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_324
id	ecaade2022_324
authors	Lin, Yu-Ting and Hsu, Pei-Hsien
year	2022
title	Dynamic Inflatable Structures and Digital Fabrication Process
doi	https://doi.org/10.52842/conf.ecaade.2022.1.311
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. 311–320
summary	Inflatable structures made of flat film materials have an advantage of low cost, lightweight and rapid deployment, but the variation of their forms is relatively limited, and it is a challenge to produce pneumatic deformations. This paper proposes a designing and manufacturing process of inflatable structures which are made of flat film materials and are able to perform dynamic movements. The process includes steps in which a target 3D surface is produced through programmed 2D paths heat-sealed on flat films of different thickness, leading to a structure composed of air chambers. A parametric modelling procedure and associated principles are developed for the relationship between the forms of a flat-film-based inflatable structure and the heat sealing patterns on the film. A system of double-layer air chambers was designed to control the direction of bending movements. In addition, the form variation of a designed inflatable structure can be achieved by a parametric design process described in this paper.
keywords	Pneumatic Structural System, Inflatable Structure, Digital Fabrication, Design Tool, Kinetic Structure
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2024_101
id	ecaade2024_101
authors	Yu, Jiaqi; Guo, Kening; Bai, Zishen; Wen, Zitong
year	2024
title	Application of Artificial Neural Network for Predicting U-Values of Building Envelopes in Temperate Zones
doi	https://doi.org/10.52842/conf.ecaade.2024.1.585
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 1, pp. 585–592
summary	Due to the global energy deficit, building energy consumption has become a significant issue in recent years. Many researchers have focused on building energy consumption simulations to manage energy consumption accurately and provide a comfortable indoor environment for occupants. In building energy simulations, accurate input of building parameters is essential. As important thermal parameters, the thermal transmittance (U-value) of building envelopes can affect building operational energy consumption. In most building energy simulation studies, the U-value was set to the theoretical U-value which was a fixed value. However, the U-value constantly varies due to several environmental impacts, especially fluctuating air temperature and relative humidity (T/RH). Thus, the U-values are dynamic in actual situations, and inputting dynamic U-values into building energy simulations can reduce the gap between the simulation and the actual situation. In this study, the dynamic U-values of conventional cavity envelopes in temperate zones were predicted by an artificial neural network (ANN) model. Firstly, the in-situ dynamic U-value measurement was conducted in Sheffield, the UK, from summer to winter in 2022. The heat flow meter method was applied, and the tested envelope was a conventional cavity envelope widely used in the UK. The indoor and outdoor T/RH were measured and recorded as well. Then, the measured data were applied to train the optimal ANN model. The input parameters included the indoor and outdoor T/RH, and the output parameter was the dynamic U-value. Finally, the prediction results obtained by the optimal ANN model were closely correlated with the measured dynamic U-value. This quantitative study of dynamic U-values examined the relationship between dynamic U-values of conventional cavity envelopes and environmental factors, which can provide reliable information for improving the inputting patterns of building parameters and the accuracy of the building energy simulation.
keywords	Artificial Neural Network Model, In-situ U-value Measurement, Dynamic U-value Prediction, Conventional Cavity Envelopes
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2022_122
id	ecaade2022_122
authors	Kinoshita, Airi, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2022
title	Enhanced Tracking Method with Object Detection for Mixed Reality in Outdoor Large Space
doi	https://doi.org/10.52842/conf.ecaade.2022.2.457
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. 457–466
summary	Mixed-reality landscape simulation is one of the visual methods used in landscape design studies. A markerless tracking method using image processing has been proposed for properly aligning the real and virtual worlds involved with landscape simulations in large spaces. However, this method is challenging because tracking breaks down if a dynamic object is encountered during the mixed-reality execution. In this study, we integrated deep-learning object detection with natural feature-based tracking, which tracks manually defined feature points (tracking reference points), with the aim of reducing the impact of moving objects such as people and cars on mixed-reality tracking. The prototype system was implemented and tracking was performed on pre-recorded video taken outdoors. Performance was verified in terms of the number of errors associated with tracking the reference points and the accuracy of the mixed-reality display results (camera pose estimation results). Compared to the conventional system, our system was able to reduce the influence of moving objects that cause errors when tracking reference points. The accuracy of the camera pose estimation results was also verified to be improved. This research will contribute to developing mixed-reality simulation systems for large-scale spaces that are accessible to everyone, including users in the architectural field.
keywords	Landscape Visualization, Mixed Reality, Object Detection, Tracking, Deep Learning
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ascaad2022_022
id	ascaad2022_022
authors	Marey, Ahmed; Goubran, Sherif
year	2022
title	Low-cost Portable Wireless Electroencephalography to Detect Emotional Responses to Visual Cues: Validation and Potential Applications
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. 139-154
summary	This paper validates the using a low-cost EEG headset – Emotiv Insight 2.0 – for detecting emotional responses to visual stimuli. The researchers detected, based on brainwave activity, the viewer’s emotional states in reference to a series of visuals and mapped them on valance and arousal axes. Valence in this research is defined as the viewer’s positive or negative state, and arousal is defined as the intensity of the emotion or how calm or excited the viewer is. A set of thirty images – divided into two categories: Objects and Scenes – was collected from the Open Affective Standard Image Set (OASIS) and used as a reference for validation. We collected a total of 720 data points for six different emotional states: Engagement, Excitement, Focus, Interest, Relaxation, and Stress. To validate the emotional state score generated by the EEG headset, we created a regression model using those six parameters to estimate the valence and arousal level, and compare them to values reported by OASIS. The results show the significance of the Engagement parameter in predicting the valence level in the Objects category and the significance of the Excitement parameter in the Scenes category. With the emergence of personal EEG headsets, understanding the emotional reaction in different contexts will help in various fields such as urban design, digital art, and neuromarketing. In architecture, the findings can enable designers to generate more dynamic and responsive design solutions informed by users’ emotions.
series	ASCAAD
email
last changed	2024/02/16 13:24

_id	architectural_intelligence2022_10
id	architectural_intelligence2022_10
authors	Xiao Liu & Yupeng Wu
year	2022
title	A review of advanced architectural glazing technologies for solar energy conversion and intelligent daylighting control
doi	https://doi.org/https://doi.org/10.1007/s44223-022-00009-6
source	Architectural Intelligence Journal
summary	Efficient management of solar radiation through architectural glazing is a key strategy for achieving a comfortable indoor environment with minimum energy consumption. Conventional glazing consisting of a single or multiple glass pane(s) exhibits high visible light transmittance and solar heat gain coefficient, which can be a double-edged sword, i.e., it allows sufficient sunlight to enter the building interior space for passive heating and lighting; on the other hand, it can cause glare discomfort and large cooling energy consumption. Among the various advanced glazing technologies being developed, Building Integrated Photovoltaic (BIPV) glazing has a prominent position due to its ability to reduce cooling load and visual discomfort while simultaneously generating electricity from sunlight. Recent years have witnessed remarkable advances in low-concentration optics such as Dielectric based Compound Parabolic Concentrators (DiCPCs), with a growing interest in the development of Building Integrated Concentrating Photovoltaic (BICPV) glazing to improve light harvesting and electric power output. One of the challenges faced by traditional BIPV glazing systems is the lack of dynamic control over daylight and solar heat transmission to cope with variations in weather conditions and seasonal heating/cooling demands of buildings. A promising solution is to integrate an optically switchable smart material into a BIPV glazing system, which enables dynamic daylighting control in addition to solar power conversion. Thermotropic (TT) hydrogel materials such as poly(N-isopropylacrylamide) (PNIPAm) and Hydroxypropyl Cellulose (HPC) are potential candidates for hybrid BIPV smart glazing applications, due to their unique features such as high visible transparency (in the clear state), strong light-scattering capability (in the translucent state) and large solar energy modulation. This paper reviews various types of electricity-generating glazing technologies including BIPV glazing and BICPV glazing, as well as smart glazing technologies with a particular focus on TT hydrogel integrated glazing. The characteristics, benefits and limitations of hybrid BIPV smart glazing are also evaluated. Finally, the challenges and research opportunities in this emerging field are discussed.
series	Architectural Intelligence
email
last changed	2025/01/09 15:00

_id	ecaade2023_317
id	ecaade2023_317
authors	Zamani, Alireza, Mohseni, Alale and Bertug Çapunaman, Özgüç
year	2023
title	Reconfigurable Formwork System for Vision-Informed Conformal Robotic 3D Printing
doi	https://doi.org/10.52842/conf.ecaade.2023.1.387
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 387–396
summary	Robotic additive manufacturing has garnered significant research and development interest due to its transformative potential in architecture, engineering, and construction as a cost-effective, material-efficient, and energy-saving fabrication method. However, despite its potential, conventional approaches heavily depend on meticulously optimized work environments, as robotic arms possess limited information regarding their immediate surroundings (Bechthold, 2010; Bechthold & King, 2013). Furthermore, such approaches are often restricted to planar build surfaces and slicing algorithms due to computational and physical practicality, which consequently limits the feasibility of robotic solutions in scenarios involving complex geometries and materials. Building on previous work (Çapunaman et al., 2022), this research investigates conformal 3D printing of clay using a 6 degrees-of-freedom robot arm and a vision-based sensing framework on parametrically reconfigurable tensile hyperbolic paraboloid (hypar) formwork. In this paper, we present the implementation details of the formwork system, share findings from preliminary testing of the proposed workflow, and demonstrate application feasibility through a design exercise that aims to fabricate unique components for a poly-hypar surface structure. The formwork system also offers parametric control over generating complex, non-planar tensile surfaces to be printed on. Within the scope of this workflow, the vision-based sensing framework is employed to generate a digital twin informing iterative tuning of the formwork geometry and conformal toolpath planning on scanned geometries. Additionally, we utilized the augmented fabrication framework to observe and analyze deformations in the printed clay body that occurs during air drying. The proposed workflow, in conjunction with the vision-based sensing framework and the reconfigurable formwork, aims to minimize time and material waste in custom formwork fabrication and printing support materials for complex geometric panels and shell structures.
keywords	Robotic Fabrication, Conformal 3D Printing, Additive Manufacturing, Computer-Vision, Reconfigurable Formwork
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2022_84
id	sigradi2022_84
authors	Oliveira Wedekin, Gabriela; Favaretto Montenegro, Clara; Bertola Duarte, Rovenir
year	2022
title	An Experiment at the Smart Campus UEL: Guidelines for a Technological Tool of Architectural Heritage’s Visual Perception
source	Herrera, PC, Dreifuss-Serrano, C, Gómez, P, Arris-Calderon, LF, Critical Appropriations - Proceedings of the XXVI Conference of the Iberoamerican Society of Digital Graphics (SIGraDi 2022), Universidad Peruana de Ciencias Aplicadas, Lima, 7-11 November 2022 , pp. 1089–1100
summary	This research aims to think of guidelines, from a Smart Heritage perspective, for the development of an artifact that will aim to “boost” the visual perception of the architectural heritage. Thus, the Smart Campus at UEL works as the research environment, as a living lab to test the points of the Smart City. The research was designed in Design Science Research in six steps: (1) Problem Identification, (2) Suggestion, (3) Development, (4) Demonstration, (5) Evaluation, and (6) Communication. The results presented correspond to phases (1), (2) and structuring of (3). Step (2) had a focus group of four experts in the field of architectural heritage and sought a more realistic epistemological position, focusing on real problems and solutions about the visual perception of architectural heritage in visitation itineraries. Based on the experts' statements, a cross-check was made with the points raised in the Smart Heritage literature to then list the main guidelines for the artifact.
keywords	Smart Cities and Environments, Smart Heritage, Visual perception, Architectural Heritage, Smart Campus
series	SIGraDi
email
last changed	2023/05/16 16:57

_id	cdrf2022_314
id	cdrf2022_314
authors	Yuqian Li, Weiguo Xu, and Xingchen Liu
year	2022
title	Research on Architectural Generation Design of Specific Architect's Sketch Based on Image-To-Image Translation
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_28
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	Sketch is a way for architects to communicate with others. Architects record their own ideas through rapid drawing. However, sketches are abstract, vague, and even ambiguous. To this end, architects need to spend a lot of time, through modeling and other means, to present the architectural plan that can be understood by people. However, this method is time-consuming and laborious. Due to the development of deep learning technology, especially convolutional neural networks (CNN) and generative adversarial networks (GAN), they have shown great advantages in the field of image recognition and generation. With the help of these technologies, ambiguous architectural sketches can be directly transformed into architectural scheme drawings, and architects’ creative intentions can be continuously improved and developed, It will be very convenient and efficient. Therefore, based on the image-to-image translation, this paper realizes the mapping from architectural sketches to architectural scheme drawings with the help of CycleGAN. Through the analysis of the architectural generation design results of Frank Gehry's and Alberto Campo Baeza's architectural sketches, firstly, the feasibility of this method is verified. Secondly, it is found that this method can well complete the identification of sketch boundaries. In the generated scheme drawings, it can not only reflect the volume and lighting changes of the building, but also reflect the architect's creative intention and style to a large extent, The side reflects the cognitive ability of this method to architectural design.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ecaade2022_403
id	ecaade2022_403
authors	Çavuº, Özlem and Alaçam, Sema
year	2022
title	Precision Factors in Modelling of Relief Patterns on Thin Aluminum Plates - Learning from making process
doi	https://doi.org/10.52842/conf.ecaade.2022.1.111
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. 111–120
summary	Surface coordinates on thin metal sheets constantly change during the engraving, and the digital model is not truly compatible with the physical engraving process because of the ignorance of the relationship between the hand movements with the tooltip and material in digital fabrication. Hence, this research creates experiments to learn from the physicality of the making process for precision factors in modeling relief patterns on thin aluminum plates. It questions the identification and elimination of precision problems of material and behavior in the production process of relief with a robotic arm. It aims to determine the relationships among materials, tools, and geometry in robotic manufacturing. UArm Swift Pro as a tool performs the task concerning speed, the surface of the tooltip, material thickness, drawing, and engraving modes. Created 3D geometries on aluminum surfaces are compared according to the change in distance between initial and target points, curvature, and radius of the target geometry.
keywords	Engraving, Forming, Sheet Metals, Relief Patterns, Robotic Manufacturing
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_202
id	ecaade2022_202
authors	Acican, Oyku and Luyten, Laurens
year	2022
title	Experiential Learning of Structural Systems - Comparison of design-based and experiment-based pedagogies
doi	https://doi.org/10.52842/conf.ecaade.2022.2.535
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. 535–544
summary	This research aims to compare two experiential learning methods’ effectiveness for (1) a deeper understanding of structural behaviour, and (2) skills to design architectural forms that are structurally informed. A course was planned to investigate the effect of the type and order of the two teaching units: (1) guided experiments on a parametric design model, and (2) parametric design of a tower and custom experiments using Grasshopper and Karamba. Results indicate that the group that started with the experiments learned to ask the relevant questions by experimenting with the appropriate parameters that helped them to find the structural principles and apply them during their design phase. The group that started with the design were lost in the structural concepts and in identifying the meaningful parameters to test for. However, after the experiment was completed, this group could make a knowledge transfer. Acquisition of structures knowledge may require the experience of multiple situations while the application of this knowledge may involve selecting the relevant structural experience with the architectural form-finding process. In the future, a proposed experiential learning method will be compared with an instructive learning approach of structural systems for architecture students.
keywords	Structures Education, Experiential Learning, Parametric Structural Analysis, Comparative Pedagogy
series	eCAADe
email
last changed	2024/04/22 07:10

_id	caadria2022_47
id	caadria2022_47
authors	An, Yudi
year	2022
title	Impact of Covid-19 on Associations between Land Use and Bike-Sharing Usage
doi	https://doi.org/10.52842/conf.caadria.2022.1.605
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. 605-614
summary	Bike-sharing as a human-centred, zero-emission, sustainable, alternative, and easily accessible transport mode has been implemented globally and consistently contributing to communities and the environment by alleviating consumption of natural sources, traffic congestion, and air pollution, which is considered a solution for future cities. The appearance of Covid-19 significantly impacts public transportation modes, including the bike-sharing system. The intention of this study was to investigate the spatiotemporal impact of the Covid-19 pandemic on associations between urban factors and bike-sharing usage in Los Angeles, United States, by analysing a sizeable actual trip dataset and employing geographically weighted regression (GWR) models. GWR was conducted for examining the varying spatial association between bike infrastructure, public transport, and urban land use factors, and bike-sharing trip volume. The results indicated that bike-sharing usage significantly decreased during the pandemic and essential service as restaurant was found consistently and positively associated with bike-sharing use. GWR provided clear spatial patterns of bike usage based on urban land use and big user databases. The outcomes of this study could inspire policymakers and shared mobility operators to support these safe, sustainable transport alters (such as rebalancing bike stations), help city resilience, and shape a sustainable future of mobility in the post-Covid-19 era.
keywords	Bike-Sharing, Covid-19, Land Use, Geographically Weighted Regression, Big Data, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	cdrf2022_478
id	cdrf2022_478
authors	Andrea Macruz, Mirko Daneluzzo, and Hind Tawaku
year	2022
title	Performative Ornament: Enhancing Humidity and Light Levels for Plants in Multispecies Design
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_41
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	The paper shifts the design conversation from a human-centered design methodology to a posthuman design, considering human and nonhuman actors. It asks how designers can incorporate a multispecies approach to creating greater intelligence and performance projects. To illustrate this, we describe a project of “ornaments” for plants, culminating from a course in an academic setting. The project methodology starts with “Thing Ethnography” analyzing the movement of a water bottle inside a house and its interaction with different objects. The relationship between water and plant was chosen to be further developed, considering water as a material to increase environmental humidity for the plant and brightness through light reflectance and refraction. 3D printed biomimetic structures as supports for water droplets were designed according to their performance and placed in different arrangements around the plant itself. Humidity levels and illuminance of the structures were measured. Ultimately, this created a new approach for working with plants and mass customization. The paper discusses the resultant evidence-based design and environmental values.
series	cdrf
email
last changed	2024/05/29 14:03

_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	sigradi2022_54
id	sigradi2022_54
authors	Balci, Ozan; Alaçam, Sema
year	2022
title	Zone-sensitive RIZOBots in Action: Examining the Behavior of Mobile Robots In a Heterogeneous Environment
source	Herrera, PC, Dreifuss-Serrano, C, Gómez, P, Arris-Calderon, LF, Critical Appropriations - Proceedings of the XXVI Conference of the Iberoamerican Society of Digital Graphics (SIGraDi 2022), Universidad Peruana de Ciencias Aplicadas, Lima, 7-11 November 2022 , pp. 397–408
summary	This study proposes a framework for the use of mobile robots namely RIZOBots in form studies in the early phases of design. The proposed framework was tested in two experiments. An agent-based model was utilized for the movement of mobile robots, a drawing task was defined as the task. In particular, rule sets for agent-agent and agent-environment interaction were used. Light-sensitivity rules were utilized to achieve agent-environment interaction, apart from obstacle detection. This study focuses on the effects of two different zone-related states on the behavior of RIZOBot which is a configurable differential-drive wheeled robot developed by authors using off-the-shelf products and 3D printed body parts. Two zone types with very basic features are used to define environmental conditions. The traces left on the canvas, the irregularities in the movement of the robots, and the robot-environment interaction will be evaluated in the study. The results and analysis of the two selected experiments are presented and the potential of the proposed framework is discussed.
keywords	Robotics, Swarm robotics, Swarm behaviour, Mobile agents, Zone-sensitivity
series	SIGraDi
email
last changed	2023/05/16 16:56

_id	ecaade2022_102
id	ecaade2022_102
authors	Casalnuovo, Gianluca and Erioli, Alessio
year	2022
title	Deep Trails - Coupling of structural optimization and self-organization processes for the computational design of composite surface tectonics
doi	https://doi.org/10.52842/conf.ecaade.2022.2.085
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. 85–94
summary	This research explores the constructive and expressive capabilities of stigmergic-based creasing patterns integrating structural and ornamental conditions in fibre-composite surface tectonics, generated by the reciprocal influence of multi-agent systems and Non- Linear Time History (NLHT) dynamic structural simulation. Building upon precedents on the use of agent bodies and behavioural tectonics such as the work of Roland Snooks, our approach employs NLTH simulation for the dynamical assessment of the structural failure modes to provide information for agents behaviour and a comparative assessment of the bodies pattern contribution. Considering the obtained results, insights gained on the structural behaviour of multi-agent composite surface tectonics while attempting to explore its embedded architectural, morphological and expressive qualities are discussed.
keywords	Computational Design, Multi-Agent System, Ornament, Structural Optimization, Fibre-Composite Materials, Stigmergy, Non-Linear Time History
series	eCAADe
email
last changed	2024/04/22 07:10

_id	cdrf2022_253
id	cdrf2022_253
authors	Chuheng Tan and Ximing Zhong
year	2022
title	A Rapid Wind Velocity Prediction Method in Built Environment Based on CycleGAN Model
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_22
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	Although the wind microclimate and wind environment play important roles in urban prediction, the time-consuming and complicated setup and process of wind simulation are widely regarded as challenges. There are several methods to use deep learning (DL) models for wind speed prediction by labeling pairs of wind simulation dataset samples. However, many wind simulation experiments are needed to obtain paired datasets, which is still time-consuming and cumbersome. Compared with previous studies, we propose a method to train a DL model without labelling paired data, which is based on Cycle Generative Adversarial Network (cycleGAN). To verify our hypothesis, we evaluate the results and process of the pix2pix model (requires paired datasets) and cycleGAN (does not requires paired datasets), and explore the difference of results between these two DL models and professional CFD software. The result shows that cycleGAN can perform as well as pix2pix in accuracy, indicating that some random city plans image samples and random wind simulation samples can train surrogate models as accurate as labelled DL methods. Although the DL method has similar results to the professional CFD method, the details of the wind flow results still need improvement. This study can help designers and policymakers to make informed decisions to choose Dl methods for real-time wind speed prediction for early-stage design exploration.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ascaad2022_085
id	ascaad2022_085
authors	Cicek, Selen; Koc, Mustafa; Korukcu, Berfin
year	2022
title	Urban Map Generation in Artist's Style using Generative Adversarial Networks (GAN)
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. 264-282
summary	Artificial Intelligence is a field that is able to learn from existing data to synthesize new ones using deep learning methods. Using Artificial Neural Networks that process big datasets, complex tasks and challenges become easily resolved. As the zeitgeist suggests, it is possible to produce novel outcomes for future projections by applying various machine learning algorithms on the generated data sets. In that context, the focus of this research is exploring the reinterpretation of 21st century urban plans with familiar artist styles using different subtypes of deep-learning-based generative adversarial networks (GAN) algorithms. In order to explore the capabilities of urban map transformation with machine learning approaches, two different GAN algorithms which are cycleGAN and styleGAN have been applied on the two main data sets. First data set, the urban data set, contains 50 cities urban plans in .jpeg format collected according to the diversity of the urban morphologies. Whereas the second data set is composed of four well-known artist’s paintings, that belong to various artistic movements. As a result of training the same data sets with different GAN algorithms and epoch values were compared and evaluated. In this respect, the study not only investigates the reinterpretation of stylistic urban maps and shows the discoverability of new representation techniques, but also offers a comparison of the use of different image to image translation GAN algorithms.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	cdrf2022_3
id	cdrf2022_3
authors	Deli Liu and Keqi Wang
year	2022
title	Spatial Analysis of Villages in Jilin Province Based on Space Syntax and Machine Learning
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_1
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	The development of machine learning technology gives architects and urban planners a new tool that can be used for research and design. The topic of this paper is to analyze the rural space of Jilin Province with the machine learning algorithms and space syntax theory, and to obtain the inherent formation and development laws of rural spatial forms, which can be used as a reference and evaluation system for subsequent rural development, and also can emphasize the locality and continuity of rural development. First, based on geographic information data, researching the connection between the distribution of villages and geographic data at a macro level and to classify them. Then, from each category, selecting one township and use all villages in its area as samples for the more specific study. Spatial features of individual village are extracted based on space syntax theory, and representative spatial features which can as feature values for cluster analysis are selected through comparative analysis. Then classify villages from high-dimensional data and explore their type characteristics. Finally, we hope the result of this study can help provide useful theoretical references for rural construction and nature conservation in the future.
series	cdrf
email
last changed	2024/05/29 14:02

_id	caadria2022_129
id	caadria2022_129
authors	Fukuda, Tomohiro, Nagamachi, Shiho, Nakamura, Hoki, Yamauchi, Yuji, Ito, Nao and Shimizu, Shunta
year	2022
title	Web-Based Three-Dimensional Augmented Reality of Digital Heritage for Nighttime Experience
doi	https://doi.org/10.52842/conf.caadria.2022.1.737
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. 737-746
summary	Digital heritage is a sustainable medium that allows people to understand the historical shape and context of cities and architecture, leading to visions for the future. Opportunities for the public to experience life-size representations of digital heritage in three-dimensional augmented reality (3D-AR) at outdoor sites are still limited, especially at night. Therefore, the objective of this study is to develop a web-based 3D-AR method to digitally reconstruct a heritage site. A prototype system was developed using the five-storey pagoda of Tango Kokubunji Temple, which was built around 1330 AD and later destroyed, as a digital heritage reconstruction. An interactive initial positioning method was developed to display the five-storey pagoda on real historical foundation stones by tapping a crosshair button, under the condition that the artificial lighting is insufficient at night and the distance between the viewpoint and the 3D model of the pagoda is large. Combining the lighting effects of the real and virtual worlds at night was also demonstrated. We held an event where the general public could experience 3D-AR on their own mobile devices, and conducted a usability evaluation to verify the system.
keywords	digital heritage, digital restoration, augmented reality (AR), web system, lighting design, virtual and real worlds, SDG 4, SDG 8
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ijac202220106
id	ijac202220106
authors	Förster, Nick; Ivan Bratoev, Jakob Fellner, Gerhard Schubert, Frank Petzold
year	2022
title	Collaborating with the crowd
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 1, pp. 76–95
summary	Microscopic agent-based simulations promise the meaningful inclusion of crowd dynamics in planning processes. However, such complex urban issues depend on a multiplicity of criteria. Thus, an isolated model cannot represent the walk of pedestrians meaningfully in planning contexts. This paper reframes crowd simulation as collaborative experimentation and embeds it directly in the design process. Beyond the simulation algorithm, this perspective draws attention to user interactions, interfaces, and visualizations as crucial simulation elements. Through a prototype, we combine an agent-based pedestrian simulation with a hybrid physical–digital interface. Based on this configuration, we explore requirements of the early design stages and accordingly discuss concepts for interaction, simulation, and visualization. The prototype blends user inputs with intuitive design interactions, adapts the simulation process to qualitative and dynamic negotiations, and presents results immediately in the discussed context. Thus, it aligns crowd simulation with contingent collaborations and reveals its potential in the early design stages.
keywords	Urban design, architectural design, design decision support, pedestrian simulation, human–computer interaction, collaborative design, early design stages
series	journal
last changed	2024/04/17 14:29

For more results click below: