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 652

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

_id	caadria2024_186
id	caadria2024_186
authors	Huang, Jingfei and Tu, Han
year	2024
title	Inconsistent Affective Reaction: Sentiment of Perception and Opinion in Urban Environments
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. 395–404
doi	https://doi.org/10.52842/conf.caadria.2024.2.395
summary	The ascension of social media platforms has transformed our understanding of urban environments, giving rise to nuanced variations in sentiment reaction embedded within human perception and opinion, and challenging existing multidimensional sentiment analysis approaches in urban studies. This study presents novel methodologies for identifying and elucidating sentiment inconsistency, constructing a dataset encompassing 140,750 Baidu and Tencent Street view images to measure perceptions, and 984,024 Weibo social media text posts to measure opinions. A reaction index is developed, integrating object detection and natural language processing techniques to classify sentiment in Beijing Second Ring for 2016 and 2022. Classified sentiment reaction is analysed and visualized using regression analysis, image segmentation, and word frequency based on land-use distribution to discern underlying factors. The perception affective reaction trend map reveals a shift toward more evenly distributed positive sentiment, while the opinion affective reaction trend map shows more extreme changes. Our mismatch map indicates significant disparities between the sentiments of human perception and opinion of urban areas over the years. Changes in sentiment reactions have significant relationships with elements such as dense buildings and pedestrian presence. Our inconsistent maps present perception and opinion sentiments before and after the pandemic and offer potential explanations and directions for environmental management, in formulating strategies for urban renewal.
keywords	Urban Sentiment, Affective Reaction, Social Media, Machine Learning, Urban Data, Image Segmentation.
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	cdrf2022_199
id	cdrf2022_199
authors	Jingming Li
year	2022
title	Using Text Understanding to Create Formatted Semantic Web from BIM
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_17
summary	The application of BIM in the building life cycle needs to be continuous. The information collected and accumulated in the early stages should flow to the subsequent phases. However, BIM applications currently focus on collision inspection, compliance inspection, and engineering calculation, few models can be successively used in the following stages. Remodeling is required in the operation and maintenance period, resulting in waste. Meanwhile, some of the information accumulated by BIM might be frequently used in the operation and maintenance stage, while some data are relatively rarely used. The semantic web can help manage building information at all stages. But the generation of a semantic web is mostly manually completed. It is necessary to standardize the repeated semantic description in the model and convert BIM into a standard semantic model for information indexing, reducing the resource consumption of model loading and optimizing the efficiency of the operation and maintenance system. When the existing research transforms from BIM to the semantic web, there will be a lack of information and descriptions of the ownership relationship between entities due to the limitation of formats. To realize the standard transformation from BIM to the semantic web, this work proposes a method of using Natural Language Processing (NLP) to understand the text and infer the relationship between entities according to the knowledge map. First, the entities are extracted from BIM, such as air conditioning unit, electric lamp, fan, etc., if the name of the extracted entity is irregular, the names are translated with the help of NLP and Ontology (such as brick or haystack) to obtain the standard definition. By comparing the complete knowledge graph (such as the knowledge graph of the air conditioning system), the relationships can be deduced, and then a standardized semantic model can be generated.
series	cdrf
email
last changed	2024/05/29 14:02

_id	ijac202321201
id	ijac202321201
authors	Steinfeld, Kyle
year	2023
title	Clever little tricks: A socio-technical history of text-to-image generative models
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 211–241
summary	The emergence of text-to-image generative models (e.g., Midjourney, DALL-E 2, Stable Diffusion) in the summer of 2022 impacted architectural visual culture suddenly, severely, and seemingly out of nowhere. To contextualize this phenomenon, this text offers a socio-technical history of text-to-image generative systems. Three moments in time, or “scenes,” are presented here: the first at the advent of AI in the middle of the last century; the second at the “reawakening” of a specific approach to machine learning at the turn of this century; the third that documents a rapid sequence of innovations, dubbed “clever little tricks,” that occurred across just 18 months. This final scene is the crux, and represents the first formal documentation of the recent history of a specific set of informal innovations. These innovations were produced by non-affiliated researchers and communities of creative contributors, and directly led to the technologies that so compellingly captured the architectural imagination in the summer of 2022. Across these scenes, we examine the technologies, application domains, infrastructures, social contexts, and practices that drive technical research and shape creative practice in this space.
keywords	Machine learning, text-to-image, socio-technical study, generative AI
series	journal
last changed	2024/04/17 14:30

_id	caadria2022_167
id	caadria2022_167
authors	Aman, Jayedi, Matisziw, Timothy C, Kim, Jong Bum and Luo, Dan
year	2022
title	Sensing the City: Leveraging Geotagged Social Media Posts and Street View Imagery to Model Urban Streetscapes Using Deep Neural Networks
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. 595-604
doi	https://doi.org/10.52842/conf.caadria.2022.1.595
summary	Understanding the relationships between individuals and the urban streetscape is an essential component of sustainable city planning. However, analysis of these relationships involves accounting for a complex mix of human behaviour, perception, as well as geospatial context. In this context, a comprehensive framework for predicting preferred streetscape characteristics utilizing deep learning and geospatial techniques is proposed. Geotagged social media posts and street view imagery are employed to account for individual sentiment and geospatial context. Natural Language Processing (NLP) and computer vision (CV) are then used to infer sentiment and model the visual environment within which individuals make posts to social media. An application of the developed framework is provided using Instagram posts and Google Street View imagery of the urban environment. A spatial analysis is conducted to assess the extent to which urban attributes correlate with the sentiment of social media postings. The results shed light on sustainable streetscape planning by focusing on the relationship between users and the built environment in a complex urban setting. Finally, limitations of the developed methodology as well as future directions are discussed.
keywords	Urban sustainability, data mining, pedestrian sentiments, transportation behavior, street level imagery, transformers, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ecaade2022_411
id	ecaade2022_411
authors	Cesar Rodrigues, Ricardo, Rubio Koga, Renan, Hitomi Hirota, Ercilia and Bertola Duarte, Rovenir
year	2022
title	Mapping Space Allocation with Artificial Intelligence - An approach towards mass customized housing units
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. 631–640
doi	https://doi.org/10.52842/conf.ecaade.2022.2.631
summary	Artificial Intelligence represents a substantial part of the available tools on architectural design, especially for Space Layout Planning (SLP). At the same time, the challenge of Mass Customization (MC) is to increase the product variety while maintaining a good cost-benefit ratio. Thus, this research aims to identify new, valid, and easily understandable data patterns through human-machine interaction in an attempt to deal with the challenges of MC during the early phases of SLP. The Design Science Research method was adopted to develop a digital artifact based on deep generative models and a reverse image search engine. The results indicate that the artifact can deliver a series of design alternatives and enhance the navigation process in the solution space, besides giving key insights on dataset design for further research.
keywords	Floor plans, Generative Adversarial Networks, Mass Customization
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
source	Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
doi	https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_22
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	ijac202220201
id	ijac202220201
authors	Horvath; Anca-Simona
year	2022
title	How we talk(ed) about it: Ways of speaking about computational architecture
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 2, pp. 150–175
summary	If we understand architecture as a three-part system formed by the building, its image, or drawings and imagesdescribing buildings, and the critical discourse around architecture, then the texts or ways of speaking aboutarchitecture play a key role in understanding the field and its development. By analysing a corpus of around 4.6million words from texts written between 2005 and 2020 that form a part of critical discourse in computational architecture (understood as the result of the intense digitalization of the field), this paper aims tomap ways of speaking about computational architecture. This contributes to architectural theory and mighthelp gain a better understanding of the evolution of the digitalization of construction in general. Findings showthat computational architecture is surrounded by a specific way of speaking, hybridized with words fromfields such as biology, neuroscience, arts and humanities, and engineering. While some topics such as‘sustainability’ or ‘biology’ come up consistently in the discourse, others, such as ‘people’ or ‘human’, haveperiods when they are more and less popular. After highlighting open research questions, the paperconcludes by presenting a map of periodic and recurring topics in ways of speaking about computationalarchitecture over the last 15 years, thus tracking and documenting long-term trends, and illuminating patternsin the broader field of digital construction.
keywords	Architectural design, computational architecture, design theory, digital architecture, digital construction, natural language processing
series	journal
last changed	2024/04/17 14:29

_id	ascaad2022_060
id	ascaad2022_060
authors	Senem, Mehmet; Koc, Mustafa; Tuncay, Hayriye; As, Imdat
year	2022
title	Using Deep Learning to Generate Front and Backyards in Landscape Architecture
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. 2-16
summary	The use of artificial intelligence (AI) engines in the design disciplines is a nascent field of research, which became very popular over the last decade. In particular, deep learning (DL) and related generative adversarial networks (GANs) proved to be very promising. While there are many research projects exploring AI in architecture and urban planning, e.g., in order to generate optimal floor layouts, massing models, evaluate image quality, etc., there are not many research projects in the area of landscape architecture - in particular the design of two-dimensional garden layouts. In this paper, we present our work using GANs to generate optimal front- and backyard layouts. We are exploring various GAN engines, e.g., DCGAN, that have been successfully used in other design disciplines. We used supervised and unsupervised learning utilizing a massive dataset of about 100,000 images of front- and backyard layouts, with qualitative and quantitative attributes, e.g., idea and beauty scores, as well as functional and structural evaluation scores. We present the results of our work, i.e., the generation of garden layouts, and their evaluation, and speculate on how this approach may help landscape architects in developing their designs. The outcome of the study may also be relevant to other design disciplines.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	sigradi2022_53
id	sigradi2022_53
authors	Stuart-Smith, Robert; Danahy, Patrick
year	2022
title	3D Generative Design for Non-Experts: Multiview Perceptual Similarity with Agent-Based Reinforcement Learning
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. 115–126
summary	Advances in additive manufacturing allow architectural elements to be fabricated with increasingly complex geometrical designs, however, corresponding 3D design software requires substantial knowledge and skill to operate, limiting adoption by non-experts or people with disabilities. Established non-expert approaches typically constrain geometry, topology, or character to a pre-established configuration, rather than aligning to figural and aesthetic characteristics defined by a user. A methodology is proposed that enables a user to develop multi-manifold designs from sketches or images in several 3d camera projections. An agent-based design approach responds to computer vision analysis (CVA) and Deep Reinforcement Learning (RL) to design outcomes with perceptual similarity to user input images evaluated by Structural Similarity Indexing (SSIM). Several CVA and RL ratios were explored in training models and tested on untrained images to evaluate their effectiveness. Results demonstrate a combination of CVA and RL motion behavior can produce meshes with perceptual similarity to image content.
keywords	Generative Design, Machine Learning, Agent-Based Systems, Non-Expert Design
series	SIGraDi
email
last changed	2023/05/16 16:55

_id	caadria2022_139
id	caadria2022_139
authors	Ataman, Cem, Tuncer, Bige and Perrault, Simon
year	2022
title	Asynchronous Digital Participation in Urban Design Processes: Qualitative Data Exploration and Analysis With Natural Language Processing
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. 383-392
doi	https://doi.org/10.52842/conf.caadria.2022.1.383
summary	This paper aims to improve the usability of qualitative urban big data sources by utilizing Natural Language Processing (NLP) as a promising AI-based technique. In this research, we designed a digital participation experiment by deploying an open-source and customizable asynchronous participation tool, "Consul Project‚, with 47 participants in the campus transformation process of the Singapore University of Technology and Design (SUTD). At the end of the data collection process with several debate topics and proposals, we analysed the qualitative data in entry scale, topic scale, and module scale. We investigated the impact of sentiment scores of each entry on the overall discussion and the sentiment scores of each introduction text on the ongoing discussions to trace the interaction and engagement. Furthermore, we used Latent Dirichlet Allocation (LDA) topic modelling to visualize the abstract topics that occurred in the participation experiment. The results revealed the links between different debates and proposals, which allow designers and decision makers to identify the most interacted arguments and engaging topics throughout participation processes. Eventually, this research presented the potentials of qualitative data while highlighting the necessity of adopting new methods and techniques, e.g., NLP, sentiment analysis, LDA topic modelling, to analyse and represent the collected qualitative data in asynchronous digital participation processes.
keywords	Urban Design, Digital Participation, Qualitative Urban Data, Natural Language Processing (NLP), Sentiment Analysis, LDA Topic Modelling, SDG 10, SDG 11.
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	caadria2022_507
id	caadria2022_507
authors	Bolojan, Daniel, Vermisso, Emmanouil and Yousif, Shermeen
year	2022
title	Is Language All We Need? A Query Into Architectural Semantics Using a Multimodal Generative Workflow
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. 353-362
doi	https://doi.org/10.52842/conf.caadria.2022.1.353
summary	This project examines how interconnected artificial intelligence (AI)-assisted workflows can address the limitations of current language-based models and streamline machine-vision related tasks for architectural design. A precise relationship between text and visual feature representation is problematic and can lead to "ambiguity‚ in the interpretation of the morphological/tectonic complexity of a building. Textual representation of a design concept only addresses spatial complexity in a reductionist way, since the outcome of the design process is co-dependent on multiple interrelated systems, according to systems theory (Alexander 1968). We propose herewith a process of feature disentanglement (using low level features, i.e., composition) within an interconnected generative adversarial networks (GANs) workflow. The insertion of natural language models within the proposed workflow can help mitigate the semantic distance between different domains and guide the encoding of semantic information throughout a domain transfer process.
keywords	Neural Language Models, GAN, Domain Transfer, Design Agency, Semantic Encoding, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ijac202220310
id	ijac202220310
authors	Castro Henriques, Goncalo; Pedro Maciel Xavier; Victor de Luca Silva; Luca Rédua Bispo; Joao Victor Fraga
year	2022
title	Computation for Architecture, hybrid visual and textual language: Research developments and considerations about the implementation of structural imperative and object-oriented paradigms
source	International Journal of Architectural Computing 2022, Vol. 20 - no. 3, pp. 673–687
summary	In the fourth industrial revolution, programming promises to be a fundamental subject like mathematics, science, languages or the arts. Architects design more than buildings developing innovative methods and they are among the pioneers in visual programming development. However, after more than 10 years of visual programming in architecture, despite the fast-learning curve, visual programming presents considerable limitations to solve complex problems. To overcome limitations, the authors propose to associate the advantages of visual and textual languages in Python. The article addresses an ongoing research study to implement Computational Methods in Architectural Education. The authors began by describing the general goal of this project, and of this article in particular. This article focuses on the implementation of two disciplines ‘Computation for Architecture in Python’ I and II. The first discipline uses programming based on the construction of functions in the imperative language, implemented in the text editor, in visual programming, using Grasshopper methods. The second discipline, which is under development, intends to teach object-oriented programming. The results of the first discipline are encouraging; despite reported difficulties in programming fundamentals, such as lists, loops and recursion. The development of the second discipline, in object-oriented programming, deals with the concepts of classes and objects, and more abstract principles such abstraction, inheritance, polymorphism or encapsulation. This paradigm allows building robust programs, but requires a more in-depth syntax. The article reports this ongoing research on this new paradigm of object-oriented language, expanding the application of a hybrid visual-textual language in Architecture
keywords	computation, textual programming, visual programming, imperative programming, object oriented programming
series	journal
last changed	2024/04/17 14:30

_id	ascaad2022_044
id	ascaad2022_044
authors	Shah, Syed; Petzold, Frank
year	2022
title	Research Data Management and a System Design to Semi-Automatically Complete Integrated Data Management Plans [Position Paper]
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. 577-593
summary	Data is an integral part of modern scientific work. Good research data management (RDM) and the communication of the related information is extremely an important matter. It is not only crucial for the ongoing research and its claims but also for the future uses of data. In recent years some guiding principles, e.g. FAIR principles and initiatives at the national and international level, e.g. NFDI, NFDI4Ing have also been founded to improve RDM. The data and its metadata are often handled in file system like structures which are versioned and logged. The information relating to the data handling are documented in data management plan (DMP). DMPs are also usually managed in similar file structures. These are made available in editable document formats as well as online free-text editable forms to which users are required to keep updating manually. These are isolated documents which have neither direct relation to data for verification nor are common to understand with consistency. In this paper, research data management of large-scale interdisciplinary projects is presented. On one hand it introduces, contemporary practices of RDM and on the other hand it helps researchers to determine the features of RDM system in the situations when it comes to select or develop a system for the same purpose. It further introduces a system design for semi-automatic completion of DMP functions in collaborative environment a.k.a. virtual research environment (VRE). It is assumed that the proposed system will assist and enable users to update semi-automatically integrated DMP during all phases of data life cycle. Direct relation to the data for verification, common understanding and consistency will also be maintainable.
series	ASCAAD
email
last changed	2024/02/16 13:29

_id	sigradi2022_220
id	sigradi2022_220
authors	Torreblanca-Díaz, David A.
year	2022
title	Biodigital Product Design Through Additive Fabrication Technologies: Beer Tap Handles Project
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. 1225–1236
summary	Biomimicry is a new transdisciplinary science that studies the models of nature to solve human problems with a systemic approach; design based on nature has had a significant evolution in recent decades thanks to digital technologies advantage, especially digital fabrication and parametric software. This text presents the process of design, experimentation and fabrication of beer tap handles series based on morphological patterns from nature. The project followed this methodological sequence (1) Design problem (2) Selection of biological referents (3) Morphologic synthesis (4) Analysis of thicknesses and stress (5) Detailed design (6) Fabrication of 1:1 scale prototype through Fused Deposition Modelling technology -FDM- (7) User testing (8) Conclusions and improvement proposal. The digital design and fabrication process were effective, the prototypes worked and reached the project goals, the users perceived that the beer tap handles are comfortable, functional and have an attractive appearance.
keywords	Biomimicry, Bio-informed disciplines, Parametric design, Additive fabrication technologies, Fused deposition modelling technology
series	SIGraDi
email
last changed	2023/05/16 16:57

_id	ascaad2022_037
id	ascaad2022_037
authors	Affara, Lama; Nakhal, Bilal
year	2022
title	Computer Vision Aided Hotspot Creation in Virtual Environments
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. 61-73
summary	Hotspot creation is one of the most important modules within virtual environments which helps show the navigators of these environments some information about semantic elements within it and facilitate the navigation between the virtual spaces. In this paper, a system for automatic hotspot proposals and creation in virtual environments is proposed. The system uses computer vision modules to automatically propose hotspot locations in addition to identifying and creating these hotspots with candidate labels. Two main modules used in the system are object detection and scene segmentation. The scene segmentation helps give candidate hotspot areas and provides an overall understanding of the semantics of the virtual environment. The object detection module also uses pretrained deep networks for automatic hotspot creation over these objects. The system helps speed up the hotspot creation process and offers a tool for virtual environment users and creators.
series	ASCAAD
email
last changed	2024/02/16 13:24

_id	caadria2022_33
id	caadria2022_33
authors	Alva, Pradeep, Mosteiro-Romero, Martin, Miller, Clayton and Stouffs, Rudi
year	2022
title	Digital Twin-Based Resilience Evaluation of District-Scale Archetypes
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. 525-534
doi	https://doi.org/10.52842/conf.caadria.2022.1.525
summary	District-scale energy demand models can be powerful tools for understanding interactions in complex urban areas and optimising energy systems in new developments. The process of coupling characteristics of urban environments with simulation software to achieve accurate results is nascent. We developed a digital twin through a web map application for a 170ha district-scale university campus as a pilot. The impact on the built environment is simulated with pandemic (COVID-19) and climate change scenarios. The former can be observed through varying occupancy rates and average cooling loads in the buildings during the lockdown period. The digital twin dashboard was built with visualisations of the 3D campus, real-time data from sensors, energy demand simulation results from the City Energy Analyst (CEA) tool, and occupancy rates from WiFi data. The ongoing work focuses on formulating a resilience assessment metric to measure the robustness of buildings to these disruptions. This district-scale digital twin demonstration can help in facilities management and planning applications. The results show that the digital twin approach can support decarbonising initiatives for cities.
keywords	Digital twin, City Information Modelling, Planning Support System, energy demand model, SGD 11, SGD 13
series	CAADRIA
email
last changed	2022/07/22 07:34

_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	ecaade2022_378
id	ecaade2022_378
authors	Dokonal, Wolfgang, Mosler, Pascal, Gehring, Maximilian and Rüppel, Uwe
year	2022
title	On the Road towards? - Developing a toolset for a low-cost VR-enhanced design approach
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. 163–169
doi	https://doi.org/10.52842/conf.ecaade.2022.1.163
summary	For several years, we have been experimenting with Head Mounted Displays (HMD) being used as Virtual Reality (VR) interfaces. We tried to develop easy to use workflows for these devices so that they can be integrated into the architectural design process. Additionally, we were able to upgrade those systems with sensor boxes and designed new systems for movement control, collision detection, and additional effects for an increased feeling of immersion. Our systems focused on the use of the ultra-low-cost HMD devices and the intention was to clarify how much benefit within the design process we can achieve already at an early design phase in using this workflow without having extremely detailed models available. We experienced with our students in the past that the change from analogue design methods towards software-supported design reduced their understanding of space and scale and was therefore a negative factor in the design process. In this paper, we will focus on scripts for the game engine Unity with new functionalities that we tested with the students in two workshops.
keywords	Sense of Space, Virtual Reality, Unity Toolset
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_78
id	ecaade2022_78
authors	Eroglu, Ruºen and Gül, Leman Figen
year	2022
title	Architectural Form Explorations through Generative Adversarial Networks - Predicting the potentials of StyleGAN
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. 575–582
doi	https://doi.org/10.52842/conf.ecaade.2022.2.575
summary	In recent years, generative models have been rapidly transforming into a broad field of research, and artificial intelligence (AI) works are increasing. Since deep learning technologies such as Generative Adversarial Networks (GANs) providing synthesized new images are becoming more accessible, researchers in the design and related fields are very much interested in adapting GANs into practice. Especially, StyleGAN has a strong capability for image learning, reconstruction simulation, and absorbing the pixel characteristics of images in the input dataset. StyleGAN also produces similar imitation outputs and summarizes all the input data into one "average output". The study aims to reveal the potential of these outputs that can be employed as a visual inspiration aid for designers. This article will discuss the outputs of the experiments, findings, and prospects of StyleGAN.
keywords	Artificial Intelligence, Machine Learning, Generative Adversarial Networks, StyleGAN
series	eCAADe
email
last changed	2024/04/22 07:10

_id	ecaade2022_205
id	ecaade2022_205
authors	Gajda, Weronika and Cannaerts, Corneel
year	2022
title	Citography - Mapping collective mediated experiences
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. 297–305
doi	https://doi.org/10.52842/conf.ecaade.2022.2.297
summary	The ongoing research project Citography explores the impact of technologies such as image sharing, social media, mobile devices, geolocation, surveying, computer vision and data visualisation on our understanding, mapping and design of cities. It questions how these technologies impact notions of place, location, commons and citizenship. This paper presents a first framework resulting from a case study looking into the relationships between protests in physical public space of the city and within the public sphere of social media. It uses data scraping, modelling, data visualisation and animation to construct a tempo-spatial model of the city. The case study explores public spaces vs public sphere and their vision with different devices, emphasising collectively constructed surroundings by people who participate in the protest.
keywords	Protest, Public Space, Public Sphere, Media Ecology
series	eCAADe
email
last changed	2024/04/22 07:10

For more results click below: