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 610

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

_id	ascaad2021_146
id	ascaad2021_146
authors	Aly, Zeyad; Aly Ibrahim, Sherif Abdelmohsen
year	2021
title	Augmenting Passive Actuation of Hygromorphic Skins in Desert Climates: Learning from Thorny Devil Lizard Skins
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 264-278
summary	The exploitation of latent properties of natural materials such as wood in the passive actuation of adaptive building skins is of growing interest due to their added value as a low-cost and low-energy approach. The control of wood response behavior is typically conducted via physical experiments and numerical simulations that explore the impact of hygroscopic design parameters. Desert climates however suffer from water scarcity and high temperatures. Complementary mechanisms are needed to provide sufficient sources of water for effective hygroscopic operation. This paper aims to exploit such mechanisms, with specific focus on thorny devil lizard skins whose microstructure surface properties allow for maximum humidity absorption. We put forward that this process enhances hygroscopic-based passive actuation systems and their adaptation to both humidity and temperature in desert climates. Specific parameters and rules are deduced based on the lizard skin properties. Physical experiments are conducted to observe different actuation mechanisms. These mechanisms are recorded, and texture and bending morphologies are modeled for adaptive skins using Grasshopper.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	caadria2021_052
id	caadria2021_052
authors	Yousif, Shermeen and Bolojan, Daniel
year	2021
title	Deep-Performance - Incorporating Deep Learning for Automating Building Performance Simulation in Generative Systems
doi	https://doi.org/10.52842/conf.caadria.2021.1.151
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 151-160
summary	In this study, we introduce a newly developed method called Deep-Performance, to enable automatic environmental performance simulation prediction without the need to perform simulations, by integrating deep learning strategies. The aim is to train neural networks on datasets with thousands of building design samples and their corresponding performance simulation. The trained model would offer performance prediction for design options emerging in generative protocols. The research is a work-in-progress within a broader project aimed at automating buildings environmental performance evaluations of daylight analysis and energy simulation, using deep learning (DL) models. This paper focuses on the implementation of a supervised DL method for automating the retrieval of daylight analysis metrics, targeting successful daylight design and higher building enclosure efficiency. We have further improved a Pix2Pix model trained on 5 different datasets, each containing 6000 paired images of architectural floor plans and their daylight simulation metrics. In the inference phase, the model was able to accurately predict the daylight simulation for unseen sets of floor plans. For validation, two quantitative assessment metrics were followed to assess the predicted daylight performance against the daylight performance simulation. Both assessment metrics showed high accuracy levels.
keywords	Deep Learning; Artificial Intelligence; Deep-Performance; Automating Building Performance Simulation; Generative Systems
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	sigradi2021_5
id	sigradi2021_5
authors	Ng, Provides, Fernandez, Alberto, Doria, David, Odaibat, Baha and Karastathi, Nikoletta
year	2021
title	AI In+form: Intelligence and Aggregation for Solar Designs in the Built Environment
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 203–215
summary	Designers are increasingly challenged by a constant change of context and the interaction of layers of data from a huge variety of sources, from natural-artificial to human-machine. This research aims at mapping the interrelations of energy problems, bio- and artificial intelligence, and human-machine interaction to reflect and rethink the future of solar design. This paper first discusses its theoretical approach that stands at the convergence of light-harvesting systems, their aggregation and intelligence. Afterwhich, this paper explores their translation into iterative processes between designer and artificial intelligences, which is defined as rule/agent-based and machine learning systems; in particular, the relationship between Cellular Automata, Genetic Algorithm, and Generative Adversarial Networks (GANs) is discussed. Finally, it introduces a design project - @R.E.Ar_ - showing the proposed combinatorial pipeline and some preliminary results.
keywords	artificial intelligence, bio-inspired, solar design, Aggregation, human-machine interaction
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	caadria2021_308
id	caadria2021_308
authors	Wang, Dasong and Snooks, Roland
year	2021
title	Intuitive Behavior - The Operation of Reinforcement Learning in Generative Design Processes
doi	https://doi.org/10.52842/conf.caadria.2021.1.101
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 101-110
summary	The paper posits a novel approach for augmenting existing generative design processes to embed a greater level of design intention and create more sophisticated generative methodologies. The research presented in the paper is part of a speculative research project, Artificial Agency, that explores the operation of Machine Learning (ML) in generative design and robotic fabrication processes. By framing the inherent limitation of contemporary generative design approaches, the paper speculates on a heuristic approach that hybridizes a Reinforcement Learning based top-down evolutionary approach with bottom-up emergent generative processes. This approach is developed through a design experiment that establishes a topological field with intuitive global awareness of pavilion-scale design criteria. Theoretical strategies and technical details are demonstrated in the design experiment in regard to the translation of ML definitions within a generative design context as well as the encoding of design intentions. Critical reflections are offered in regard to the impacts, characteristics, and challenges towards the further development of the approach. The paper attempts to broaden the range and impact of Artificial Intelligence applications in the architectural discipline.
keywords	Machine Learning; Generative Design Process; Multi-Agent Systems; Reinforcement Learning
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	acadia21_470
id	acadia21_470
authors	£ochnicki, Grzegorz; Kalousdian, Nicolas Kubail; Leder, Samuel; Maierhofer, Mathias; Wood, Dylan; Menges, Achim
year	2021
title	Co-Designing Material-Robot Construction Behaviors
doi	https://doi.org/10.52842/conf.acadia.2021.470
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 470-479.
summary	This paper presents research on designing distributed, robotic construction systems in which robots are taught construction behaviors relative to the elastic bending of natural building materials. Using this behavioral relationship as a driver, the robotic system is developed to deal with the unpredictability of natural materials in construction and further to engage their dynamic characteristics as methods of locomotion and manipulation during the assembly of actively bent structures. Such an approach has the potential to unlock robotic building practice with rapid-renewable materials, whose short crop cycles and small carbon footprints make them particularly important inroads to sustainable construction. The research is conducted through an initial case study in which a mobile robot learns a control policy for elastically bending bamboo bundles into designed configurations using deep reinforcement learning algorithms. This policy is utilized in the process of designing relevant structures, and for the in-situ assembly of these designs. These concepts are further investigated through the co-design and physical prototyping of a mobile robot and the construction of bundled bamboo structures. This research demonstrates a shift from an approach of absolute control and predictability to behavior-based methods of assembly. With this, materials and processes that are often considered too labor-intensive or unpredictable can be reintroduced. This reintroduction leads to new insights in architectural design and construction, where design outcome is uniquely tied to the building material and its assembly logic. This highly material-driven approach sets the stage for developing an effective, sustainable, light-touch method of building using natural materials.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ijac202119101
id	ijac202119101
authors	Budig, Michael; Oliver Heckmann, Markus, Hudert, Amanda Qi Boon Ng, Zack Xuereb Conti, and Clement Jun Hao Lork
year	2021
title	Computational screening-LCA tools for early design stages
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 1, 6–22
summary	Life Cycle Assessment (LCA) has been widely adopted to identify the Global Warming Potential (GWP) in the construction industry and determine its high environmental impact through Greenhouse Gas (GHG) emissions, energy and resource consumptions. The consideration of LCA in the early stages of design is becoming increasingly important as a means to avoid costly changes at later stages of the project. However, typical LCA-based tools demand very detailed information about structural and material systems and thus become too laborious for designers in the conceptual stages, where such specifications are still loosely defined. In response, this paper presents a workflow for LCA-based evaluation where the selection of the construction system and material is kept open to compare the impacts of alternative design variants. We achieve this through a strict division into support and infill systems and a simplified visualization of a schematic floor layout using a shoebox approach, inspired from the energy modelling domain. The shoeboxes in our case are repeatable modules within a schematic floor plan layout, whose enclosures are defined by parametric 2D surfaces representing total ratios of permanent supports versus infill components. Thus, the assembly of modular surface enclosures simplifies the LCA evaluation process by avoiding the need to accurately specify the physical properties of each building component across the floor plan. The presented workflow facilitates the selection of alternative structural systems and materials for their comparison, and outputs the Global Warming Potential (GWP) in the form of an intuitive visualization output. The workflow for simplified evaluation is illustrated through a case study that compares the GWP for selected combinations of material choice and construction systems.
keywords	Computational life cycle assessment tool, embodied carbon, parametric design, construction systems, global warming potential
series	journal
email
last changed	2021/06/03 23:29

_id	caadria2021_160
id	caadria2021_160
authors	Ding, Jie and Xiang, Ke
year	2021
title	The influence of spatial geometric parameters of Glazed-atrium on office building energy consumption in the hot summer-warm winter region of China
doi	https://doi.org/10.52842/conf.caadria.2021.1.391
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 391-400
summary	To investigate the influence of the spatial geometric parameters of glazed-atrium on building energy consumption, this study established a prototypical office building model in the hot summer-warm winter region in China, and simulated the effect of energy consumption of six selected factors based on orthogonal experimental design (OED). Through the statistical analysis, the results showed that the floor height and the skylight-roof ratio were the most important parameters affecting the total energy consumption, with the contribution rates of 55.5% and 18.2%, followed by the section shape parameter and the plane orientation. In addition, the floor height and the section shape parameter were closely related to the cooling load and the lighting load, respectively, and both energy consumption could be reduced to a lower degree when the atrium inner interface window-wall ratio was 60%. Finally, the optimized parameter combination and energy-saving design strategies were proposed. This study provides architects with a simplified energy evaluation of atrium spatial geometric parameters in the early design stage, and it has an important guiding significance for the sustainable development of office buildings in the future.
keywords	Energy consumption; Spatial geometric factors; Glazed atrium; Office building; Hot summerâ€“warm winter region
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2021_448
id	caadria2021_448
authors	Koh, Seow Jin, Mok, Chiew Kai, Tan, Rachel and Chen, Edmund
year	2021
title	Optimising Harbour Typology in the Form Finding Process using Computational Design: A case study of a Greenfield port facility
doi	https://doi.org/10.52842/conf.caadria.2021.2.619
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 619-628
summary	The bulk of computational design strategies and research have been focused on issues related to architectural form and building systems. This is done by employing computational tools to optimise architectural forms, building performance and generally, improve quality of living. Many of these methodologies are based on the concept of form finding - varying geometric elements to generate and evaluate options to derive optimised solutions. However, beyond building designs, the concept of form finding can find its relevance in other design applications too such as engineering, landscape, and in our case, the design of ports, or more specifically harbour typology. In most building scenarios, the plot of land earmarked for development is typically selected beforehand, hence little exploration have been done to optimise land topology, when in fact the profile of land is the governing feature in most designs. For performance driven facilities like ports with high economic and political impact, there is value in optimizing topology to maximise throughput. Through the multi-disciplinary and collaborative effort of stakeholders and specialists, our project explored optimizing harbour topology via performance-based approach using computational design. The phenomenon, including impact and effects of trade-offs, are discussed and presented in this paper through a case study of a Greenfield port facility.
keywords	form finding; form optimisation; port masterplanning; harbour typology; computational design
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	caadria2021_305
id	caadria2021_305
authors	Keshavarzi, Mohammad, Afolabi, Oladapo, Caldas, Luisa, Yang, Allen Y. and Zakhor, Avideh
year	2021
title	GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
doi	https://doi.org/10.52842/conf.caadria.2021.1.091
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 91-100
summary	The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design and general 3D deep learning tasks.
keywords	Computational Geometry; Generative Modeling; 3D Manipulation; Texture Synthesis
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2021_131
id	ecaade2021_131
authors	Körner, Andreas
year	2021
title	Thermochromic Animation - Thermally-informed and colour-changing surface-configurations
doi	https://doi.org/10.52842/conf.ecaade.2021.2.453
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 453-462
summary	All factors of thermal comfort are invisible to humans and do not (yet) impact visual navigation in the built environment. Thermochromic materials change their colour relative to temperature. In architecture, their applications as responsive ornaments and as intelligent composite systems are discussed. Nonetheless, design research on their use together with computational design is scarce. This study investigates thermochromics concerning architectural surfaces. Design and material experiments were conducted to test the hypothesis that thermochromic animation can be configured to visualise invisible parameters of thermal comfort. Scale prototypes were fabricated from different materials and coated with thermochromics. They varied in layer number and sub-coatings. The colour change was observed with several instruments. Heat transfer simulations of digital doppelgangers accompanied the physical experiments. The results suggest that this method can be used to configure thermochromic animation. This can be implemented into a procedural design model for porous and multi-layered thermochromic surfaces in the future. In this, digital simulation and material-based design are combined in a method that advances the use of thermochromic materials in the context of digital architectural design.
keywords	thermochromics; fabrication; simulation; materials; colour
series	eCAADe
email
last changed	2022/06/07 07:52

_id	ascaad2021_118
id	ascaad2021_118
authors	Abdelmohsen, Sherif; Passaint Massoud
year	2021
title	Material-Based Parametric Form Finding: Learning Parametric Design through Computational Making
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 521-535
summary	Most approaches developed to teach parametric design principles in architectural education have focused on universal strategies that often result in the fixation of students towards perceiving parametric design as standard blindly followed scripts and procedures, thus defying the purpose of the bottom-up framework of form finding. Material-based computation has been recently introduced in computational design, where parameters and rules related to material properties are integrated into algorithmic thinking. In this paper, we discuss the process and outcomes of a computational design course focused on the interplay between the physical and the digital. Two phases of physical/digital exploration are discussed: (1) physical exploration with different materials and fabrication techniques to arrive at the design logic of a prototype panel module, and (2) deducing and developing an understanding of rules and parameters, based on the interplay of materials, and deriving strategies for pattern propagation of the panel on a façade composition using variation and complexity. The process and outcomes confirmed the initial hypothesis, where the more explicit the material exploration and identification of physical rules and relationships, the more nuanced the parametrically driven process, where students expressed a clear goal oriented generative logic, in addition to utilizing parametric design to inform form finding as a bottom-up approach.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	caadria2021_006
id	caadria2021_006
authors	Agirachman, Fauzan Alfi and Shinozaki, Michihiko
year	2021
title	VRDR - An Attempt to Evaluate BIM-based Design Studio Outcome Through Virtual Reality
doi	https://doi.org/10.52842/conf.caadria.2021.2.223
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 223-232
summary	During the COVID-19 pandemic situation, educational institutions were forced to conduct all academic activities in distance learning formats, including the architecture program. This act barred interaction between students and supervisors only through their computers screen. Therefore, in this study, we explored an opportunity to utilize virtual reality (VR) technology to help students understand and evaluate design outcomes from an architectural design studio course in a virtual environment setting. The design evaluation process is focused on building affordance and user accessibility aspect based on the design objectives that students must achieve. As a result, we developed a game-engine based VR system called VRDR for evaluating design studio outcomes modeled as Building Information Modeling (BIM) models.
keywords	virtual reality; building information modeling; building affordance; user accessibility; architectural education
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	ascaad2021_021
id	ascaad2021_021
authors	Albassel, Mohamed; Mustafa Waly
year	2021
title	Applying Machine Learning to Enhance the Implementation of Egyptian Fire and Life Safety Code in Mega Projects
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 7-22
summary	Machine Learning has become a significant research area in architecture; it can be used to retrieve valuable information for available data used to predict future instances. the purpose of this research was to develop an automated workflow to enhance the implementation of The Egyptian fire & life safety (FLS) code in mega projects and reduce the time wasted on the traditional process of rooms’ uses, occupant load, and egress capacity calculations to increase productivity by applying Supervised Machine Learning based on classification techniques through data mining and building datasets from previous projects, and explore the methods of preparation and analyzing data (text cleanup- tokenization- filtering- stemming-labeling). Then, provide an algorithm for classification rules using C# and python in integration with BIM tools such as Revit-Dynamo to calculate cumulative occupant load based on factors which are mentioned in the Egyptian FLS code, determine classification and uses of rooms to validate all data related to FLS. Moreover, calculating the egress capacity of means of egress for not only exit doors but also exit stairs. In addition, the research is to identify a clear understanding about ML and BIM through project case studies and how to build a model with the needed accuracy.
series	ASCAAD
email
last changed	2021/08/09 13:11

_id	ecaade2021_230
id	ecaade2021_230
authors	De Luca, Francesco, Sepúlveda, Abel and Varjas, Toivo
year	2021
title	Static Shading Optimization for Glare Control and Daylight
doi	https://doi.org/10.52842/conf.ecaade.2021.2.419
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 419-428
summary	Daylight and solar access influence positively building occupants' wellbeing and students' learning performance. However, an excess of sunlight can harm the visual comfort of occupants through disturbing glare effects. This study investigated, through multi-objective optimization, the potential of static shading devices to reduce glare and to guarantee daylight provision in a university building. The results showed that the reduction of disturbing glare was up to more than twice the reduced daylight, which nevertheless, was provided in adequate levels. View out and energy performance were also analyzed. Detailed results of optimal shading types and classrooms layout indications are presented.
keywords	Daylight; Visual comfort; Shading; Multi-objective optimization
series	eCAADe
email
last changed	2022/06/07 07:55

_id	caadria2021_086
id	caadria2021_086
authors	Eisenstadt, Viktor, Arora, Hardik, Ziegler, Christoph, Bielski, Jessica, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Exploring optimal ways to represent topological and spatial features of building designs in deep learning methods and applications for architecture
doi	https://doi.org/10.52842/conf.caadria.2021.1.191
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 191-200
summary	The main aim of this research is to harness deep learning techniques to support architectural design problems in early design phases, for example, to enable auto-completion of unfinished designs. For this purpose, we investigate the possibilities offered by established deep learning libraries such as TensorFlow. In this paper, we address a core challenge that arises, namely the transformation of semantic building information into a tensor format that can be processed by the libraries. Specifically, we address the representation of information about room types of a building and type of connection between the respective rooms. We develop and discuss five formats. Results of an initial evaluation based on a classification task show that all formats are suitable for training deep learning networks. However, a clear winner could be determined as well, for which a maximum value of 98% for validation accuracy could be achieved.
keywords	deep learning; spatial configuration; data representation; semantic building fingerprint
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	ecaade2021_254
id	ecaade2021_254
authors	Eisenstadt, Viktor, Arora, Hardik, Ziegler, Christoph, Bielski, Jessica, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Comparative Evaluation of Tensor-based Data Representations for Deep Learning Methods in Architecture
doi	https://doi.org/10.52842/conf.ecaade.2021.1.045
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 45-54
summary	This paper presents an extended evaluation of tensor-based representations of graph-based architectural room configurations. This experiment is a continuation of examination of recognition of semantic architectural features by contemporary standard deep learning methods. The main aim of this evaluation is to investigate how the deep learning models trained using the relation tensors as data representation means perform on data not available in the training dataset. Using a straightforward classification task, stepwise modifications of the original training dataset and manually created spatial configurations were fed into the models to measure their prediction quality. We hypothesized that the modifications that influence the class label will not decrease this quality, however, this was not confirmed and most likely the latent non-class defining features make up the class for the model. Under specific circumstances, the prediction quality still remained high for the winning relation tensor type.
keywords	Deep Learning; Spatial Configuration; Semantic Building Fingerprint
series	eCAADe
email
last changed	2022/06/07 07:55

_id	ascaad2021_058
id	ascaad2021_058
authors	ElGewely, Maha; Wafaa Nadim, Mostafa Talaat, Ahmad El Kassed,Mohamed Yehia, Slim Abdennadher
year	2021
title	Immersive VR Environment for Construction Detailing Education: BIM Approach
source	Abdelmohsen, S, El-Khouly, T, Mallasi, Z and Bennadji, A (eds.), Architecture in the Age of Disruptive Technologies: Transformations and Challenges [9th ASCAAD Conference Proceedings ISBN 978-1-907349-20-1] Cairo (Egypt) [Virtual Conference] 2-4 March 2021, pp. 114-128
summary	According to literature in education, adults learn best when learning is active, self-directed, problem-based, and relevant to their needs. In Building Construction Education, construction site visits provide students with real-life practical experience which are considered an extension for classroom. Nevertheless, it is challenging to integrate construction site visits regularly during the academic semester with respect to the class specific needs. Virtual Reality as an interactive immersive technology may facilitate virtual construction site that meets the learning needs where students can explore and build in a real scale environment. The proposed VR environment is an HMD VR platform for construction detailing that provides experiential learning in a zero-risk environment. It builds on integrating VR technology as a medium and Building Information Modeling (BIM) as a repository of information. This work discusses the proposed environment curricular unit prototype design, implementation, and validation. System usability and immersion are assessed both qualitatively and quantitatively. After considering the feedback, The VR environment prototype is then validated on the level of learning outcomes, providing the evidence that it would enhance students’ engagement, motivation and achievement accordingly.
series	ASCAAD
email
last changed	2021/08/09 13:13

_id	caadria2021_118
id	caadria2021_118
authors	Huang, Chien-hua
year	2021
title	Reinforcement Learning for Architectural Design-Build - Opportunity of Machine Learning in a Material-informed Circular Design Strategy
doi	https://doi.org/10.52842/conf.caadria.2021.1.171
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 171-180
summary	This paper discusses the potentials of reinforcement learning in game engine for design, implementation, and construction of architecture. It inaugurates a new design tool that promotes a material-informed design-build workflow for architectural design and construction industries that achieves a comprehensive circular economy. As a proof of concept, it uses the project Reform Standard, a machine-learning-based searching system that designs new shell structures composed of existing wasted materials, as a demonstration to discuss how reinforcement learning, machine vision and automated searching algorithm in the game engine can promote a material-aware design and converts wastes into construction materials. The demonstrator project sorts and transforms irregular chunks of wasted broken plastics into a new form. Instead of recycling those wastes in an energy-intensive process, the game engine is capable of finding the intricacy and new machine-oriented aesthetics in those otherwise neglected wastes. Furthermore, future research directions such as robotic-aided construction are discussed by exposing the potentials and problems in the demonstrated project. Finally, the future circular strategy is discussed beyond the demonstrated tests and local uses. The standardization of material, legislation and material lifecycle needs to be comprehensively considered and designed by architects and designers during conceptual design phase.
keywords	Reinforcement Learning; ML-Agents; Unity3D; circular design; geometric analysis
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	sigradi2021_200
id	sigradi2021_200
authors	Karabagli, Kaan, Koc, Mustafa, Basu, Prithwish and As, Imdat
year	2021
title	A Machine Learning Approach to Translate Graph Representations into Conceptual Massing Models
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 191–202
summary	Machine learning (ML) has popular applications in domains involving image, video, text and voice. However, in architecture, image-based ML systems face challenges capturing the complexity of three-dimensional space. In this paper, we leverage a graph-based ML system that can capture the inherent topology of architectural conceptual designs and identify high-performing latent patterns within such designs. In particular, our goal is to translate architectural graph data into three-dimensional massing models. We are building on our prior ML work, where we, a. discovered latent topological features, b. composed building blocks into new designs, c. evaluated their feasibility, and d. explored Generative Adversarial (Neural) Networks (GAN)-generated design variations. We trained the ML system with architectural design data that we gathered from an online architectural design competition platform, translated them into machine-readable graph representations, and identified their essential subgraphs to develop novel compositions. In this paper, we explore how these novel designs (outputted in graph form), can be translated into three-dimensional architectural form. We present an ML approach to turn graph representations into functional volumetric massing models. The ultimate goal of the study is to develop an end-to-end pipeline to generate architectural design - from a graph representation to a fully developed conceptual proxy of a designed product. The research question is promising in automating conceptual design, and we believe the outcome can be relevant to other design disciplines as well.
keywords	Architectural design, machine learning, conceptual design, deep learning, artificial intelligence
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	ecaade2021_252
id	ecaade2021_252
authors	Kotov, Anatolii and Vukorep, Ilija
year	2021
title	Gridworld Architecture Testbed
doi	https://doi.org/10.52842/conf.ecaade.2021.1.037
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 37-44
summary	Over centuries architects have developed frameworks of representation of the built surroundings in diverse types of drawings or models. With the rise of digital techniques, virtual models slowly replace these representation techniques but are still far from replicating the real world's ambiguity and complexity. This paper wants to address the representational problems of architecture combined with architecture-related AI systems and missing standardized tests for such systems. For this, we suggest a standardized computational testbed that can serve for developing, testing and benchmarking design solutions for abstracted architectural problems with various AI approaches in a game-like environment.Furthermore, this paper will discuss architectural problems' subdivision into atomic subtasks solvable by specific AI systems. Ideally, there is a waste number of possible architectural subtasks that can be applied. The paper presents some examples of possible architectural game strategies that abstractly deal with concepts of walls and borders, zones and connections. Although this paper mentions different Reinforcement Learning techniques, it is not focusing on fine-tuning the AI algorithms. It aims to help achieve automation of specific design workflow phases, then in the longer term to optimize and propose alternative design solutions and improve the architectural community's overall work.
keywords	Gridworld Testbed; AI Aided Architecture; Benchmarking AI Algorithms
series	eCAADe
email
last changed	2022/06/07 07:51

For more results click below: