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 478

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

_id	acadia20_228
id	acadia20_228
authors	Alawadhi, Mohammad; Yan, Wei
year	2020
title	BIM Hyperreality
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. 228-236.
doi	https://doi.org/10.52842/conf.acadia.2020.1.228
summary	Deep learning is expected to offer new opportunities and a new paradigm for the field of architecture. One such opportunity is teaching neural networks to visually understand architectural elements from the built environment. However, the availability of large training datasets is one of the biggest limitations of neural networks. Also, the vast majority of training data for visual recognition tasks is annotated by humans. In order to resolve this bottleneck, we present a concept of a hybrid system—using both building information modeling (BIM) and hyperrealistic (photorealistic) rendering—to synthesize datasets for training a neural network for building object recognition in photos. For generating our training dataset, BIMrAI, we used an existing BIM model and a corresponding photorealistically rendered model of the same building. We created methods for using renderings to train a deep learning model, trained a generative adversarial network (GAN) model using these methods, and tested the output model on real-world photos. For the specific case study presented in this paper, our results show that a neural network trained with synthetic data (i.e., photorealistic renderings and BIM-based semantic labels) can be used to identify building objects from photos without using photos in the training data. Future work can enhance the presented methods using available BIM models and renderings for more generalized mapping and description of photographed built environments.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2020_402
id	caadria2020_402
authors	Ezzat, Mohammed
year	2020
title	A Framework for a Comprehensive Conceptualization of Urban Constructs - SpatialNet and SpatialFeaturesNet for computer-aided creative urban design
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. 111-120
doi	https://doi.org/10.52842/conf.caadria.2020.2.111
summary	Analogy is thought to be foundational for designing and for design creativity. Nonetheless, practicing analogical reasoning needs a knowledge-base. The paper proposes a framework for constructing a knowledge-base of urban constructs that builds on an ontology of urbanism. The framework is composed of two modules that are responsible for representing either the concepts or the features of any urban constructs' materialization. The concepts are represented as a knowledge graph (KG) named SpatialNet, while the physical features are represented by a deep neural network (DNN) called SpatialFeaturesNet. For structuring SpatialNet, as a KG that comprehensively conceptualizes spatial qualities, deep learning applied to natural language processing (NLP) is employed. The comprehensive concepts of SpatialNet are firstly discovered using semantic analyses of nine English lingual corpora and then structured using the urban ontology. The goal of the framework is to map the spatial features to the plethora of their matching concepts. The granularity Ã nd the coherence of the proposed framework is expected to sustain or substitute other known analogical, knowledge-based, inspirational design approaches such as case-based reasoning (CBR) and its analogical application on architectural design (CBD).
keywords	Domain-specific knowledge graph of urban qualities; Deep neural network for structuring KG; Natural language processing and comprehensive understanding of urban constructs; Urban cognition and design creativity; Case-based reasoning (CBR) and case-based design (CBD)
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2020_259
id	caadria2020_259
authors	Rhee, Jinmo, Veloso, Pedro and Krishnamurti, Ramesh
year	2020
title	Integrating building footprint prediction and building massing - an experiment in Pittsburgh
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. 669-678
doi	https://doi.org/10.52842/conf.caadria.2020.2.669
summary	We present a novel method for generating building geometry using deep learning techniques based on contextual geometry in urban context and explore its potential to support building massing. For contextual geometry, we opted to investigate the building footprint, a main interface between urban and architectural forms. For training, we collected GIS data of building footprints and geometries of parcels from Pittsburgh and created a large dataset of Diagrammatic Image Dataset (DID). We employed a modified version of a VGG neural network to model the relationship between (c) a diagrammatic image of a building parcel and context without the footprint, and (q) a quadrilateral representing the original footprint. The option for simple geometrical output enables direct integration with custom design workflows because it obviates image processing and increases training speed. After training the neural network with a curated dataset, we explore a generative workflow for building massing that integrates contextual and programmatic data. As trained model can suggest a contextual boundary for a new site, we used Massigner (Rhee and Chung 2019) to recommend massing alternatives based on the subtraction of voids inside the contextual boundary that satisfy design constraints and programmatic requirements. This new method suggests the potential that learning-based method can be an alternative of rule-based design methods to grasp the complex relationships between design elements.
keywords	Deep Learning; Prediction; Building Footprint; Massing; Generative Design
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2020_222
id	caadria2020_222
authors	Sun, Chengyu and Hu, Wei
year	2020
title	A Rapid Building Density Survey Method Based on Improved Unet
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. 649-658
doi	https://doi.org/10.52842/conf.caadria.2020.2.649
summary	How to rapidly obtain building density information in a large range is a key problem for architecture and planning. This is because architectural design or urban planning is not isolated, and the environment of the building is influenced by the distribution of other buildings in a larger area. For areas where building density data are not readily available, the current methods to estimate building density are more or less inadequate. For example, the manual survey method is relatively slow and expensive, the traditional satellite image processing method is not very accurate or needs to purchase high-precision multispectral remote sensing image from satellite companies. Based on the deep neural network, this paper proposes a method to quickly extract large-scale building density information by using open satellite images platforms such as Baidu map, Google Earth, etc., and optimizes the application in the field of building and planning. Compared with the traditional method, it has the advantages of less time and money, higher precision, and can provide data support for architectural design and regional planning rapidly and conveniently.
keywords	building density; rapidly and conveniently; neural network
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	acadia20_160
id	acadia20_160
authors	Sun, Yunjuan; Jiang, Lei; Zheng, Hao
year	2020
title	A Machine Learning Method of Predicting Behavior Vitality Using Open Source Data
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. 160-168.
doi	https://doi.org/10.52842/conf.acadia.2020.2.160
summary	The growing popularity of machine learning has provided new opportunities to predict certain behaviors precisely by utilizing big data. In this research, we use an image-based neural network to explore the relationship between the built environment and the activity of bicyclists in that environment. The generative model can produce heat maps that can be used to predict quantitatively the cycling and running activity in a given area, and then use urban design to enhance urban vitality in that area. In the machine learning model, the input image is a plan view of the built environment, and the output image is a heat map showing certain activities in the corresponding area. After it is trained, the model yields output (the predicted heat map) at an acceptable level of accuracy. The heat map shows the levels and conditions of the subject activity in different sections of the built environment. Thus, the predicted results can help identify where regional vitality can be improved. Using this method, designers can not only predict the behavioral heat distribution but also examine the different interactions between behaviors and aspects of the environment. The extent to which factors might influence behaviors is also studied by generating a heat map of the modified plan. In addition to the potential applications of this approach, its limitations and areas for improvement are also proposed.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_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
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_18
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_103
id	cdrf2019_103
authors	Runjia Tian
year	2020
title	Suggestive Site Planning with Conditional GAN and Urban GIS Data
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_10
summary	In architecture, landscape architecture, and urban design, site planning refers to the organizational process of site layout. A fundamental step for site planning is the design of building layout across the site. This process is hard to automate due to its multi-modal nature: it takes multiple constraints such as street block shape, orientation, program, density, and plantation. The paper proposes a prototypical and extensive framework to generate building footprints as masterplan references for architects, landscape architects, and urban designers by learning from the existing built environment with Artificial Neural Networks. Pix2PixHD Conditional Generative Adversarial Neural Network is used to learn the mapping from a site boundary geometry represented with a pixelized image to that of an image containing building footprint color-coded to various programs. A dataset containing necessary information is collected from open source GIS (Geographic Information System) portals from the city of Boston, wrangled with geospatial analysis libraries in python, trained with the TensorFlow framework. The result is visualized in Rhinoceros and Grasshopper, for generating site plans interactively.
series	cdrf
email
last changed	2022/09/29 07:51

_id	caadria2020_046
id	caadria2020_046
authors	Alva, Pradeep, Lee, Han Jie, Lin, Zhuoli, Mehta, Palak, Chen, Jielin and Janssen, Patrick
year	2020
title	Geo-computation for District Planning - An Agile Automated Modelling Approach
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. 793-802
doi	https://doi.org/10.52842/conf.caadria.2020.1.793
summary	This paper focuses on developing a novel geo-computational methodology for automating the generation of design options for district planning. The knowledge contribution focuses on the ability of the planners and designers to interact with and override the automated process. This approach is referred to as "agile automated modelling". The approach is demonstrated through a case study in which three adjacent districts are generated with a total area of approximately 1300 hectares. An automated modelling process is implemented based on a set of core planning principles established by the planners. The automated process generates street networks, land parcels, and 3-dimensional urban models. The process is broken down into three steps and users are then able to intervene at the end of every step to override and modify the outputs. This aims to help planners and designers to iteratively generate and assess various planning outcomes.
keywords	Geo-computation; procedural modelling; GIS; planning automation; neural network
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	ecaade2020_089
id	ecaade2020_089
authors	Ardic, Sabiha Irem, Kirdar, Gulce and Lima, Angela Barros
year	2020
title	An Exploratory Urban Analysis via Big Data Approach: Eindhoven Case - Measuring popularity based on POIs, accessibility and perceptual quality parameters
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. 309-318
doi	https://doi.org/10.52842/conf.ecaade.2020.2.309
summary	The cities are equipped with the data as a result of the individuals' sharings and application usage. This significant amount of data has the potential to reveal relations and support user-centric decision making. The focus of the research is to examine the relational factors of the neighborhoods' popularity by implementing a big data approach to contribute to the problem of urban areas' degradation. This paper presents an exploratory urban analysis for Eindhoven at the neighborhood level by considering variables of popularity: density and diversity of points of interest (POI), accessibility, and perceptual qualities. The multi-sourced data are composed of geotagged photos, the location and types of POIs, travel time data, and survey data. These different datasets are evaluated using BBN (Bayesian Belief Network) to understand the relationships between the parameters. The results showed a positive and relatively high connection between popularity - population change, accessibility by walk - density of POIs, and the feeling of safety - social cohesion. For further studies, this approach can contribute to the decision-making process in urban development, specifically in real estate and tourism development decisions to evaluate the land prices or the hot-spot touristic places.
keywords	big data approach; neighborhood analysis; popularity; point of interest (POI); accessibility; perceptual quality
series	eCAADe
email
last changed	2022/06/07 07:54

_id	caadria2020_118
id	caadria2020_118
authors	Chow, Ka Lok and van Ameijde, Jeroen
year	2020
title	Generative Housing Communities - Design of Participatory Spaces in Public Housing Using Network Configurational Theories
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. 283-292
doi	https://doi.org/10.52842/conf.caadria.2020.2.283
summary	This research-by-design project explores how public housing estates can accommodate social diversity and the appropriation of shared spaces, using qualitative and quantitative analysis of circulation networks. A case study housing estate in Hong Kong was analysed through field observations of movements and activities and as a site for the speculative re-design of shared spaces. Generative design processes were developed based on several parameters, including shortest paths, visibility integration and connectivity integration (Hillier & Hanson, 1984). Additional tools were developed to combine these techniques with optimisation of sunlight access, maximisation of views for residential towers and the provision of permeability of ground level building volumes. The project demonstrates how flexibility of use and social engagement can constitute a platform for self-organisation, similar to Jane Jacobs' notion of vibrant streets leading to active and progressive communities. It shows how computational design and configurational theories can promote a bottom-up approach for generating new types of residential environments that support participatory and diverse communities, rather than a conventional top-down approach that is perceived to embody mechanisms of social regimentation.
keywords	Urban Planning and Design; Network Configuration; Community Space and Social Interaction; Hong Kong Public Housing
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2020_190
id	caadria2020_190
authors	Karakiewicz, Justyna, Holguin, Jose Rafael and Kvan, Thomas
year	2020
title	Hope in Perturbanism
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. 41-50
doi	https://doi.org/10.52842/conf.caadria.2020.2.041
summary	A fundamental assumption in this conference is that human actions in creating and modifying our constructed environments can be rethought and made better for the environment. There are few laboratories in which to conduct research; an isolated island system offers one such opportunity. This paper reflects on work that carried out in the past five years in the Galapagos Islands by a collaborative of researchers from five institutions. The research examines potential positive changes in urban settlements and their impact on a fragile ecology of the islands. In this work, we illustrate how small perturbations (disturbances) within urban systems can lead to changes not only within urban form but also in the citizen's environmental awareness and how these, in turn, can lead to positive changes in the environment. The paper discusses applications of models we developed using Python scripting, GIS, and agent-based modelling, as we applied them to design strategies, built outcomes and community awareness.
keywords	complex adaptive systems; urban design; CAS; panarchy
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2020_167
id	ecaade2020_167
authors	Newton, David, Piatkowski, Dan, Marshall, Wesley and Tendle, Atharva
year	2020
title	Deep Learning Methods for Urban Analysis and Health Estimation of Obesity
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. 297-304
doi	https://doi.org/10.52842/conf.ecaade.2020.1.297
summary	In the 20th and 21st centuries, urban populations have increased dramatically with a whole host of impacts to human health that remain unknown. Research has shown significant correlations between design features in the built environment and human health, but this research has remained limited. A better understanding of this relationship could allow urban planners and architects to design healthier cities and buildings for an increasingly urbanized population. This research addresses this problem by using discriminative deep learning in combination with satellite imagery of census tracts to estimate rates of obesity. Data from the California Health Interview Survey is used to train a Convolutional Neural Network that uses satellite imagery of selected census tracts to estimate rates of obesity. This research contributes knowledge on methods for applying deep learning to urban health estimation, as well as, methods for identifying correlations between urban morphology and human health.
keywords	Deep Learning; Artificial Intelligence; Urban Planning; Health; Remote Sensing
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2020_384
id	caadria2020_384
authors	Patt, Trevor Ryan
year	2020
title	Spectral Clustering for Urban Networks
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. 91-100
doi	https://doi.org/10.52842/conf.caadria.2020.2.091
summary	As planetary urbanization accelerates, the significance of developing better methods for analyzing and making sense of complex urban networks also increases. The complexity and heterogeneity of contemporary urban space poses a challenge to conventional descriptive tools. In recent years, the emergence of urban network analysis and the widespread availability of GIS data has brought network analysis methods into the discussion of urban form. This paper describes a method for computationally identifying clusters within urban and other spatial networks using spectral analysis techniques. While spectral clustering has been employed in some limited urban studies, on large spatialized datasets (particularly in identifying land use from orthoimages), it has not yet been thoroughly studied in relation to the space of the urban network itself. We present the construction of a weighted graph Laplacian matrix representation of the network and the processing of the network by eigen decomposition and subsequent clustering of eigenvalues in 4d-space.In this implementation, the algorithm computes a cross-comparison for different numbers of clusters and recommends the best option based on either the 'elbow method,' or by "eigen gap" criteria. The results of the clustering operation are immediately visualized on the original map and can also be validated numerically according to a selection of cluster metrics. Cohesion and separation values are calculated simultaneously for all nodes. After presenting these, the paper also expands on the 'silhouette' value, which is a composite measure that seems especially suited to urban network clustering.This research is undertaken with the aim of informing the design process and so the visualization of results within the active 3d model is essential. Within the paper, we illustrate the process as applied to formal grids and also historic, vernacular urban fabric; first on small, extract urban fragments and then over an entire city networks to indicate the scalability.
keywords	Urban morphology; network analysis; spectral clustering; computation
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ecaade2020_534
id	ecaade2020_534
authors	Verniz, Debora and Duarte, José P
year	2020
title	From Analysis to Design - A framework for developing synthetic shape grammars
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. 535-544
doi	https://doi.org/10.52842/conf.ecaade.2020.2.535
summary	This paper focuses on the problem of lack of housing, due to fast urbanization processes and urban population growth, particularly in developing regions of the globe. The goal is to propose an alternative for planning housing settlements, using a computational-based approach, and having as a case study an existing Brazilian favela, Santa Marta. The paper proposes a strategy to bridge between the use of shape grammars from analysis to design, by performing changes on the rule level. The research includes the development of an analytical grammar that captures the physical features of the settlement and its subsequent transformation into a synthetic grammar that can generate urban configurations that keep key features of the original settlement while avoiding its flaws. The paper is focused on the grammatical transformations performed to the analytic grammar to obtain the synthetic grammar and its subsequent validation. Results show that the solutions generated by the synthetic grammar do have higher quality when compared to the case study. This strategy is proposed as a framework for the application of shape grammars in design.
keywords	shape grammars; grammatical transformations; Santa Marta favela; Santa Marta Urban Grammar
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2020_172
id	caadria2020_172
authors	Xia, Xinyu and Tong, Ziyu
year	2020
title	A Machine Learning-Based Method for Predicting Urban Land Use
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. 21-30
doi	https://doi.org/10.52842/conf.caadria.2020.2.021
summary	Land use is one of the most basic elements of urban management. In urban planning and design, land use is often determined by experience and case studies. However, the development of urbanization has led to a combinatory trend for land use, and the land use of a plot is always impacted by the surrounding environment. In such a complex situation, it is difficult to find hidden relationships among types of land use by humans alone. Within artificial intelligence, machine learning can help find correlations among data. This paper presents a new method for learning the rules relating the known land use data and predicting the land use of a target plot by constructing an artificial neural network. We take Nanjing as a specific case and study the logic of its land use. The results not only demonstrate associations between the surroundings and the target but also show the feasibility of a combinatory land use index in urban planning and design.
keywords	Land use; Urban planning and design; Machine learning; Artificial neural network
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2020_007
id	ecaade2020_007
authors	Yu, De
year	2020
title	Reprogramming Urban Block by Machine Creativity - How to use neural networks as generative tools to design space
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. 249-258
doi	https://doi.org/10.52842/conf.ecaade.2020.1.249
summary	The democratization of design requires balancing all sorts of factors in space design. However, the traditional way to organize spatial relationships cannot deal with such complex design objectives. Can one find another form of creativity rather the human brain to design space? As Margaret Boden mentioned, "computers and creativity make interesting partners with respect to two different projects." This paper addresses whether machine creativity in the form of neural networks could be considered as a powerful generative tool to reprogram urban block in order to meet multi-users' needs. It tested this theory in a specific block model called Agri-tecture, a new architectural form combing farming with the urban built environment. Specifically, the machine empowered by Generative Adversarial Network designed spatial layouts based on learning the existing cases. Nevertheless, since the machine can hardly avoid errors, architects need to intervene and verify the machine's work. Thus, a synergy between human creativity and machine creativity is called for.
keywords	machine creativity; Generative Adversarial Network; spatial layout; creativity combination; Agri-tecture
series	eCAADe
email
last changed	2022/06/07 07:57

_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	artificial_intellicence2019_207
id	artificial_intellicence2019_207
authors	Hao Zheng
year	2020
title	Form Finding and Evaluating Through Machine Learning: The Prediction of Personal Design Preference in Polyhedral Structures
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2025)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_13
summary	3D Graphic Statics (3DGS) is a geometry-based structural design and analysis method, helping designers to generate 3D polyhedral forms by manipulating force diagrams with given boundary conditions. By subdividing 3D force diagrams with different rules, a variety of forms can be generated, resulting in more members with shorter lengths and richer overall complexity in forms. However, it is hard to evaluate the preference toward different forms from the aspect of aesthetics, especially for a specific architect with his own scene of beauty and taste of forms. Therefore, this article proposes a method to quantify the design preference of forms using machine learning and find the form with the highest score based on the result of the preference test from the architect. A dataset of forms was firstly generated, then the architect was asked to keep picking a favorite form from a set of forms several times in order to record the preference. After being trained with the test result, the neural network can evaluate a new inputted form with a score from 0 to 1, indicating the predicted preference of the architect, showing the possibility of using machine learning to quantitatively evaluate personal design taste.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	ecaade2020_093
id	ecaade2020_093
authors	Veloso, Pedro and Krishnamurti, Ramesh
year	2020
title	An Academy of Spatial Agents - Generating spatial configurations with deep reinforcement learning
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. 191-200
doi	https://doi.org/10.52842/conf.ecaade.2020.2.191
summary	Agent-based models rely on decentralized decision making instantiated in the interactions between agents and the environment. In the context of generative design, agent-based models can enable decentralized geometric modelling, provide partial information about the generative process, and enable fine-grained interaction. However, the existing agent-based models originate from non-architectural problems and it is not straight-forward to adapt them for spatial design. To address this, we introduce a method to create custom spatial agents that can satisfy architectural requirements and support fine-grained interaction using multi-agent deep reinforcement learning (MADRL). We focus on a proof of concept where agents control spatial partitions and interact in an environment (represented as a grid) to satisfy custom goals (shape, area, adjacency, etc.). This approach uses double deep Q-network (DDQN) combined with a dynamic convolutional neural-network (DCNN). We report an experiment where trained agents generalize their knowledge to different settings, consistently explore good spatial configurations, and quickly recover from perturbations in the action selection.
keywords	space planning; agent-based model; interactive generative systems; artificial intelligence; multi-agent deep reinforcement learning
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2020_320
id	caadria2020_320
authors	Cheng, Jiahui, Zhang, Zhuoqun and Peng, Chengzhi
year	2020
title	Parametric Modelling and Simulation of an Indoor Temperature Responsive Rotational Shading System Design
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. 579-588
doi	https://doi.org/10.52842/conf.caadria.2020.1.579
summary	We present a digital design strategy for developing an intelligent rotational shading system responsive to changes in indoor temperatures. The strategy was first modelled with an Arduino-based physical prototype, identifying the concept of "mapping" between building indoor air temperature and rotational movement (angle) of external solar shading. A virtual parametric modelling approach was then followed to test three methods of mapping: linear, quadratic and logarithmic. The aim was to examine the performative differences exhibited by the three mapping methods in terms of the total comfort hours and estimated cooling energy demand during summer months. A typical cellular office in the Arts Tower of University of Sheffield was chosen for the parametric modelling (Rhino-Grasshopper) and environmental simulation (Honeybee-Ladybug) of horizontal and vertical rotational shading system design. The simulation shows that the horizontal shading system rotating according to the linear mapping methods achieve greater total comfort hours with lower cooling energy demand in the case of Arts Tower in Sheffield, UK.
keywords	indoor temperature responsive shading; temperature-angle mapping; parametric design; kinetic shading; overheating
series	CAADRIA
email
last changed	2022/06/07 07:55

For more results click below: