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 676

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

_id	ecaade2022_47
id	ecaade2022_47
authors	Marsillo, Laura, Suntorachai, Nawapan, Karthikeyan, Keshava Narayan, Voinova, Nataliya, Khairallah, Lea and Chronis, Angelos
year	2022
title	Context Decoder - Measuring urban quality through artificial intelligence
doi	https://doi.org/10.52842/conf.ecaade.2022.2.237
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. 237–246
summary	Understanding the quality of places during the early design process can improve design decision making and increase not only the chance of effective site development for the place and surroundings but also provide foresight to the mental, physical and environmental well-being of the future occupants. A context can be described differently depending on the designer's studies. However, in order to view the place holistically, various layers should be considered for a cross-disciplinary correlation. This paper proposes a prototypical tool to evaluate the quality of places using machine learning to help cluster and visualise design metrics according to the features provided. By selecting a location in a city, it offers other site contexts with similar characteristics and a similar level of complexity in relation to the surroundings. The tool was initially developed for Naples (Italy) as a case study city and incorporates key indicators related to connectivity of amenities, walkability, urban density, population density, outdoor thermal comfort, popular rate review and sentiment analysis from social media. With current open-source data, these indicators such as OpenStreetMap or social media sentiment can be collected with embedded geotags. These site-specific multilayers were evaluated under the metrics of 3 ranges i.e 400, 800 and 1,200-metre walking distance. This paper demonstrates the potential of using machine learning integrated with computational design tools to visualise the otherwise invisible data for users to interpret any context comprehensively in a holistic approach. Even though this tool is made for Naples, this tool can be extended to other cities across the world. As a result, the tool assists users in understanding not only site-specific location but also draws lines to other neighbourhoods within the city with a similar phenomenon of correlation between key performance indicators.
keywords	Computational Design, Urban Analysis, Machine Learning, Computer Vision, Sentiment Analysis
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ascaad2022_062
id	ascaad2022_062
authors	Kanter, Jordan; Quinteros, Kamil
year	2022
title	Gestural Design: Hand Tracking for Digital Drawing
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. 30-42
summary	Computational design is increasingly interested in the active feedback between the user/designer and the digital space. Often, our initial instinct as designers comes from a gesture, a movement of the hands that gets translated into sketches and 3D models via the tools available to us. While the physical realm allows for muscle memory, tactile feedback, and creative output via movement, digital design often negates the body of the designer as it sequesters us into a screen-mouse-hand relationship. Moreover, current CAD software tools often reinforce this standardization, further limiting the potential of physical bodily gestures as a vehicle for architectural form-making. Seeking new opportunities for a gestural interface, this research explores how Machine Learning and parametric design tools can be used to translate active movements and gestural actions into rich and complex digital models without the need of specialized equipment. In this paper, we present an open-source and economically accessible methodology for designers to translate hand movements into the digital world, implementing the MediaPipe Hands tracking library. In developing this workflow, this research explores opportunities to create more direct, vital links between expressive gesture and architectural form, with an emphasis on creating platforms that are accessible not only to design experts, but also the broader public.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	cdrf2022_304
id	cdrf2022_304
authors	Anni Dai
year	2022
title	Co-creation: Space Reconfiguration by Architect and Agent Simulation Based Machine Learning
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_27
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	This research is a manifestation of architectural co-creation between agent simulation based machine learning and an architect’s tacit knowledge. Instead of applying machine learning brains to agents, the author reversed the idea and applied machine learning to buildings. The project used agent simulation as a database, and trained the space to reconfigure itself based on its distance to the nearest agents. To overcome the limitations of machine learning model’s simplified solutions to complicated architectural environments, the author introduced a co-creation method, where an architect uses tacit knowledge to overwatch and have real-time control over the space reconfiguration process. This research combines both the strength of machine learning’s data-processing ability and an architect’s tacit knowledge. Through exploration of emerging technologies such as machine learning and agent simulation, the author highlights limitations in design automation. By combining an architect’s tacit knowledge with a new generation design method of agent simulation based machine learning, the author hopes to explore a new way for architects to co-create with machines.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ecaade2022_251
id	ecaade2022_251
authors	Awan, Abeeha, Lombardi, Davide, Ruffino, Paolo and Agkathidis, Asterios
year	2022
title	Efficacy of Gamification on Introductory Architectural Education: a literature review
doi	https://doi.org/10.52842/conf.ecaade.2022.2.553
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. 553–564
summary	Due to their recent popularity and success in fields such as engineering and business, gamification and by extension game design principles demonstrate the ability to teach complex, multi-disciplinary skills in an engaging, entertaining, and effective way. Architectural education especially introductory architectural education is a foundational and fundamental part of a budding architecture student’s career and oftentimes requires the understanding of dynamic systems, spatial reasoning, and experiential learning. The paper posits that gamification and game design principles can utilize certain components such as augmented reality, narrative design, and fun in order to create tools, gamify existing curriculum, and increase retention, engagement, and mastery of the difficult high-tech skillsets required of introductory architects. The paper focuses on reviewing and systematically analyzing research on gamification in education. In particular, it focuses on systematically reviewing and analyzing data from multiple relevant case studies chosen based on the application of technology such as augmented reality, the integration of game design, and the feasibility of gamification in educational environments. This data is examined based on feasibility, accessibility, and effects on information retention and the findings are outlined in a comparative table of methods, tools, and technologies organized based on their suitability. Ultimately, the paper aims to establish a framework for gamifying introductory modules in architectural education and hopes to create a future architectural augmented reality game meant to utilize gamification to help new architectural students.
keywords	Gamification, Game Design, Architectural Education, Educational Games, Retention, Learning
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_166
id	caadria2022_166
authors	Eisenstadt, Viktor, Bielski, Jessica, Mete, Burak, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2022
title	Autocompletion of Floor Plans for the Early Design Phase in Architecture: Foundations, Existing Methods, and Research Outlook
doi	https://doi.org/10.52842/conf.caadria.2022.1.323
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. 323-332
summary	This paper contributes the current research state and possible future developments of AI-based autocompletion of architectural floor plans and shows demand for its establishment in computer-aided architectural design to facilitate decent work, economic growth through accelerating the design process to meet the future workload. Foundations of data representations together with the autocompletion contexts are defined, existing methods described and evaluated in the integrated literature review, and criteria for qualitative and sustainable autocompletion are proposed. Subsequently, we contribute three unique deep learning-based autocompletion methods currently in development for the research project metis-II. They are described in detail from a technical point of view on the backdrop of how they adhere to the proposed criteria for creating our novel AI.
keywords	Artificial Intelligence, Architectural Design, Floor Plan, Autocompletion, SDG 8, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_239
id	caadria2022_239
authors	Huang, Chenyu, Zhang, Gengjia, Yin, Minggang and Yao, Jiawei
year	2022
title	Energy-driven Intelligent Generative Urban Design, Based on Deep Reinforcement Learning Method With a Nested Deep Q-R Network
doi	https://doi.org/10.52842/conf.caadria.2022.1.233
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. 233-242
summary	To attain "carbon neutrality," lowering urban energy use and increasing the use of renewable resources have become critical concerns for urban planning and architectural design. Traditional energy consumption evaluation tools have a high operational threshold, requiring specific parameter settings and cross-disciplinary knowledge of building physics. As a result, it is difficult for architects to manage energy issues through 'trial and error' in the design process. The purpose of this study is to develop an automated workflow capable of providing urban configurations that minimizing the energy use while maximizing rooftop photovoltaic power potential. Based on shape grammar, parametric meta models of three different urban forms were developed and batch simulated for its energy performance. Deep reinforcement learning (DRL) is introduced to find the optimal solution of the urban geometry. A neural network was created to fit a real-time mapping of urban form indicators to energy performance and was utilized to predict reward for the DRL process, namely a Deep R-Network, while nested within a Deep Q-Network. The workflow proposed in this paper promotes efficiency in optimizing the energy performance of solutions in the early stages of design, as well as facilitating a collaborative design process with human-machine interaction.
keywords	energy-driven urban design, intelligent generative design, rooftop photovoltaic power, deep reinforcement learning, SDG 11, SDG 12
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ijac202220302
id	ijac202220302
authors	Kabošová, Lenka; Angelos Chronis; Theodoros Galanos
year	2022
title	Fast wind prediction incorporated in urban city planning
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 3, pp. 511–527
summary	Digital design and analysis tools are continually progressing, enabling more seamless integration of climatic impacts into the conceptual design stage, which naturally means enhanced environmental performance of the final designs. Planning sustainable urban configurations and, consequently, environment-derived architectural forms becomes more rapid and requires less effort enabling smooth incorporation into day-to-day practice. This research paper presents a wind prediction-based architectural design method for improving outdoor wind comfort through urbanism and architecture. The added value of the environment-driven design loop consisting of parametric design, wind flow analysis, and necessary design modifications lies in leveraging the newly developed wind prediction tool InFraRed. As is demonstrated in the application study in Kosice, Slovakia, iterating through various design options and evaluating their impact on the wind flow is swift and reliable. That enables the designer to explore the best-performing design alternatives for outdoor wind comfort, yet the extra time required for the analysis is negligible
keywords	real-time wind predictions, wind comfort, parametric design, computational fluid dynamics analysis, machine learning, infrared
series	journal
last changed	2024/04/17 14:29

_id	caadria2022_279
id	caadria2022_279
authors	Kim, Dongyun, Guida, George and Garcia del Castillo y Lopez, Jose Luis
year	2022
title	PlacemakingAI : Participatory Urban Design with Generative Adversarial Networks
doi	https://doi.org/10.52842/conf.caadria.2022.2.485
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. 485-494
summary	Machine Learning (ML) is increasingly present within the architectural discipline, expanding the current possibilities of procedural computer-aided design processes. Practical 2D design applications used within concept design stages are however limited by the thresholds of entry, output image fidelity, and designer agency. This research proposes to challenge these limitations within the context of urban planning and make the design processes accessible and collaborative for all urban stakeholders. We present PlacemakingAI, a design tool made to envision sustainable urban spaces. By converging supervised and unsupervised Generative Adversarial Networks (GANs) with a real-time user interface, the decision-making process of planning future urban spaces can be facilitated. Several metrics of walkability can be extracted from curated Google Street View (GSV) datasets when overlayed on existing street images. The contribution of this framework is a shift away from traditional design and visualization processes, towards a model where multiple design solutions can be rapidly visualized as synthetic images and iteratively manipulated by users. In this paper, we discuss the convergence of both a generative image methodology and this real-time urban prototyping and visualization tool, ultimately fostering engagement within the urban design process for citizens, designers, and stakeholders alike.
keywords	Machine Learning, Generative Adversarial Networks, user interface, real-time, walkability, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_203
id	ecaade2022_203
authors	Kim, Frederick Chando and Huang, Jeffrey
year	2022
title	Perspectival GAN - Architectural form-making through dimensional transformation
doi	https://doi.org/10.52842/conf.ecaade.2022.1.341
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. 341–350
summary	With the ascendance of Generative Adversarial Networks (GAN), promising prospects have arisen from the abilities of machines to learn and recognize patterns in 2D datasets and generate new results as an inspirational tool in architectural design. Insofar as the majority of ML experiments in architecture are conducted with imagery based on readily available 2D data, architects and designers are faced with the challenge of transforming machine-generated images into 3D. On the other hand, GAN-generated images are found to be able to learn the 3D information out of 2D perspectival images. To facilitate such transformation from 2D and 3D data in the framework of deep learning in architecture, this paper explores making new architectural forms from flat GAN images by employing traditional tools of projective geometry. The experiments draw on Brook Taylor’s 19th- century theorem of inverse projection system for creating architectural form from perspectival information learned from GAN images of Swiss alpine architecture. The research develops a parametric tool that automates the dimensional transformation of 2D images into 3D architectural forms. This research identifies potential synergic interactions between traditional tools and techniques of architects and deep learning algorithms to achieve collective intelligence in designing and representing creative architecture forms between humans and machines.
keywords	Machine Learning, GAN, Architectural Form, Perspective Projection, Inverse Perspective, Digital Representation
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_176
id	ecaade2022_176
authors	Kotov, Anatolii, Starke, Rolf and Vukorep, Ilija
year	2022
title	Spatial Agent-based Architecture Design Simulation Systems
doi	https://doi.org/10.52842/conf.ecaade.2022.2.105
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. 105–112
summary	This paper presents case studies and analysis of agent-based reinforcement learning (RL) systems towards practical applications for specific architecture/engineering tasks using Unity 3D-based simulation methods. Finding and implementing sufficient abstraction for architecture and engineering problems to be solved by agent-based systems requires broad architectural knowledge and the ability to break down complex problems. Modern artificial intelligence (AI) and machine learning (ML) systems based on artificial neural networks can solve complex problems in different domains such as computer vision, language processing, and predictive maintenance. The paper will give a theoretical overview, such as more theoretical abstractions like zero-sum games, and a comparison of presented games. The application section describes a possible categorization of practical usages. From more general applications to more narrowed ones, we explore current possibilities of RL application in the field of relatable problems. We use the Unity 3D engine as the basis of a robust simulation environment.
keywords	AI Aided Architecture, Reinforcement Learning, Agent Simulation
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_120
id	caadria2022_120
authors	Lin, Yuxin
year	2022
title	Rhetoric, Writing, and Anexact Architecture: The Experiment of Natural Language Processing (NLP) and Computer Vision (CV) in Architectural Design
doi	https://doi.org/10.52842/conf.caadria.2022.1.343
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. 343-352
summary	This paper presents a novel language-driven and artificial intelligence-based architectural design method. This new method demonstrates the ability of neural networks to integrate the language of form through written texts and has the potential to interpret the texts into sustainable architecture under the topic of the coexistence between technologies and humans. The research merges natural language processing, computer vision, and human-machine interaction into a machine learning-to-design workflow. This article encompasses the following topics: 1) an experiment of rethinking writing in architecture through anexact form as rhetoric; 2) an integrative machine learning design method incorporating Generative Pre-trained Transformer 2 model and Attentional Generative Adversarial Networks for sustainable architectural production with unique spatial feeling; 3) a human-machine interaction framework for model generation and detailed design. The whole process is from inexact to exact, then finally anexact, and the key result is a proof-of-concept project: Anexact Building, a mixed-use building that promotes sustainability and multifunctionality under the theme of post-carbon. This paper is of value to the discipline since it applies current and up-to-date digital tools research into a practical project.
keywords	Rhetoric and writing, Natural Language Processing, Computer Vision, GPT-2, AttnGAN, Human-computer Interaction, Architectural Design, Post-carbon, SDG3, SDG11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_276
id	caadria2022_276
authors	Mondal, Tushar
year	2022
title	Autonomous Transhumance
doi	https://doi.org/10.52842/conf.caadria.2022.2.253
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. 253-262
summary	The Arctic is a zone of confluent resources where climate change has begun disrupting the once stable ecological and transhumant lifestyles. Encroachment on pastureland by oil, gas and mining facilities limit reindeer herding activity, and the presence of such infrastructure continues to alter their sensory perceptions and consequently their capacity to read and navigate their environment. Parallel to this, thawing permafrost results in the release of gaseous methane, causing landforms called pingos to explode without detectable warning. This paper proposes a strategy for adapting to these rapid changes by implementing an autonomous system to balance the Arctic ecology through two mutual dependent interventions- (1) Regenerating the pingos to prevent explosion and create new pastoral lands. (2) Seasonally herding the reindeer to these new pastures. The project uses primary data, physical tests, and current technological tools to inform the discourse and suggest a derivative solution. Advanced computational tools like machine learning, robotics, and simulations are used to speculate upon the post-carbon Arctic ecology. The project performs through a strategy of local interventions, networking the living and non-living agents in a tight rope act that balances the Arctic ecology.
keywords	Arctic, Pingo, Regenerated Landscape, Reindeer, Autonomous Herding, SDG 13, SDG 15
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ascaad2022_099
id	ascaad2022_099
authors	Sencan, Inanc
year	2022
title	Progeny: A Grasshopper Plug-in that Augments Cellular Automata Algorithms for 3D Form Explorations
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. 377-391
summary	Cellular automata (CA) is a well-known computation method introduced by John von Neumann and Stanislaw Ulam in the 1940s. Since then, it has been studied in various fields such as computer science, biology, physics, chemistry, and art. The Classic CA algorithm is a calculation of a grid of cells' binary states based on neighboring cells and a set of rules. With the variation of these parameters, the CA algorithm has evolved into alternative versions such as 3D CA, Multiple neighborhood CA, Multiple rules CA, and Stochastic CA (Url-1). As a rule-based generative algorithm, CA has been used as a bottom-up design approach in the architectural design process in the search for form (Frazer,1995; Dinçer et al., 2014), in simulating the displacement of individuals in space, and in revealing complex relations at the urban scale (Güzelci, 2013). There are implementations of CA tools in 3D design software for designers as additional scripts or plug-ins. However, these often have limited ability to create customized CA algorithms by the designer. This study aims to create a customizable framework for 3D CA algorithms to be used in 3D form explorations by designers. Grasshopper3D, which is a visual scripting environment in Rhinoceros 3D, is used to implement the framework. The main difference between this work and the current Grasshopper3D plug-ins for CA simulation is the customizability and the real-time control of the framework. The parameters that allow the CA algorithm to be customized are; the initial state of the 3D grid, neighborhood conditions, cell states and rules. CA algorithms are created for each customizable parameter using the framework. Those algorithms are evaluated based on the ability to generate form. A voxel-based approach is used to generate geometry from the points created by the 3D cellular automata. In future, forms generated using this framework can be used as a form generating tool for digital environments.
series	ASCAAD
email
last changed	2024/02/16 13:38

_id	cdrf2022_78
id	cdrf2022_78
authors	Sharif Anouar, Adam Anouar, and Ayoub Lharchi
title	Heritage Information Modeling: The Case of Chellah’s Gate
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_7
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	This paper aims to propose an integrated workflow for the digitization of the built cultural heritage. To this end, we leverage the power of computational tools and the relevancy of Building Information Modeling (BIM) process to overcome the limitations and challenges faced by Scan-to-BIM. We describe the automatic generation of an as-built BIM model of a heritage building in a three-step procedure. Firstly, we outline the data acquisition method of the point cloud. Secondly, we describe the automatic processing and segmentation of the point cloud according to architectural elements using Machine Learning. Then, we tested and compared various meshing algorithms and utilized a combination depending on the desired level of details. Lastly, the resulting geometry is converted into a BIM object that will be subsequently semantically labeled. We used a UNESCO world heritage in Morocco—Chellah, as a case study to test the robustness of our protocol.
email
last changed	2024/05/29 14:02

_id	caadria2022_267
id	caadria2022_267
authors	Toohey, Gabrielle, Nguyen, Tommy Bao Nghi, Vilppola, Ritva, Qiu, Waishan, Li, Wenjing and Luo, Dan
year	2022
title	Data-Driven Evaluation of Streets to Plan for Bicycle Friendly Environments: A Case Study of Brisbane Suburbs
doi	https://doi.org/10.52842/conf.caadria.2022.1.243
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. 243-252
summary	Empirical cycling data from across the world illustrates the many barriers that car-dependent cities face when implementing cycling programs and infrastructure. Most studies focus on physical criteria, while perception criteria are less addressed. The correlations between the two are still largely unknown. This paper introduces a methodology that utilises computer vision analysis techniques to evaluate 15,383 Google Street View Images (SVI) of Brisbane City against both physical and perception cycling criteria. The study seeks to better understand correlations between the quality of a street environment and an urban area's 'bicycle-friendliness'. PSPNet Image Segmentation is utilised against SVIs to determine the percentage of an image corresponding with objects and the environment related to specific cycling factors. For physical criteria, these images are then further analysed by Masked RCNN processes. For perception criteria, subjective ranking of the images is undertaken using Machine Learning (ML) techniques to score images based on survey data. The methodology effectively allows for current findings in cycling research to be further utilised in combination via computer visioning (CV) and ML applications to measure different physical elements and urban design qualities that correspond with bicycle-friendliness. Such findings can assist targeted design strategies for cities to encourage the use of safer and more sustainable modes of transport.
keywords	Bicycle-friendly, Quality Streetscapes, Active Living, Visual Assessment, Computer Visioning, Machine Learning, SDG 3, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_223
id	ecaade2022_223
authors	Tuzun Canadinc, Seda and Yan, Wei
year	2022
title	3D-Model-Based Augmented Reality for Enhancing Physical Architectural Models
doi	https://doi.org/10.52842/conf.ecaade.2022.2.495
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. 495–504
summary	In the presentation of architectural projects, physical models are still commonly used as a powerful and effective representation for building design and construction. On the other hand, Augmented Reality (AR) promises a wide range of possibilities in visualizing and interacting with 3D physical models, enhancing the modeling process. To benefit both, we present a novel medium for architectural representation: a marker-less AR powered physical architectural model that employs dynamic digital features. With AR enhancement, physical capabilities of a model could be extended without sacrificing its tangibility. We developed a framework to investigate the potential uses of 3D-model- based AR registration method and its augmentation on physical architectural models. To explore and demonstrate integration of physical and virtual models in AR, we designed this framework providing physical and virtual model interaction: a user can manipulate the physical model parts or control the visibility and dynamics of the virtual parts in AR. The framework consists of a LEGO model and an AR application on a hand-held device which was developed for this framework. The AR application utilizes a marker-less AR registration method and employs a 3D-model-based AR registration. A LEGO model was proposed as the physical 3D model in this registration process and machine learning training using Vuforia was utilized for the AR application to recognize the LEGO model from any point of view to register the virtual models in AR. The AR application also employs a user interface that allows user interaction with the virtual parts augmented on the physical ones. The working application was tested over its registration, physical and virtual interactions. Overall, the adoption of AR and its combination with physical models, and 3D-model-based AR registration allow for many advantages, which are discussed in the paper.
keywords	Augmented Reality, AR, 3D-model based AR, Architectural Representation, Architectural Modeling
series	eCAADe
email
last changed	2024/04/22 07:10

_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	caadria2022_393
id	caadria2022_393
authors	Yu, Daniel, Irger, Matthias, Tohidi, Alex and Haeusler, Matthias Hank
year	2022
title	Designing Out Heat ‚ Developing a Computer-Aided Street Layout Tool to Address Urban Heat in Existing Streets and Suburbs
doi	https://doi.org/10.52842/conf.caadria.2022.2.739
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. 739-748
summary	As cities are getting hotter, the urban heat islands effect will become an increased concern for cities. While urban heat migration strategies are well researched and understood, some strategies of implementing urban heat mitigation focus on private land - thus depend on the owner's uptake. This research shifts mitigation strategies to the public land where governments have legislative control over the corridor between privately owned cadastral ‚ the street corridor. This paper asks the question how a computational tool could assist councils in redesigning streets to mitigate urban heat. Literature review confirmed a direct relationship between the magnitude of urban heat and street layout, vegetation and materials used, position of street to sun and wind direction - yet no tool that assists a designer exists - the focus of the research. We present first findings and the iterative development of our street design tool. Via our tool one can alter variables such as vegetation type, materials or street configuration until urban heat mitigation is optimized. This is a significant step towards cooling our cities as designers now have a process that translates expert knowledge on urban heat into a tool that lets them design as well as evaluate their design.
keywords	Urban heat island, landscape architecture, urban design, traffic engineering, computational tools, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	cdrf2022_233
id	cdrf2022_233
authors	Yubo Liu, Zhilan Zhang, and Qiaoming Deng
year	2022
title	Exploration on Diversity Generation of Campus Layout Based on GAN
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_20
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	Previous studies have shown that GAN has made some progress in the generation of campus layout plan, but the result is single output for single input condition. This paper hopes to make some attempts and explorations on the diversity generation of campus planning layout design by machine learning. Based on Pix2Pix model, this paper proposes a method to divide image channels so that both the campus function bubble diagram and the site boundary can both become the input conditions. There is a strong correspondence between the campus functional bubble diagram and the campus layout. The main idea of this study is to control the generated results by changing the input of the campus functional bubble diagram, so that we can have a diversity layout of campus according to the same site conditions. In the experiment, we train thirty samples of campus planning layout design, and finally evaluate the generated results in a qualitative and quantitative way, which proves that the generated results are relatively ideal. This research enables designers to participate in the process of machine learning generative design to control the generation results.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ecaade2022_158
id	ecaade2022_158
authors	Zhao, Xingjian, Wang, Tsung-Hsien and Peng, Chengzhi
year	2022
title	Automatic Room Type Classification using Machine Learning for Two-Dimensional Residential Building Plans
doi	https://doi.org/10.52842/conf.ecaade.2022.2.593
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. 593–600
summary	Building plan semantic retrieval is of interest in every stage of construction and facility management processes. A conceptual design model with a space layout can be used for the early building evaluation, such as functional spatial validation, circulation and security checking, cost estimation, and preliminary energy consumption simulation. With the development of information technology, existing machine learning methods applied to semantic segmentation of building plan images have successfully identified building elements such as doors, windows, and walls. However, for the higher level of room type/function recognition, the prediction accuracy is low when building plans do not contain sufficient details such as furniture. In this paper, we present a workflow and a predictive model for residential room type classification. Given a building plan image, the building elements are first identified, followed by room feature extraction by connectivity and morphological characterization using a rule-based algorithm. The Multi-Layer Perceptron (MLP) is trained with the feature set and then predicts the room type of test samples. We collected 1,586 residential room samples from 165 building layout plans and categorized rooms into nine types. Finally, our current model can achieve a classification accuracy of 0.82.
keywords	Floor Plan Semantic Retrieval, Room Type Classification, Machine Learning
series	eCAADe
email
last changed	2024/04/22 07:10

For more results click below: