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 14290

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

_id	ijac202220206
id	ijac202220206
authors	Khalil, Randa; Ahmed El-Kordy; Hesham Sobh
year	2022
title	A review for using swarm intelligence in architectural engineering
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 2, pp. 254–276
summary	Swarm intelligence algorithms are natural-inspired computational methods that mimic the social interactionbetween creatures to solve certain problems. Swarmative computational architecture (SCA) is a novelnomenclature proposed by the authors to present the use of various swarm algorithms in solving architectural problems. It includes three main aspects: form generation/adaptation, performance evaluation, andoptimization. This study provides a systematic review and comparative analysis for the major publicationswithin the review scope. The correspondence between dynamic subjects and the objective functions for theoptimization process is presented. Particularly, dynamic subjects such as building formation parameters andobjective functions such as occupant comfort and energy consumption. The main results and criteria arecategorized into the design approach, case study, form generation/adaptation, and performance evaluation/optimization. Finally, this review presents the current trends and highlights the gaps in the use of swarmalgorithms to solve architectural engineering problems
keywords	Swarm intelligence, evolutionary algorithm, performative computational architecture, architectural design,building design, computational optimization
series	journal
last changed	2024/04/17 14:29

_id	acadia20_506
id	acadia20_506
authors	Khalilbeigi Khameneh, Arman; Mottaghi, Esmaeil; Ghazvinian, Ali; Kalantari, Saeede
year	2020
title	Con-Create
doi	https://doi.org/10.52842/conf.acadia.2020.1.506
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. 506-515.
summary	Net structures, because of their minimal material waste and intuitive aesthetics, are gaining more interest recently. There are various efforts to redesign the tensile- and compression-only structures, as the computational tools and novel materials have broadened the scope of geometries possible to construct. However, the fabrication process of these structures faces different challenges, especially for mass construction. Some of these challenges are related to the technology and equipment utilized for materializing these complicated forms and geometries. Working with concrete as a quickly forming material for these irregular forms seems promising. Nevertheless, using this material has difficulties, including the preparation of formworks and joints, material reinforcement, structural behavior in the fresh state, and the assembly procedure. This paper introduces a method based on computational design and geometrical solutions to address some of these challenges. The goal is to shift the complexity of construction from the high-tech equipment used in the fabrication stage to integrating design and fabrication through a hierarchical system made entirely by affordable 2D CNC laser cutters. The stages of developing the method and the process of designing and building an architectural size proof-of-concept prototype by the proposed method are discussed. The efficiency of the method has been shown by comparing the designed prototype with the Con-Create Pavilion.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2016_068
id	ecaade2016_068
authors	Khalili-Araghi, Salman and Kolarevic, Branko
year	2016
title	Captivity or Flexibility: Complexities in a Dimensional Customization System
doi	https://doi.org/10.52842/conf.ecaade.2016.2.633
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 2, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 633-642
summary	Houses are essentially one-of-a-kind products that should reflect individualized differences of inhabitants who live in them. Homebuyers and homebuilders alike are thus captivated by the difficulties of housing customization. Achieving customer satisfaction depends on the flexibility of customized solutions, though the challenge of flexibility lies in the complexity of design validation. Constraints may be seen as design limitations, but they could provide for the efficiency of design validation. This paper addresses the complexities in the adoption of mass customization in the housing industry, and presents a dimensional customization system which would effectively use building information modeling (BIM) software, parametric design, and automatic verification of dimensional constraints to merge customization and validation.
wos	WOS:000402064400064
keywords	Mass Customization; Housing Industry; Building Information Modeling; Parametric Modeling; Automatic Constraint Satisfaction
series	eCAADe
email
last changed	2022/06/07 07:52

_id	ecaade2016_223
id	ecaade2016_223
authors	Khallaf, Mohamed and Jupp, Julie
year	2016
title	Designing for Urban Microclimates: Towards A Generative Performance-based Approach to Wind Flow Optimization
doi	https://doi.org/10.52842/conf.ecaade.2016.2.095
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 2, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 95-106
summary	This paper presents the foundations of a multidisciplinary design optimisation method that addresses the problem of competing wind flow profiles within urban microclimates. The simultaneous integration of architectural and urban design parameters and their aerodynamic constraints are investigated. Differences in the height of tall buildings, which define the urban canopy layer are accounted for. The formulation that supports the simulation of aerodynamic forces at the architectural and urban scales includes multidisciplinary parameter specification of 2D and 3D building geometry, spatial morphology, spatial topology, wind flow settings, and wind flow compliance. The MDO framework and its development are discussed relative to their generative performance-based capacity and innovative approach to multidisciplinary wind flow optimization
wos	WOS:000402064400009
keywords	Urban microclimate; Multidisciplinary design optimisation; Generative performance-based design; Systems level perspective
series	eCAADe
email
last changed	2022/06/07 07:52

_id	ascaad2023_105
id	ascaad2023_105
authors	Khamis, Noha; El Harairy, Yosra
year	2023
title	Employing Extended Reality (XR) to Expanding Narratives of Place-Making, Spatial Presence and Immersive Experience
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 963-974.
summary	Extended Reality XR, which encompasses various forms of virtual reality VR and augmented reality AR, has emerged as a powerful experimental tool in design and environmental psychology research due to its ability to produce comprehensive and immersive experiences for users through narratives. A strong sensation of spatial presence, which may be viewed as a subjective sense of space cognition and its surroundings, is one sign of a good XR experience. Despite the fact that XR research has shed light on numerous elements that may affect presence and place-making in XR environments, there is still much to learn about the varied phenomenology of narrative possibilities that ensure a successful immersion experience. The paper focuses on extended reality and how it influences how we create spaces, feel present in our surroundings, and have an immersive experience. In this paper, the concepts of place-making and spatial presence were examined in relation to how people might create a consistent sense of reality during both real-world and virtual experiences. The purpose of this study is to evaluate the ideas of place-making, presence, and immersion experience as they have been developed in XR research while also addressing variables that could affect expanding narratives. The study covers major elements of the "place" literature, connects them to the idea of presence, and then exhibits their use in the context of extended reality. It also discusses the phenomenological properties of presence in human consciousness. A user study conducted through a designed immersive experience as a simulation to some spaces of the Grand Egyptian Museum. Samples of users’ responses were collected through a survey addressing their perceptions of the virtual visit. The study showed that place-making and spatial presence in extended reality work as a link between real-world locations and virtual attributes. When moving from the real world to the virtual one, boundaries become more fluid, themes can be developed, and virtual spaces mimic the real spaces. The study outline proposals for further work and lays out some ideas for future research.
series	ASCAAD
email
last changed	2024/02/13 14:41

_id	caadria2009_027
id	caadria2009_027
authors	Khampanya, Rom ; Surapong Lertsithichai
year	2009
title	Tangidesk: A Tangible Interface Prototype for Urban Design and Planning
doi	https://doi.org/10.52842/conf.caadria.2009.705
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 705-714
summary	This paper describes the design and implementation of TangiDESK, a tangible interface prototype to assist in the design and planning of urban design projects. The prototype derives from the need for an intuitive user interface similar to a designer’s or architect’s CAD system but also simple enough for non-designers like city planners and developers who are not accustomed to CAD interfaces to use and understand easily. Users can manipulate the objects or modify its relationship with other elements in the site while making preliminary design decisions together in a single environment. With TangiDESK, designers and planners can collaborate and make informative decisions more effectively and accurately in early stages of an urban design project.
keywords	Tangible user interface; urban design and planning; computeraided design; collaborative design; project feasibility
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	caadria2024_535
id	caadria2024_535
authors	Khan, Md Zishaan, Erhan, Halil and Abuzuraiq, Ahmed M.
year	2024
title	A Critical Review of Data Democratisation and its Adoption in Designing Built-Environments
doi	https://doi.org/10.52842/conf.caadria.2024.2.181
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 181–190
summary	Data democratisation aims to empower the stakeholders in a problem domain and engage them in participating in decision-making by providing access to all relevant data. Its application in multiple fields, such as information systems, healthcare, business, and policymaking, can guide us to develop a novel approach to design democratisation informed by data to enhance the stakeholders’ participation in creating built environments. In this paper, we identified the basic principles and attributes of data democratisation through a systematic literature review and existing tool analysis to identify potential system features supporting data democratisation. Both guided us in developing a conceptual framework for data-informed design democratisation. We propose a set of practical recommendations for interactive system development for this purpose. Our study aims to contribute to expanding the knowledge in the field of design-data democratisation and offers guidance for leveraging stakeholder engagement for design.
keywords	data democratisation, built environment design, design decision-making, urban design, architecture, public engagement.
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_399
id	ecaade2024_399
authors	Khan, Md Zishaan; Erhan, Halil; Yagmur Kilimci, Elif Sezen
year	2024
title	Data-Informed Design Democratization: Engaging design stakeholders for creating livable built environments
doi	https://doi.org/10.52842/conf.ecaade.2024.2.475
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 475–484
summary	Fostering an inclusive and democratic decision-making process is essential to developing liveable, socially acceptable, and environmentally conscious built environments. For informed decision-making in this process, stakeholders’ understanding of design data plays an important role, as do the other disciplines embracing data-informed discourses and cultures. However, more work is needed to develop novel platforms for supporting data-informed decision-making in built environment design. Public engagement and town hall meetings are common methods to engage the public. They are often restricted by time, space, and participation scope. The online tools for data democratization in various fields offer opportunities to promote a democratic discourse; although their purpose varies, their characteristics can guide the search for novel approaches adopting a new class of tools for building design. We propose a conceptual framework for evaluating and designing tools supporting data-informed [built environment] design democratization through inclusive discourses called Di-Dem. As a contribution, we demonstrated the application of the framework in evaluating ten platforms offered for similar purposes.
keywords	Data Democratization, Democratic Discourse in Built Environment Design, Data-informed Participation, Inclusive Data Visualization, Engaging Stakeholders
series	eCAADe
email
last changed	2024/11/17 22:05

_id	acadia07_262
id	acadia07_262
authors	Khan, Omar
year	2007
title	Mis(sed)information in Public Space
doi	https://doi.org/10.52842/conf.acadia.2007.262
source	Expanding Bodies: Art • Cities• Environment [Proceedings of the 27th Annual Conference of the Association for Computer Aided Design in Architecture / ISBN 978-0-9780978-6-8] Halifax (Nova Scotia) 1-7 October 2007, 262-267
summary	This paper looks at the question of freedom and control in relation to the design of interactive media architecture projects for public spaces. It speculates on how designers of responsive systems must negotiate the relationship between their designs, the users’ participation and the protocols of existing public spaces. Using Stafford Beer’s formulation for a “liberty machine” it reflects on strategies for under-specifying such systems, to make them more adaptable to change. Questions that it poses include: How open should a system be? What role should public participation play in its instantiation? Who should maintain it? Who or what should control its objectives?
series	ACADIA
email
last changed	2022/06/07 07:52

_id	acadia08_286
id	acadia08_286
authors	Khan, Omar
year	2008
title	Reconfigurable Molds as Architecture Machines
doi	https://doi.org/10.52842/conf.acadia.2008.286
source	Silicon + Skin: Biological Processes and Computation, [Proceedings of the 28th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) / ISBN 978-0-9789463-4-0] Minneapolis 16-19 October 2008, 286-291
summary	In The Architecture Machine (1970), Nicholas Negroponte postulates the development of design machines wherein the “design process, considered as evolutionary, can be presented to a machine, also considered as evolutionary, and a mutual training, resilience, and growth can be developed.” The book, dedicated to “the first machine that can appreciate the gesture,” argues for developing machines with human like qualities. This paper aims to develop an alternative trajectory to the “evolutionary” architecture machine, this time not towards anthropomorphism but responsiveness. The aim on one level is the same: to create machines that appreciate the gesture. However our approach is tied to more modest aims and means that bring current thinking on evolutionary processes and the forming of materials together. The reconfigurable mold (RCM) is an architecture machine that produces parts that can be combined to create more complex organizations. The molds are simple analog computers that employ various continuous scales like volume, weight and heat to develop their unique components. Parametric alterations are made possible by affecting these measures in the process of fabrication. An underlying material that is instrumental in the molds is rubber, whose variable elasticity provides unique possibilities for indexing the gesture that remains elusive for industrial processes.
keywords	Casting; Digital Fabrication; Generative; Material; Morphogenesis
series	ACADIA
last changed	2022/06/07 07:52

_id	cf2019_042
id	cf2019_042
authors	Khan, Sumbul; Bige Tuncer, Ramanathan Subramanian and Lucienne Blessing
year	2019
title	3D CAD modeling using gestures and speech: Investigating CAD legacy and non-legacy procedures
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, pp. 347-366
summary	3D CAD modeling using natural interaction techniques necessitates greater research into the modeling procedures employed by users. In a previously conducted experiment, we elicited speech and gestures input for 3D CAD modeling tasks for conceptual design. In this paper, we examine the 3D modeling procedures articulated by the participants, using gestures and speech, for creating basic 3D models of increasing complexity. We identified 3D modeling procedures and characterized them as CAD legacy and non-legacy procedures. Results show that (1) non-legacy procedures were employed by a considerable number of participants who had fair and high proficiency in CAD and (2) Non-legacy procedures with fewer steps were rated favorably by participants. Based on the results, we provide recommendations on key aspects of non-legacy procedures that need to be incorporated in CAD modeling programs to facilitate speech and gestural input.
keywords	Gestures, 3D CAD modeling, Human Computer Interaction, computer aided design, natural interaction
series	CAAD Futures
email
last changed	2019/07/29 14:15

_id	acadia17_318
id	acadia17_318
authors	Khan, Sumbul; Tunçer, Bige
year	2017
title	Intuitive and Effective Gestures for Conceptual Architectural Design: An Analysis Of User Elicited Hand Gestures For 3D CAD Modeling
doi	https://doi.org/10.52842/conf.acadia.2017.318
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 318- 323
summary	Gesture-based natural interfaces necessitate research into gestures that are intuitive for designers and effective for natural interaction. Intuitive knowledge is significant for conceptual design as it reduces time taken to complete tasks and improves usability of products. In a previously conducted experiment, we elicited gestures for 3D CAD modeling tasks for conceptual architectural design. In this study, we present a preliminary analysis of intuitiveness scores of gestures and evaluators’ ratings to analyze which gestures were more intuitive and effective for CAD manipulation tasks. Results show that gestures with high intuitive scores were not necessarily rated as effective by evaluators and that bimanual symmetric gestures consistently scored high for both intuitiveness and effectiveness. Based on our findings we give recommendations for the design of gesture-based CAD modeling systems for single and multiple users.
keywords	design methods; information processing; HCI; collaboration; art and technology
series	ACADIA
email
last changed	2022/06/07 07:52

_id	cf2011_p141
id	cf2011_p141
authors	Khan,Mohammad Ashraf; Dong Andy
year	2011
title	Using Geo-Located Augmented Reality for Community Evaluation
source	Computer Aided Architectural Design Futures 2011 [Proceedings of the 14th International Conference on Computer Aided Architectural Design Futures / ISBN 9782874561429] Liege (Belgium) 4-8 July 2011, pp. 701-720.
summary	Conventional practices of two-dimensional representation of three-dimensional objects remain an impediment to end-user engagement in participatory urban design. An alternative is to harness geo-located augmented reality (GAR) technology to embed life-sized virtual three-dimensional images at the actual site of proposed interventions. This format offers closest to real-life visualizations for end-users, enabling them to firstly comprehend and then express feelings concerning future proposals. This paper presents an iPhone web-app that capitalizes on the Layar browser’s GAR interface to tip the economies of scale in favor of intimately attached users of public space, rather than often remotely detached clients and their commissioned designers. Walk-around virtual images of public space designs can be viewed and commented via iPhones by the public. It further allows users to display their own ideas as alternatives, thus in effect serving as an instrument for advancement of CAAD-enabled participative environmental design in general and the idea of reclamation of authorship of public space in particular. This paper briefly describes the development of a prototype, including its preliminary evaluation, and then highlights a study to determine the 3D rendering performance parameters of GAR technology, as the core component of the idea. The paper concludes with a discussion of future implications.
keywords	Participative Environmental Design, Collaborative Architectural Design, CAAD, IPhone, End-User Engagement
series	CAAD Futures
email
last changed	2012/02/11 19:21

_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	caadria2022_286
id	caadria2022_286
authors	Khean, Nariddh, During, Serjoscha, Chronis, Angelos, Konig, Reinhard and Haeusler, Matthias Hank
year	2022
title	An Assessment of Tool Interoperability and its Effect on Technological Uptake for Urban Microclimate Prediction with Deep Learning Models
doi	https://doi.org/10.52842/conf.caadria.2022.1.273
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. 273-282
summary	The benefits of deep learning (DL) models often overshadow the high costs associated with training them. Especially when the intention of the resultant model is a more climate resilient built environment, overlooking these costs are borderline hypocritical. However, the DL models that model natural phenomena‚conventionally simulated through predictable mathematical modelling‚don't succumb to the costly pitfalls of retraining when a model's predictions diverge from reality over time. Thus, the focus of this research will be on the application of DL models in urban microclimate simulations based on computational fluid dynamics. When applied, predicting wind factors through DL, rather than arduously simulating, can offer orders of magnitude of improved computational speed and costs. However, despite the plethora of research conducted on the training of such models, there is comparatively little work done on deploying them. This research posits: to truly use DL for climate resilience, it is not enough to simply train models, but also to deploy them in an environment conducive of rapid uptake with minimal barrier to entry. Thus, this research develops a Grasshopper plugin that offers planners and architects the benefits gained from DL. The outcomes of this research will be a tangible tool that practitioners can immediately use, toward making effectual change.
keywords	Deep Learning, Technological Adoption, Fluid Dynamics, Urban Microclimate Simulation, Grasshopper, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2018_111
id	ecaade2018_111
authors	Khean, Nariddh, Fabbri, Alessandra and Haeusler, M. Hank
year	2018
title	Learning Machine Learning as an Architect, How to? - Presenting and evaluating a Grasshopper based platform to teach architecture students machine learning
doi	https://doi.org/10.52842/conf.ecaade.2018.1.095
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 1, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 95-102
summary	Machine learning algorithms have become widely embedded in many aspects of modern society. They have come to enhance systems, such as individualised marketing, social media services, and search engines. However, contrasting its growing ubiquity, the architectural industry has been comparatively resistant in its adoption; objectively one of the slowest industries to integrate with machine learning. Machine learning expertise can be separate from professionals in other fields; however, this separation can be a major hinderance in architecture, where interaction between the designer and the design facilitates the production of favourable outcomes. To bridge this knowledge gap, this research suggests that the solution lies with architectural education. Through the development of a novel educative framework, the research aims to teach architecture students how to implement machine learning. Exploration of student-centred pedagogical strategies was used to inform the conceptualisation of the educative module, which was subsequently implemented into an undergraduate computational design studio, and finally evaluated on its ability to effectively teach designers machine learning. The developed educative module represents a step towards greater technological adoption in the architecture industry.
keywords	Artificial Intelligence; Machine Learning; Neural Networks; Student-Centred Learning; Educative Framework
series	eCAADe
email
last changed	2022/06/07 07:52

_id	caadria2018_126
id	caadria2018_126
authors	Khean, Nariddh, Kim, Lucas, Martinez, Jorge, Doherty, Ben, Fabbri, Alessandra, Gardner, Nicole and Haeusler, M. Hank
year	2018
title	The Introspection of Deep Neural Networks - Towards Illuminating the Black Box - Training Architects Machine Learning via Grasshopper Definitions
doi	https://doi.org/10.52842/conf.caadria.2018.2.237
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 237-246
summary	Machine learning is yet to make a significant impact in the field of architecture and design. However, with the combination of artificial neural networks, a biologically inspired machine learning paradigm, and deep learning, a hierarchical subsystem of machine learning, the predictive capabilities of machine learning processes could prove a valuable tool for designers. Yet, the inherent knowledge gap between the fields of architecture and computer science has meant the complexity of machine learning, and thus its potential value and applications in the design of the built environment remain little understood. To bridge this knowledge gap, this paper describes the development of a learning tool directed at architects and designers to better understand the inner workings of machine learning. Within the parametric modelling environment of Grasshopper, this research develops a framework to express the mathematic and programmatic operations of neural networks in a visual scripting language. This offers a way to segment and parametrise each neural network operation into a basic expression. Unpacking the complexities of machine learning in an intermediary software environment such as Grasshopper intends to foster the broader adoption of artificial intelligence in architecture.
keywords	machine learning; neural network; action research; supervised learning; education
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	cf2019_032
id	cf2019_032
authors	Khean, Nariddh; Alessandra Fabbri, David Gerber and M. Hank Haeusler
year	2019
title	Examining Potential Socio-economic Factors that Aﬀect Machine Learning Research in the AEC Industry
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 254
summary	Machine learning (ML) has increasingly dominated discussions about the shape of mankind’s future, permeating almost all facets of our digital, and even physical, world. Yet, contrary to the relentless march of almost all other industries, the architecture, engineering and construction (AEC) industry have lagged behind in the uptake of ML for its own challenges. Through a systematic review of ML projects from a leading global engineering ﬁrm, this paper investigates social, political, economic, and cultural (SPEC) factors that have helped or hindered ML’s uptake. Further, the paper discusses how ML is perceived at various points in the economic hierarchy, how eﬀective forms of communication is vital in a highly-specialized workforce, and how ML’s unexpected eﬀectiveness have forced policy makers to reassess data governance and privacy; all the while considering what this means for the adoption of ML in the AEC industry. This investigation, its methodology, background research, systematic review, and its conclusion are presented.
keywords	Machine learning · Artiﬁcial intelligence · Research and development · Architecture, engineering, and construction industry · Social factors · Political factors · Economic factors · Cultural factors
series	CAAD Futures
type	normal paper
email
last changed	2019/07/29 14:17

_id	d460
authors	Khedro, Taha
year	1995
title	AgentCAD for Cooperative Design
source	Sixth International Conference on Computer-Aided Architectural Design Futures [ISBN 9971-62-423-0] Singapore, 24-26 September 1995, pp. 667-672
summary	AgentCAD is a network infrastructure of distributed CAD applications that facilitates the concurrent an cooperative interaction of several designers working together, possibly over several physical locations, on a design project. It provides a set of services and protocols that support the communications of distributed design information captured by CAD drawings, multiple design views, and design changes. It coordinates access to a common and multiple design models as well as the activities of designers based on captured knowledge of designers' tasks, capabilities, and interests, which characterize their behaviors. The idea of AgentCAD represents a departure from the usual way in which CAD applications are used as single-user tools, applied to one view of specific design problems. In describing the AgentCAD environment, we discuss the organization of AgentCAD, its communication model, and the cooperative interaction protocols for designers in the context of a design scenario.
keywords	Cooperative Design; Collaborative Design; Distributed Problem Solving; Communications; Coordination
series	CAAD Futures
last changed	1999/08/03 17:16

_id	68fb
authors	Khemlani, L., Timerman, A., Benne, B. and Kalay, Y.E.
year	1998
title	Intelligent representation for computer-aided building design
source	Automation in Construction 8 (1) (1998) pp. 49-71
summary	At the core of any computational system that can support design development, analysis, and evaluation is an “intelligent” building representation which should be able to represent all the different components that make up a building, along with the manner in which they come together. In other words, the representation must be informationally complete and semantically rich. The paper discusses these two criteria and briefly reviews other research efforts aimed at developing building representations for computer-aided design that attempt to meet them. Our solution to this problem is then presented. It is aimed primarily at the schematic design phase, the rationale for which is also stated. Taking the view that buildings are unique assemblies of discrete, mostly standardized components, our representation is clearly divided into two components: the Object Database (ODB) which stores detailed information about various building elements, and the Project Database (PDB) which holds information about how these elements are assembled to make up a particular building. An ODB may be shared by many building projects, while the PDB must necessarily be unique to each. The data schemas of both the PDB and the ODB are described in detail and their computational implementation, to the extent that it has been completed, is illustrated.
series	journal paper
last changed	2003/03/05 13:12

For more results click below: