image generation algorithm, also the method of spatial sequence rules, this article proposes a brand-new strategy of encoding, decoding, and form generation between 2D drawings and 3D models, which we name 2D-3D Form Encoding WorkFlow. This method could provide some innovative design possibilities that generate the latent 3D forms between several different architectural styles. Benefited from the 2D network advantages and the image amplification network nested outside the benchmark network, we have significantly expanded the resolution of training results when compared with the existing form-finding algorithm and related achievements in recent years
series	cdrf
email
last changed	2022/09/29 07:51

_id	caadria2020_444
id	caadria2020_444
authors	Higgs, Baptiste and Doherty, Ben
year	2020
title	Sanitary Sanity: Evaluating Privacy Preserving Machine Learning Methods for Post-occupancy Evaluation
doi	https://doi.org/10.52842/conf.caadria.2020.2.697
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 697-706
summary	Traditional post-occupancy evaluation (POE) of building performance has typically privileged physical building attributes over human behavioural data. This is due to a lack of capability and is especially the case for private spaces such as Sanitary Facilities (SFs). A privacy-preserving sensor-based system using Machine Learning (ML) was previously developed, however it was limited to basic body position classification. Yet, SF usage behaviour can be significantly more complex. This research accordingly builds on the aforementioned work to expand behavioural classifications using a sensor-based ML system. Specifically, the case study uses a GridEYE thermal sensor array, which is trained on a cubicle location within a workplace SF. A variety of ML algorithms are then evaluated on their behaviour-classifying ability. A detailed analysis of behaviour-classification performance is then provided. A system with greater fidelity is thus demonstrated, albeit hampered by imprecise behaviour definitions. Regardless, this contributes to the capability of the broader field of research that is investigating Evidence Based Design (EBD) by extending the ability to examine human behaviour, especially in private spaces. This further contributes to the growing body of work surrounding SF provision.
keywords	EBD; Data; Internet of Things; Machine Learning; Post Occupancy Evaluation
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	acadia20_658
id	acadia20_658
authors	Ho, Brian
year	2020
title	Making a New City Image
doi	https://doi.org/10.52842/conf.acadia.2020.1.658
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 658-667.
summary	This paper explores the application of computer vision and machine learning to streetlevel imagery of cities, reevaluating past theory linking urban form to human perception. This paper further proposes a new method for design based on the resulting model, where a designer can identify areas of a city tied to certain perceptual qualities and generate speculative street scenes optimized for their predicted saliency on labels of human experience. This work extends Kevin Lynch’s Image of the City with deep learning: training an image classification model to recognize Lynch’s five elements of the city image, using Lynch’s original photographs and diagrams of Boston to construct labeled training data alongside new imagery of the same locations. This new city image revitalizes past attempts to quantify the human perception of urban form and improve urban design. A designer can search and map the data set to understand spatial opportunities and predict the quality of imagined designs through a dynamic process of collage, model inference, and adaptation. Within a larger practice of design, this work suggests that the curation of archival records, computer science techniques, and theoretical principles of urbanism might be integrated into a single craft. With a new city image, designers might “see” at the scale of the city, as well as focus on the texture, color, and details of urban life.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2022_161
id	ecaade2022_161
authors	Kharbanda, Kritika, Papadopoulou, Iliana, Pouliou, Panagiota, Daw, Karim, Belwadi, Anirudh and Loganathan, Hariprasath
year	2022
title	LearnCarbon - A tool for machine learning prediction of global warming potential from abstract designs
doi	https://doi.org/10.52842/conf.ecaade.2022.2.601
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. 601–610
summary	The new construction that is projected to take place between 2020 and 2040 plays a critical role in embodied carbon emissions. The change in material selection is inversely proportional to the budget, as the project progresses. Given the fact that early-stage design processes often do not include environmental performance metrics, there is an opportunity to investigate a toolset that enables early-stage design processes to integrate this type of analysis into the preferred workflow of concept designers. The value here is that early-stage environmental feedback can inform the crucial decisions that are made in the beginning, giving a greater chance for a building with better environmental performance in terms of its life cycle. This paper presents the development of a tool called LearnCarbon, as a plugin of Rhino3d, used to educate architects and engineers in the early stages about the environmental impact of their design. It facilitates two neural networks trained with the Embodied Carbon Benchmark Study by Carbon Leadership Forum, which learn the relationship between building geometry, typology, and structure with the Global Warming potential in tCO2e. The first one, a regression model, is able to predict the GWP based on the massing model of a building, along with information about typology and location. The second one, a classification model, predicts the construction type given a massing model and target GWP. LearnCarbon can help improve the building life cycle impact significantly, through early predictions of the structure’s material, and can be used as a tool for facilitating sustainable discussions between the architect and the client.
keywords	Machine Learning, Carbon Emissions, LCA, Rhino Plug-in
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2020_163
id	caadria2020_163
authors	Koh, Immanuel
year	2020
title	The Augmented Museum - A Machinic Experience with Deep Learning
doi	https://doi.org/10.52842/conf.caadria.2020.2.639
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 639-648
summary	Today we witness a shift in the role with which museum used to play -- from one that was simply a spatial container filled with physical artworks on display, to one that is now layered with the digital/online version of the artworks themselves. Deep learning algorithms have become an important means to process such large datasets of digital artworks in providing an alternative curatorial practice (biased/unbiased), and consequentially, augmenting the navigation of the museum's physical spaces. In collaboration with a selection of museums, a series of web/mobile applications have been made to investigate the potential of such machinic inference, as well as interference of the physical experience.
keywords	Machine Learning; Deep Learning; Experience Design; Artificial Intelligence
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ijac202018402
id	ijac202018402
authors	Mette Ramsgaard Thomsen, Paul Nicholas, Martin Tamke, Sebastian Gatz, Yuliya Sinke and Gabriella Rossi
year	2020
title	Towards machine learning for architectural fabrication in the age of industry 4.0
source	International Journal of Architectural Computing vol. 18 - no. 4, 335–352
summary	Machine Learning (ML) is opening new perspectives for architectural fabrication, as it holds the potential for the profession to shortcut the currently tedious and costly setup of digital integrated design to fabrication workflows and make these more adaptable. To establish and alter these workflows rapidly becomes a main concern with the advent of Industry 4.0 in building industry. In this article we present two projects, which presents how ML can lead to radical changes in generation of fabrication data and linking these directly to design intent. We investigate two different moments of implementation: linking performance to the generation of fabrication data (KnitCone) and integrating the ability to adapt fabrication data in realtime as response to fabrication processes (Neural-Network Steered Robotic Fabrication). Together they examine how models can employ design information as training data and be trained to by step processes within the digital chain. We detail the advantages and limitations of each experiment, we reflect on core questions and perspectives of ML for architectural fabrication: the nature of data to be used, the capacity of these algorithms to encode complexity and generalize results, their task-specificness versus their adaptability and the tradeoffs of using them with respect to conventional explicit analytical modelling.
keywords	Machine learning, architectural design, industry 4.0, digital fabrication, robotic fabrication, CNC knit, neural networks
series	journal
email
last changed	2021/06/03 23:29

_id	ecaade2020_411
id	ecaade2020_411
authors	Muehlbauer, Manuel, Song, Andy and Burry, Jane
year	2020
title	Smart Structures - A Generative Design Framework for Aesthetic Guidance in Structural Node Design - Application of Typogenetic Design for Custom-Optimisation of Structural Nodes
doi	https://doi.org/10.52842/conf.ecaade.2020.1.623
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 623-632
summary	Virtual prototypes enable performance simulation for building components. The presented research extended the application of generative design using virtual prototypes for interactive optimisation of structural nodes. User-interactivity contributed to the geometric definition of design spaces rather than the final geometric outcome, enabling another stage of generative design for the micro-structure of the structural node. In this stage, the micro-structure inside the design space was generated using fixed topology. In contrast to common optimisation strategies, which converge towards a single optimal outcome, the presented design exploration process allowed the regular review of design solutions. User-based selection guided the evolutionary process of design space exploration applying Online Classification. Another guidance mechanism called Shape Comparison introduced an intelligent control system using an inital image input as design reference. In this way, aesthetic guidance enabled the combined evaluation of quantitative and qualitative criteria in the custom-optimisation of structural nodes. Interactive node design extended the potential for shape variation of custom-optimized structural nodes by addressing the geometric definition of design spaces for multi-scalar structural optimisation.
keywords	generative design; evolutionary computation; interactive machine learning; typogenetic design
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2020_313
id	caadria2020_313
authors	Sanatani, Rohit Priyadarshi
year	2020
title	A Machine-Learning driven Design Assistance Framework for the Affective Analysis of Spatial Enclosures
doi	https://doi.org/10.52842/conf.caadria.2020.1.741
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 741-750
summary	There is a growing research direction that adopts an empirical approach to affective response in space, and aims at generating bodies of quantitative data regarding the correlations between spatial features and emotional states. This paper demonstrates a machine-learning driven computational framework that draws upon training data sets to predict the 'affective impact' of designed enclosures. For demonstration, it has been scripted as a Rhinoceros + Grasshopper based design tool that uses existing training data collected by the author. The data comprises of the spatial parameters of Enclosure Volume (V), Length/Width ratio (P) and Window Area/Total Internal Surface Area ratio (D) - and the corresponding emotional parameters of Valence and Arousal. The test values of these parameters are computed by defining the components of the test enclosure (walls, windows, floors and ceilings) in the script. Nonlinear regression components are run on the training datasets and the test input data is used to compute and display the real time predicted affective state on the circumplex model of affect.
keywords	Affective Analysis; Affective Computing; Design Assistance; Machine Learning; Spatial Enclosures
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	sigradi2023_234
id	sigradi2023_234
authors	Santos, Ítalo, Andrade, Max, Zanchettin, Cleber and Rolim, Adriana
year	2023
title	Machine learning applied in the evaluation of airport projects in Brazil based on BIM models
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 875–887
summary	In a country with continental dimensions like Brazil, air transport plays a strategic role in the development of the country. In recent years, initiatives have been promoted to boost the development of air transport, among which the BIM BR strategy stands out, instituted by decree n-9.983 (2019), decree n-10.306 (2020) and more recently, the publication of the airport design manual (SAC, 2021). In this context, this work presents partial results of a doctoral research based on the Design Science Research (DSR) method for the application of Machine Learning (ML) techniques in the Artificial Intelligence (AI) subarea, aiming to support SAC airport project analysts in the phase of project evaluation. Based on a set of training and test data corresponding to airport projects, two ML algorithms were trained. Preliminary results indicate that the use of ML algorithms enables a new scenario to be explored by teams of airport design analysts in Brazil.
keywords	Airports, Artificial intelligence, BIM, Evaluation, Machine learning.
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	ecaade2020_283
id	ecaade2020_283
authors	Sebestyen, Adam and Tyc, Jakub
year	2020
title	Machine Learning Methods in Energy Simulations for Architects and Designers - The implementation of supervised machine learning in the context of the computational design process
doi	https://doi.org/10.52842/conf.ecaade.2020.1.613
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 613-622
summary	Application of Machine Learning (ML) in the field of architecture is a worthwhile topic to discuss in the context of digital architecture. Authors propose to extend this discussion, presenting an integrated ML pipeline built with the state-of-the-art data science tools. To investigate the affordances of such pipelines, an ML model being able to predict the environmental metrics of a generalized facade system is created. This approach is valid for arbitrary facades, as long as the proposed design could be discretized in the form analogous to the data generated for the ML model training. The presented experiment evaluates the precision of the sunlight hours and radiation values predictions, aiming at the application in the early design phases. Conducted investigation builds up on the knowledge embedded in the Grasshopper and Ladybug toolsets. Potential application of Convolutional Neural Networks and categorical datasets for classifications tasks to increase the precision of the ML models have been identified. Possibility to extend the approach beyond the workspace of Rhino and Grasshopper is suggested. Further research outlook, investigating the data pattern recognition capabilities in relation to the three-dimensional forms discretized as multidimensional arrays, is stated.
keywords	Machine Learning; Environmental Analysis; Parametric Design; Supervised Learning
series	eCAADe
email
last changed	2022/06/07 08:00

_id	ijac202119406
id	ijac202119406
authors	Silva Dória, David Rodrigues; Ramaswami, Keshav; Claypool, Mollie; Retsin, Gilles
year	2021
title	Public parts, resocialized autonomous communal life
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 4, 568–593
summary	Commoning embodies the product of social contracts and behaviors between groups of individuals. In thecase of social housing and the establishment of physical domains for life, commoning is an intersection of thesecontracts and the restrictions and policies that prohibit and allow them to occur within municipalities. Via aplatform-based project entitled Public Parts (2020), this article will also present positions on the reification ofthe common through a set of design methodologies and implementations of automation. This platform seeksto subvert typical platform models to decrease ownership, increase access, and produce a new form ofcommunal autonomous life amongst individuals that constitute the rapidly expanding freelance, work fromhome, and gig economies. Furthermore, this text investigates the consequences of merging domestic spacewith artificial intelligence by implementing machine learning to reconfigure spaces and program. Theproblems that arise from the deployment of machine learning algorithms involve issues of collection, usage,and ownership of data. Through the physical design of space, and a central AI which manages the platform andthe automated management of space, the core objective of Public Parts is to reify the common througharchitecture and collectively owned data.
keywords	Common, housing, platforms, reification, artificial intelligence, automation
series	journal
email
last changed	2024/04/17 14:29

_id	ecaade2020_015
id	ecaade2020_015
authors	Yazici, Sevil
year	2020
title	A machine-learning model driven by geometry, material and structural performance data in architectural design process
doi	https://doi.org/10.52842/conf.ecaade.2020.1.411
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 411-418
summary	Artificial Intelligence (AI), based on interpretation of data, influences various professions including architectural design today. Although research on integrating conceptual design with Machine Learning (ML) algorithms as a subset of the AI has been investigated previously, there is not a framework towards integration of architectural geometry with material properties and structural performance data towards decision making in the early-design phase. Undertaking performance simulations require significant amount of computation power and time. The aim of this research is to integrate ML algorithms into design process to achieve time efficiency and improve design results. The proposed workflow consists of three stages, including generation of the parametric model; running structural performance simulations to collect the data, and operating the ML algorithms, including Artificial Neural Network (ANN), Non-Linear Regression (NLR) and Gaussian Mixture (GM) for undertaking different tasks. The results underlined that the system generates relatively fast solutions with accuracy. Additionally, ML algorithms can assist generative design processes.
keywords	Machine-learning; performance simulation; data-driven design; early-design phase
series	eCAADe
email
last changed	2022/06/07 07:57

_id	cdrf2022_209
id	cdrf2022_209
authors	Yecheng Zhang, Qimin Zhang, Yuxuan Zhao, Yunjie Deng, Feiyang Liu, Hao Zheng
year	2022
title	Artificial Intelligence Prediction of Urban Spatial Risk Factors from an Epidemic Perspective
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_18
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	From the epidemiological perspective, previous research methods of COVID-19 are generally based on classical statistical analysis. As a result, spatial information is often not used effectively. This paper uses image-based neural networks to explore the relationship between urban spatial risk and the distribution of infected populations, and the design of urban facilities. We take the Spatio-temporal data of people infected with new coronary pneumonia before February 28 in Wuhan in 2020 as the research object. We use kriging spatial interpolation technology and core density estimation technology to establish the epidemic heat distribution on fine grid units. We further examine the distribution of nine main spatial risk factors, including agencies, hospitals, park squares, sports fields, banks, hotels, Etc., which are tested for the significant positive correlation with the heat distribution of the epidemic. The weights of the spatial risk factors are used for training Generative Adversarial Network models, which predict the heat distribution of the outbreak in a given area. According to the trained model, optimizing the relevant environment design in urban areas to control risk factors effectively prevents and manages the epidemic from dispersing. The input image of the machine learning model is a city plan converted by public infrastructures, and the output image is a map of urban spatial risk factors in the given area.
series	cdrf
email
last changed	2024/05/29 14:02

_id	cdrf2019_179
id	cdrf2019_179
authors	Yuzhe Pan, Jin Qian, and Yingdong Hu
year	2020
title	A Preliminary Study on the Formation of the General Layouts on the Northern Neighborhood Community Based on GauGAN Diversity Output Generator
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_17
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
summary	Recently, the mainstream gradually has become replacing neighborhood-style communities with high-density residences. The original pleasant scale and enclosed residential spaces have been broken, and the traditional neighborhood relations are going away. This research uses machine learning to train the model to generate a new plan, which is used in today’s residential design. First, in order to obtain a better generation effect, this study extracts the transcendental information of the neighborhood community in north of China, using roads, buildings etc. as morphological representations; GauGAN, compared to the pix2pix and pix2pixHD, used by predecessors, can achieve a clearer and a more diversified output and also fit irregular contours more realistically. ANN model trained by 167 general layout samples of a neighborhood community in north of China from 1950s to 1970s can generate various general layouts in different shapes and scales. The experiment proves that GauGAN is more suitable for general layout generation than pix2pix (pix2pixHD); Distributed training can improve the clarity of the generation and allow later vectorization to be more convenient.
series	cdrf
email
last changed	2022/09/29 07:51

_id	caadria2020_234
id	caadria2020_234
authors	Zhang, Hang and Blasetti, Ezio
year	2020
title	3D Architectural Form Style Transfer through Machine Learning
doi	https://doi.org/10.52842/conf.caadria.2020.2.659
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 659-668
summary	In recent years, a tremendous amount of progress is being made in the field of machine learning, but it is still very hard to directly apply 3D Machine Learning on the architectural design due to the practical constraints on model resolution and training time. Based on the past several years' development of GAN (Generative Adversarial Network), also the method of spatial sequence rules, the authors mainly introduces 3D architectural form style transfer on 2 levels of scale (overall and detailed) through multiple methods of machine learning algorithms which are trained with 2 types of 2D training data set (serial stack and multi-view) at a relatively decent resolution. By exploring how styles interact and influence the original content in neural networks on the 2D level, it is possible for designers to manually control the expected output of 2D images, result in creating the new style 3D architectural model with a clear designing approach.
keywords	3D; Form Finding; Style Transfer; Machine Learning; Architectural Design
series	CAADRIA
email
last changed	2022/06/07 07:57

For more results click below: