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 611

_id cdrf2021_55
id cdrf2021_55
authors Shengyu Meng
year 2021
title Exploring in the Latent Space of Design: A Method of Plausible Building Facades Images Generation, Properties Control and Model Explanation Base on StyleGAN2
source Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)

doi https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_6
summary GAN has been widely applied in the research of architectural image generation. However, the quality and controllability of generated images, and the interpretability of model are still potential to be improved. In this paper, by implementing StyleGAN2 model, plausible building façade images could be generated without conditional input. In addition, by applying GANSpace to analysis the latent space, high-level properties could be controlled for both generated images and novel images outside of training set. At last, the generating and controlling process could be visualized with image embedding and PCA projection method, which could achieve unsupervised classification of generated images, and help to understand the correlation between the images and their latent vectors.
series cdrf
email
last changed 2022/09/29 07:53

_id caadria2021_117
id caadria2021_117
authors Ikeno, Kazunosuke, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year 2021
title Can a Generative Adversarial Network Remove Thin Clouds in Aerial Photographs? - Toward Improving the Accuracy of Generating Horizontal Building Mask Images for Deep Learning in Urban Planning and Design
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. 377-386
doi https://doi.org/10.52842/conf.caadria.2021.2.377
summary Information extracted from aerial photographs is widely used in the fields of urban planning and architecture. An effective method for detecting buildings in aerial photographs is to use deep learning to understand the current state of a target region. However, the building mask images used to train the deep learning model must be manually generated in many cases. To overcome this challenge, a method has been proposed for automatically generating mask images by using textured 3D virtual models with aerial photographs. Some aerial photographs include thin clouds, which degrade image quality. In this research, the thin clouds in these aerial photographs are removed by using a generative adversarial network, which leads to improvements in training accuracy. Therefore, the objective of this research is to propose a method for automatically generating building mask images by using 3D virtual models with textured aerial photographs to enable the removable of thin clouds so that the image can be used for deep learning. A model trained on datasets generated by the proposed method was able to detect buildings in aerial photographs with an accuracy of IoU = 0.651.
keywords Urban planning and design; Deep learning; Generative Adversarial Network (GAN); Semantic segmentation; Mask image
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 acadia21_318
id acadia21_318
authors Borhani, Alireza; Kalantar, Negar
year 2021
title Nesting Fabrication
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. 318-327.
doi https://doi.org/10.52842/conf.acadia.2021.318
summary Positioned at the intersection of the computational modes of design and production, this research explains the principles and applications of a novel fabrication-informed geometric system called nesting. Applying the nesting fabrication method, the authors reimage the construction of complex forms by proposing geometric arrangements that lessen material waste and reduce production time, transportation cost, and storage space requirements. Through this method, appearance and performance characteristics are contingent on fabrication constraints and material behavior. In this study, the focus is on developing design rules for this method and investigating the main parameters involved in dividing the global geometry of a complex volume into stackable components when the first component in the stack gives shape to the second. The authors introduce three different strategies for nesting fabrication: 2D, 2.5D, and 3D nesting. Which of these strategies can be used depends on the geometrical needs of the design and available tools and materials. Next, by revisiting different fabrication approaches, the authors introduce readers to the possibility of large-scale objects with considerable overhangs without the need for nearly any temporary support structures. After establishing a workflow starting with the identification of geometric rules of nesting and ending with fabrication limits, this work showcases the proposed workflow through a series of case studies, demonstrating the feasibility of the suggested method and its capacity to integrate production constraints into the design process. Traversing from pragmatic to geometrical concerns, the approach discussed here offers an integrated approach supporting functional, structural, and environmental matters important when turning material, technical, assembly, and transportation systems into geometric parameters.
series ACADIA
type paper
email
last changed 2023/10/22 12:06

_id ecaade2021_273
id ecaade2021_273
authors Dania, Panagiota, Theodoropoulou, Helena G., Karagianni, Anna, Geropanta, Vasiliki and Parthenios, Panagiotis
year 2021
title Enhancing User Experience through Interaction Design - Rethinking the municipal agora of Chania through AR narratives
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. 263-272
doi https://doi.org/10.52842/conf.ecaade.2021.2.263
summary This paper examines the relationship between designing interactive experiences based on new technologies and the process of architectural narration. It highlights the idea of rethinking a building with historical, architectural and functional value, as an experience and a journey. Referring to the historic building of the Municipal Market of Chania, Greece and using the conceptual idea of designing through narratives, it delineates the process of integrating new technologies into the process of designing a spatial and temporal experience. Exploiting Augmented Reality, we design an application implementing a digital layer with architectural and historical content, that is integrated into reality, improving the on-site visit, providing enhanced understanding of the building and introducing experiential visitor-building interaction. The application is available through mobile devices and the proposed system is evaluated by a group of users showing the positive effects of the use of interactive technologies in redesigning the experience of a space.
keywords Mobile AR; cultural dissemination; architectural narration; interactive spatial experiences; interactive visualization
series eCAADe
email
last changed 2022/06/07 07:55

_id caadria2021_311
id caadria2021_311
authors Gu, Xiangshu, Tian, Shulin, Zhang, Baihui, Tong, Ziyu and Gan, Jingwen
year 2021
title SECTIONMATRIX - Mapping Urban Form through Urban Sections
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. 599-608
doi https://doi.org/10.52842/conf.caadria.2021.2.599
summary Most of the traditional studies on urban morphology are based on aerial views. However, the 2D plane model fails to describe the height information of buildings and the relation of buildings and the urban external space. An urban section is another map of an urban area. Through a series of continuous vertical urban slices, the city texture can be transformed into planar linear information containing height and width information. This paper proposes several indicators to describe a series of urban section slices and uses a three-dimensional coordinate mapping method Sectionmatrix to quantify and analyze the relation between the physical geometrical indicators and urban form from the section perspective. Through the case analysis of multiple residential blocks in Nanjing, China, the results showed that Sectionmatrix is convenient and efficient. Sectionmatrix relates the geometrical properties to the spatial characteristics of urban areas and provides a new way to classify, map and define building typologies. This new classification method reveals the tortuosity and complexity of residential blocks. By bridging the gap between quantity and form, the research also suggests other possible applications of Sectionmatrix as a control instrument and test framework for entire cities planning and design.
keywords Urban Morphology; Urban Section; Sectionmatrix; Quantitative Analysis
series CAADRIA
email
last changed 2022/06/07 07:51

_id caadria2021_166
id caadria2021_166
authors Hu, Wei
year 2021
title The experiment of neural network on the cognition of style
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. 61-70
doi https://doi.org/10.52842/conf.caadria.2021.2.061
summary This paper introduces a method to obtain quantified style description vector which is for computer analysis input by using image style classification task. In the experiment, 3331 architectural photos of three styles obtained by crawling and filtering were used as training data. A deep convolutional neural network was trained to map architectural images to high-dimensional feature space, and then the high-dimensional style description vector was used to output the measurement results of style cognition with fully connected neural network. Tested by test data-set of 371 architectural pictures, the accuracy rate of style cognition reached more than 80%. The neural network using architectural data training was applied to the style cognition of non-architectural objects, high accuracy rate was also achieved, it proved that this quantified style description vector did include the information about style cognition to some extent instead of simply classification. Finally, the similarities and differences between the cognitive characteristics of style of neural network and human beings are investigated.
keywords deep neural network; style cognition experiment; eye tracker
series CAADRIA
email
last changed 2022/06/07 07:50

_id acadia21_152
id acadia21_152
authors Kwon, Hyojin; Sherman, Adam
year 2021
title Crooked Captures
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. 152-157.
doi https://doi.org/10.52842/conf.acadia.2021.152
summary With flashy renderings dominating news feeds and high-flying drones filming from otherwise inaccessible vantage points, our encounters with the built environment increasingly involve perspectival views, but not necessarily those experienced firsthand. As tools for image production and consumption evolve, so too will methods for studying historical precedents.

Crooked Captures treats this proliferation of digital images as fertile ground for photogrammetric explorations into how two-dimensional imaging techniques can influence three-dimensional form. While photogrammetry, the process of determining spatial measurements of physical objects from photographic inputs, has been an area of investigation for almost two centuries, the technique’s potential has blossomed with increased access to high quality cameras. Typical photogrammetric applications couple high-fidelity scanning and computing to produce faithful digital copies of physical artifacts and scenes for measuring and surveying. Leading photogrammetry software packages promise accuracy and precision, touting the exact replication of physical forms in digital space—so-called reality capture—as an indisputable virtue.

series ACADIA
type project
email
last changed 2023/10/22 12:06

_id caadria2021_191
id caadria2021_191
authors Shou, Xinyue, Chen, Pinyang and Zheng, Hao
year 2021
title Predicting the Heat Map of Street Vendors from Pedestrian Flow through Machine Learning
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. 569-578
doi https://doi.org/10.52842/conf.caadria.2021.2.569
summary Street vending is a recent policy advocated by city governments to support small and intermediate businesses in the post-pandemic period in China. Street vendors select their locations primarily based on their intuitions about the surrounding environment; they temporarily occupy popular locations that benefit their business. Taking the city of Chengdu as an example, this study aims to formulate the rules governing vendors location selection using machine learning and big data analysis techniques, thus identifying streets likely to become vital street markets. We propose a semantic segmentation method to construct heat maps that visualize and quantify the distribution of street vendors and pedestrians on public urban streets. The image-based generative adversarial network (GAN) is then trained to predict the vendors heat maps from the pedestrians heat map, finding the relationship between the locations of the vendors and the pedestrians. Our successful prediction of the vendors locations highlights machine learning techniques ability to quantify experience-based decision strategies. Moreover, suggesting potential marketing locations to vendors could help increase cities vitality.
keywords Machine Learning; Big Data Analysis; Semantic Segmentation; Generative Adversarial Networks
series CAADRIA
email
last changed 2022/06/07 07:56

_id sigradi2021_234
id sigradi2021_234
authors Al Nouri, Mhd Ziwar, Baghdadi, Bilal and Khateeb, Nairooz
year 2021
title Re-coding Post-War Syria: The Role of Data Collection & Objective Investigations in PostWar Smart City
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. 127–145
summary Re-coding post-war Syria is an ongoing research and data platform, focused on innovation and collecting comprehensive, infrastructural and socioeconomic analytics, synchronization data, by using AI driven to give a more transparent image of innovating a new methodology to regenerate the future of post-war smart cities into advanced and sustainable urban environments in a smarter way (Fig. 1). The pressure to achieve a rapid Post-war smart city without clear strategy and comprehensive analysis of all aspects will cause a particularly catastrophic collapse in the interconnected social structure, services, education and health care system, leaving a long-term impact on the society. This paper presents the current status of the Research & Documentation methodology in the Data Collection phase by the objective investigations conducted through a series of local and international workshops species developed in this research called “Re-Coding“, offering consequent direct ground surveys, statistics and documentation study of the targeted areas, merging professionalism and youth power with local community to detect an open source data used as a tool to re-generate a precarious area towards a new methodology.
keywords Post-War Smart cities, Collecting Data, Local community, Objective Investigations, Artificial intelligence
series SIGraDi
email
last changed 2022/05/23 12:10

_id sigradi2021_361
id sigradi2021_361
authors Almeida, Julio, Bevilaqua, Diogo, Piaia, Luana and Secchi, Carla
year 2021
title TEC-House: Itinerant Modular Space Based on Digital Fabrication
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. 1499–1510
summary The academy aims to understand and insert digital technologies in the collaborative, interdisciplinary and innovative process. Thus, the process of this project aims to develop an itinerant space that enables integration between academics and the community, associated with digital technologies, making it essential as a precursor of knowledge, innovation and social well-being. Based on concepts from Smart City and Smart Campus, as it addresses a phenomenon of development intrinsic to technological processes in pursuit of environmental quality, it appropriates of digital manufacturing tools as a programmatic production model. Inspired by the generation of physical objects from digital models along the lines of Wikihouse, a modular architectural executive method was developed as an alternative for flexibility and movement. At the end of the process, there is the conception of the TEC-House, idealized as an itinerant modular space, based on anthropometric parameters where function determines the way they integrate, constituting modifying places.
keywords TEC-House, Digital Manufacturing, Modular, Itinerant Space, Innovation
series SIGraDi
email
last changed 2022/05/23 12:11

_id caadria2021_233
id caadria2021_233
authors Ascoli, Raphaël
year 2021
title Augmenting computational design agency in emerging economies
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. 639-648
doi https://doi.org/10.52842/conf.caadria.2021.2.639
summary This /practice-based design research/ investigates the possibility of computational design to increase agency and impact in emerging economies through real-world projects. By cultivating a new kind of relationship to issues in development and local untapped resources, they inspire for more public engagement and resource-based conversations within a spatial framework. The topics that were addressed in this research are the democratization of data and affordability of construction. These two on-going early-stage initiatives have used computational design tools at specific areas in the projects development, therefore optimizing the parts where low-tech tools werent sufficient. This demand driven design process explores ways in which different levels of technology can augment each other.
keywords space; resource; housing; myanmar; optimization
series CAADRIA
email
last changed 2022/06/07 07:54

_id sigradi2021_281
id sigradi2021_281
authors Bernal, Marcelo, Vegas, Gonzalo, Williams, Marvina and Andersen, Katie
year 2021
title Quantification of Effective Temporal Exposure to Daylight Illuminance Levels in Healthcare Settings
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. 315–326
summary The purpose of this study is the quantification of the exposure of occupants to daylight illuminance levels. The case study is the typical floor of a patient tower occupied by nurses in twelve hours shifts, from 7 am to 7 pm. Significant evidence exists regarding the positive impact of access to daylight on staff outcomes in healthcare facilities in terms of reduction of stress, absenteeism, medication errors, and burn outs. However, the standard daylight simulation methods evaluate the building and do not capture the dynamic nature of people’s behavior while moving through the space. The proposed approach combines agent-based simulation and daylight performance analysis to compute the occupants’ exposure to daylight levels throughout the year. The results show the discrepancies between building-centric and human-centric types of analysis and the contribution of dynamic simulation methods to design occupancy schedules to warranty equitable access to daylight to building occupants.
keywords Event model, Building occupancy, Behavior modeling, Space-use analysis, Design tools
series SIGraDi
email
last changed 2022/05/23 12:10

_id acadia21_400
id acadia21_400
authors Bruce, Mackenzie; Clune, Gabrielle; Xie, Ruxin; Mozaffari, Salma; Adel, Arash
year 2021
title Cocoon: 3D Printed Clay Formwork for Concrete Casting
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. 400-409.
doi https://doi.org/10.52842/conf.acadia.2021.400
summary Concrete, a material widely used in the construction industry today for its low cost and considerable strength as a composite building material, allows designers to work with nearly any form imaginable; if the technology to build the formwork is possible. By combining two historic and widely used materials, clay and concrete, our proposed novel process, Cocoon, integrates robotic clay three-dimensional (3D) printing as the primary formwork and incrementally casting concrete into this formwork to fabricate nonstandard concrete elements. The incremental casting and printing process anchors the concrete and clay together, creating a symbiotic and harmonious relationship. The concrete’s fluidity takes shape from the 3D printed clay formwork, allowing the clay to gain structure from the concrete as it cures. As the clay loses moisture, the formwork begins to shrink, crack, and reveal the concrete below. This self-demolding process produces easily removable formwork that can then be recycled by adding water to rehydrate the clay creating a nearly zero-waste formwork. This technique outlines multiple novel design features for complex concrete structures, including extended height limit, integrated void space design, tolerable overhang, and practical solutions for clay deformation caused by the physical stress during the casting process. The novelty of the process created by 3D printing clay formwork using an industrial robotic arm allows for rapid and scalable production of nearly zero-waste customizable formwork. More significant research implications can impact the construction industry, integrating more sustainable ways to build, enabled by digital fabrication technologies.
series ACADIA
type paper
email
last changed 2023/10/22 12:06

_id ecaade2021_326
id ecaade2021_326
authors Chan, Holly, Brown, Andre, Moleta, Tane and Schnabel, Marc Aurel
year 2021
title Augmented Spaces - If walls could talk
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. 575-584
doi https://doi.org/10.52842/conf.ecaade.2021.2.575
summary This paper explores the development of Augmented Spaces that involve embedding within the built environment, digitally responsive recognition of human presence. Contemporary digital media provides the opportunity to enhance physical space with the property of immediate interaction, which results in a high level of user engagement and responsivenenss. Through the addition of digital media, emotional and reflective value can be added to the built form. If space is designed to be reactive, rather than passive, a dialogue can be established between the user/inhabitant and the environment. We report on the establishment and analysis of a set of prototype digital interventions in urban space that react to human presence. One is in a building threshold space; one an urban street. We describe the development of a digital particle system with two inputs; the first being the geometry that generates the particles and the second being the geometry that displaces the particles. The research goals that we report on are driven by three over-riding response criteria, Visceral, Behavioural and Reflective.
keywords augmented space; reactive; synesthetic
series eCAADe
email
last changed 2022/06/07 07:56

_id ijac202119312
id ijac202119312
authors Chen, Chen; Chacón Vega, Ricardo Jose; Kong, Tiong Lee
year 2021
title Using genetic algorithm to automate the generation of an open-plan office layout
source International Journal of Architectural Computing 2021, Vol. 19 - no. 3, 449–465
summary Today, the concept of open plan is more and more widely accepted that many companies have switched to open-plan offices. Their design is an issue in the scope of space layout planning. Although there are many professional architectural layout design software in the market, in the real life, office designers seldom use these tools because their license fees are usually expensive and using them to solve an open-plan office design is like using an overly powerful and expensive tool to fix a minor problem. Therefore, manual drafting through a trial and error process is most often used. This article attempts to propose a lightweight tool to automate open-plan office layout generation using a nested genetic algorithm optimization with two layers, where the inner layer algorithm is embedded in the outer one. The result is enhanced by a local search. The main objective is to maximize space utilization by maximizing the size of the open workspace. This approach is different from its precedents, in that the location search is conducted on a grid map rather than several pre-selected candidate locations. Consequently, the generated layout design presents a less rigid workstation arrangement, inviting a casual and unrestrictive work environment. The real potential of the approach is reflected in the productivity of test fits. Automating and simplifying the generation of layouts for test fits can tremendously decrease the amount of time and resources required to generate them. The experimental case study shows that the developed approach is powerful and effective, making it a totally automated process.
keywords Automated process, office design, genetic algorithm, open-plan office, space layout planning
series journal
email
last changed 2024/04/17 14:29

_id caadria2021_038
id caadria2021_038
authors Chen, Jielin and Stouffs, Rudi
year 2021
title From Exploration to Interpretation - Adopting Deep Representation Learning Models to Latent Space Interpretation of Architectural Design Alternatives
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. 131-140
doi https://doi.org/10.52842/conf.caadria.2021.1.131
summary An informative interpretation of the hyper-dimensional design solution space can potentially enhance the cognitive capacity of designers with respect to both conventional design practice and the research domain of computational-aided generative design. However, the hitherto research of design space exploration has had limited focus on the interpretation of the hyper solution space per se due to the knowledge gap pertaining to representation and generation. Representation learning techniques, as a core paradigm in the statistically empowered domain of machine learning, possess the capability of extracting a convoluted probabilistic distribution of hyperspace with latent features from unorganized data sources in a generalized manner, which can be an intuitive modus operandi for a structural interpretation of the intricate latent design solution space and benefit the challenging task of architectural design exploration. We examine and demonstrate the potential capabilities of representation learning techniques for the interpretation of latent architectural design solution space with consideration of disentanglement and diversity.
keywords Design space exploration; latent space interpretation; representation learning; deep generative modelling; generative architectural design
series CAADRIA
email
last changed 2022/06/07 07:55

_id caadria2021_008
id caadria2021_008
authors Chung, Minyoung and Lee, Hyunsoo
year 2021
title Using Virtual Filters to Measure how the Elderly Perceive Color
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. 325-334
doi https://doi.org/10.52842/conf.caadria.2021.2.325
summary This study was conducted to test the effectiveness of a virtual filter that digitally compensates for age-related changes in color perception. Many elderly people experience declining color perception. Medical studies have been conducted on how elderly peoples lenses affect their color perception. However, digital practical method for improving elderly peoples color perception need to be developed. Subway map is a good example of many elders daily experience. To adapt virtual filters to subway maps colors, standard short-wavelength colors, namely purple and green, were selected for variance independence (VI) because colors with short wavelengths of 400-600 nm on visible light are difficult for elderly people to perceive. Standard color VIs of subway lines and VI transferred to artificial lenses were measured with a spectrophotometer. CIE LAB and RGB; Color value on virtual filter (VD) was analyzed from VI. This virtual filter was developed based on artificial lenses using Dynamo. A visual programming algorithm was developed to adjust the color of a virtual filter through an interface. The results showed that virtual filters can be used to help elderly people detect short-wavelength colors. Therefore, virtual filters should be incorporated into lenses for use by the elderly.
keywords Virtual filter; Elderly people's perception; Colors on subway map
series CAADRIA
email
last changed 2022/06/07 07:56

_id caadria2021_142
id caadria2021_142
authors Cruz Gambardella, Camilo and McCormack, Jon
year 2021
title Searching for designs in-between - Exploration of design space using a 3D printing-inspired evolutionary system.
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. 111-120
doi https://doi.org/10.52842/conf.caadria.2021.1.111
summary The use of evolutionary methods in design and art is increasing in diversity and popularity. Approaches to using these methods for creative production typically focus either on optimisation or exploration. In this paper we introduce an evolutionary system for design that combines these two approaches, enabling users to explore landscapes of design alternatives using design-oriented measures of fitness, along with their own aesthetic preferences. We test our methods using a biologically-inspired generative system capable of producing 3D objects that can be exported directly as 3D printing toolpath instructions. For the search stage of our system we combine the use of the CMA-ES algorithm for optimisation and linear interpolation between generated objects for feature exploration. We investigate the systems capabilities by evolving highly fit artefacts and then combining them with aesthetically interesting ones.
keywords Generative Design; Evolutionary Design; 3D Printing
series CAADRIA
email
last changed 2022/06/07 07:56

_id ecaade2021_240
id ecaade2021_240
authors Dan, Yuze, Shen, Zhenjiang, Lin, Yumin, Zhu, Yiyun and Xiao, Jianqiang
year 2021
title The Development of Design Support System for Public Participation of Community Public Space Design Using Mixed Reality
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. 205-212
doi https://doi.org/10.52842/conf.ecaade.2021.1.205
summary Public participation has been continuously encouraged in community planning and design. However, lacking effective participatory tools, the professional design documents are complicated for the public to understand, let alone express their design intentions. The advancement of computer graphics brings possibilities to suppress this barrier, especially for the emergence of Mixed Reality (MR). In this research, we used MR technology to develop a design support tool for public participation. We implemented this system successfully by creating interactive interfaces, developing design functions, implementing design data, and establishing interactive visualizations. To examine its effectiveness, we did a participatory design experiment. We invited twelve participants to view the 3D design proposal and then make adjustments based on their respective preferences using the MR design support system. This experiment demonstrated that this system could achieve intuitive on-site 3D visualization for the public to understand professional design proposals and real-time design interactions to present their design intentions.
keywords Public participation; Design support system; Mixed Reality; Interactive visualization; Community design
series eCAADe
email
last changed 2022/06/07 07:55

For more results click below:

this is page 0show page 1show page 2show page 3show page 4show page 5... show page 30HOMELOGIN (you are user _anon_449953 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002