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 609

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

_id	cf2019_004
id	cf2019_004
authors	Kim, Jinsung; Jaeyeol Song and Jin-Kook Lee
year	2019
title	Recognizing and Classifying Unknown Object in BIM using 2D CNN
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 23
summary	This paper aims to propose an approach to automated classifying building element instance in BIM using deep learning-based 3D object classification algorithm. Recently, studies related to checking or validating engine of BIM object for ensuring data integrity of BIM instances are getting attention. As a part of this research, this paper train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs. Object recognition is executed in two stages; 1) class of object (e.g. wall, window, seating furniture, toilet fixture and etc.), 2) sub-type of specific classes (e.g. Toilet or Urinal). Using the trained models, BIM plug-in prototype is developed and the performance of this AI-based approach with test BIM model is checked. We expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of BIM.
keywords	3D object classification, Building element, Building information modeling, Data integrity, Interior element
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	caadria2019_650
id	caadria2019_650
authors	Papasotiriou, Tania
year	2019
title	Identifying the Landscape of Machine Learning-Aided Architectural Design - A Term Clustering and Scientometrics Study
doi	https://doi.org/10.52842/conf.caadria.2019.2.815
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 815-824
summary	Recent advances in Machine Learning and Deep Learning revolutionise many industry disciplines and underpin new ways of problem-solving. This paradigm shift hasn't left Architecture unaffected. To investigate the impact on architectural design, this study utilises two approaches. First, a text mining method for content analysis is employed, to perform a robust review of the field's literature. This allows identifying and discussing current trends and possible future directions of this research domain in a systematic manner. Second, a Scientometrics study based on bibliometric reviews is employed to obtain quantitative measures of the global research activity in the described domain. Insights on research trends and identification of the most influential networks in this dataset were acquired by analysing terms co-occurrence, scientific collaborations, geographic distribution, and co-citation analysis. The paper concludes with a discussion on the limitations, opportunities and future research directions in the field of Machine Learning-aided architectural design.
keywords	Machine Learning; Text mining; Scientometrics
series	CAADRIA
email
last changed	2022/06/07 08:00

_id	ecaadesigradi2019_593
id	ecaadesigradi2019_593
authors	Vermillion, Joshua and de Salvatierra, Alberto
year	2019
title	Physical Computing, Prototyping, and Participatory Pedagogies - Make-a-thon as interdisciplinary catalyst for bottom-up social change
doi	https://doi.org/10.52842/conf.ecaade.2019.1.359
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 359-366
summary	This paper describes a recent make-a-thon event to engage architecture students with physical computing systems while working with engineering and entrepreneurship students. Focusing on the scale of the object or device, the pedagogical goals were to create a productive, transdisciplinary exchange--a pluralistic blend of design charrette, engineering hackathon, and entrepreneurial pitch competition. The Arduino platform and active learning methods were deployed in order to engage with a novice, diverse group of students, leading to outcomes that were responsive to the ever-shifting technological landscape and could be spun into future commercial ventures.
keywords	Physical Computing; Prototyping; Pedagogy
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_387
id	ecaadesigradi2019_387
authors	Wibranek, Bastian, Belousov, Boris, Sadybakasov, Alymbek, Peters, Jan and Tessmann, Oliver
year	2019
title	Interactive Structure - Robotic Repositioning of Vertical Elements in Man-Machine Collaborative Assembly through Vision-Based Tactile Sensing
doi	https://doi.org/10.52842/conf.ecaade.2019.2.705
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 705-713
summary	The research presented in this paper explores a novel tactile sensor technology for architectural assembly tasks. In order to enable robots to interact both with humans and building elements, several robot control strategies had to be implemented. Therefore, we developed a communication interface between the architectural design environment, a tactile sensor and robot controllers. In particular, by combining tactile feedback with real-time gripper and robot control algorithms, we demonstrate grasp adaptation, object shape and texture estimation, slip and contact detection, force and torque estimation. We investigated the integration of robotic control strategies for human-robot interaction and developed an assembly task in which the robot had to place vertical elements underneath a deformed slab. Finally, the proposed tactile feedback controllers and learned skills are combined together to demonstrate applicability and utility of tactile sensing in collaborative human-robot architectural assembly tasks. Users were able to hand over building elements to the robot or guide the robot through the interaction with building elements. Ultimately this research aims to offer the possibility for anyone to interact with built structures through robotic augmentation.
keywords	Interactive Structure; Robotics; Tactile Sensing; Man-Machine Collaboration
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

_id	cf2019_022
id	cf2019_022
authors	Koh, Immanuel and Jeffrey Huang
year	2019
title	Citizen Visual Search Engine:Detection and Curation of Urban Objects
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 170
summary	Increasingly, the ubiquity of satellite imagery has made the data analysis and machine learning of large geographical datasets one of the building blocks of visuospatial intelligence. It is the key to discover current (and predict future) cultural, social, financial and political realities. How can we, as designers and researchers, empower citizens to understand and participate in the design of our cities amid this technological shift? As an initial step towards this broader ambition, a series of creative web applications, in the form of visual search engines, has been developed and implemented to data mine large datasets. Using open sourced deep learning and computer vision libraries, these applications facilitate the searching, detecting and curating of urban objects. In turn, the paper proposes and formulates a framework to design truly citizen-centric creative visual search engines -- a contribution to citizen science and citizen journalism in spatial terms.
keywords	Deep Learning, Computer Vision, Satellite Imagery, Citizen Science, Artificial Intelligence
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	acadia19_664
id	acadia19_664
authors	Koshelyuk, Daniil; Talaei, Ardeshir; Garivani, Soroush; Markopoulou, Areti; Chronis, Angelo; Leon, David Andres; Krenmuller, Raimund
year	2019
title	Alive
doi	https://doi.org/10.52842/conf.acadia.2019.664
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 664-673
summary	In the context of data-driven culture, built space still maintains low responsiveness and adaptability. Part of this reality lies in the low resolution of live information we have about the behavior and condition of surfaces and materials. This research addresses this issue by exploring the development of a deformation-sensing composite membrane material system following a bottom-up approach and combining various technologies toward solving related technical issues—exploring conductivity properties of graphene and maximizing utilization within an architecture-related proof-of-concept scenario and a workflow including design, fabrication, and application methodology. Introduced simulation of intended deformation helps optimize the pattern of graphene nanoplatelets (GNP) to maximize membrane sensitivity to a specific deformation type while minimizing material usage. Research explores various substrate materials and graphene incorporation methods with initial geometric exploration. Finally, research introduces data collection and machine learning techniques to train recognition of certain types of deformation (single point touch) on resistance changes. The final prototype demonstrates stable and symmetric readings of resistance in a static state and, after training, exhibits an 88% prediction accuracy of membrane shape on a labeled sample data-set through a pre-trained neural network. The proposed framework consisting of a simulation based, graphene-capturing fabrication method on stretchable surfaces, and includes initial exploration in neural network training shape detection, which combined, demonstrate an advanced approach to embedding intelligence.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:51

_id	acadia21_76
id	acadia21_76
authors	Smith, Rebecca
year	2021
title	Passive Listening and Evidence Collection
doi	https://doi.org/10.52842/conf.acadia.2021.076
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. 76-81.
summary	In this paper, I present the commercial, urban-scale gunshot detection system ShotSpotter in contrast with a range of ecological sensing examples which monitor animal vocalizations. Gunshot detection sensors are used to alert law enforcement that a gunshot has occurred and to collect evidence. They are intertwined with processes of criminalization, in which the individual, rather than the collective, is targeted for punishment. Ecological sensors are used as a “passive” practice of information gathering which seeks to understand the health of a given ecosystem through monitoring population demographics, and to document the collective harms of anthropogenic change (Stowell and Sueur 2020). In both examples, the ability of sensing infrastructures to “join up and speed up” (Gabrys 2019, 1) is increasing with the use of machine learning to identify patterns and objects: a new form of expertise through which the differential agendas of these systems are implemented and made visible. I trace the differential agendas of these systems as they manifest through varied components: the spatial distribution of hardware in the existing urban environment and / or landscape; the software and other informational processes that organize and translate the data; the visualization of acoustical sensing data; the commercial factors surrounding the production of material components; and the apps, platforms, and other forms of media through which information is made available to different stakeholders. I take an interpretive and qualitative approach to the analysis of these systems as cultural artifacts (Winner 1980), to demonstrate how the political and social stakes of the technology are embedded throughout them.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2021_203
id	ecaade2021_203
authors	Arora, Hardik, Bielski, Jessica, Eisenstadt, Viktor, Langenhan, Christoph, Ziegler, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Consistency Checker - An automatic constraint-based evaluator for housing spatial configurations
doi	https://doi.org/10.52842/conf.ecaade.2021.2.351
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. 351-358
summary	The gradual rise of artificial intelligence (AI) and its increasing visibility among many research disciplines affected Computer-Aided Architectural Design (CAAD). Architectural deep learning (DL) approaches are being developed and published on a regular basis, such as retrieval (Sharma et al. 2017) or design style manipulation (Newton 2019; Silvestre et al. 2016). However, there seems to be no method to evaluate highly constrained spatial configurations for specific architectural domains (such as housing or office buildings) based on basic architectural principles and everyday practices. This paper introduces an automatic constraint-based consistency checker to evaluate the coherency of semantic spatial configurations of housing construction using a small set of design principles to evaluate our DL approaches. The consistency checker informs about the overall performance of a spatial configuration followed by whether it is open/closed and the constraints it didn't satisfy. This paper deals with the relation of spaces processed as mathematically formalized graphs contrary to existing model checking software like Solibri.
keywords	model checking, building information modeling, deep learning, data quality
series	eCAADe
email
last changed	2022/06/07 07:54

_id	caadria2019_396
id	caadria2019_396
authors	Cao, Rui, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2019
title	Quantifying Visual Environment by Semantic Segmentation Using Deep Learning - A Prototype for Sky View Factor
doi	https://doi.org/10.52842/conf.caadria.2019.2.623
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 623-632
summary	Sky view factor (SVF) is the ratio of radiation received by a planar surface from the sky to that received from the entire hemispheric radiating environment, in the past 20 years, it was more applied to urban-climatic areas such as urban air temperature analysis. With the urbanization and the development of cities, SVF has been paid more and more attention on as the important parameter in urban construction and city planning area because of increasing building coverage ratio to promote urban forms and help creating a more comfortable and sustainable urban residential building environment to citizens. Therefore, efficient, low cost, high precision, easy to operate, rapid building-wide SVF estimation method is necessary. In the field of image processing, semantic segmentation based on deep learning have attracted considerable research attention. This study presents a new method to estimate the SVF of residential environment by constructing a deep learning network for segmenting the sky areas from 360-degree camera images. As the result of this research, an easy-to-operate estimation system for SVF based on high efficiency sky label mask images database was developed.
keywords	Visual environment; Sky view factor; Semantic segmentation; Deep learning; Landscape simulation
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	ecaadesigradi2019_514
id	ecaadesigradi2019_514
authors	de Miguel, Jaime, Villafa?e, Maria Eugenia, Piškorec, Luka and Sancho-Caparrini, Fernando
year	2019
title	Deep Form Finding - Using Variational Autoencoders for deep form finding of structural typologies
doi	https://doi.org/10.52842/conf.ecaade.2019.1.071
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 71-80
summary	In this paper, we are aiming to present a methodology for generation, manipulation and form finding of structural typologies using variational autoencoders, a machine learning model based on neural networks. We are giving a detailed description of the neural network architecture used as well as the data representation based on the concept of a 3D-canvas with voxelized wireframes. In this 3D-canvas, the input geometry of the building typologies is represented through their connectivity map and subsequently augmented to increase the size of the training set. Our variational autoencoder model then learns a continuous latent distribution of the input data from which we can sample to generate new geometry instances, essentially hybrids of the initial input geometries. Finally, we present the results of these computational experiments and lay out the conclusions as well as outlook for future research in this field.
keywords	artificial intelligence; deep neural networks; variational autoencoders; generative design; form finding; structural design
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	acadia19_16
id	acadia19_16
authors	Hosmer, Tyson; Tigas, Panagiotis
year	2019
title	Deep Reinforcement Learning for Autonomous Robotic Tensegrity (ART)
doi	https://doi.org/10.52842/conf.acadia.2019.016
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 16-29
summary	The research presented in this paper is part of a larger body of emerging research into embedding autonomy in the built environment. We develop a framework for designing and implementing effective autonomous architecture defined by three key properties: situated and embodied agency, facilitated variation, and intelligence.We present a novel application of Deep Reinforcement Learning to learn adaptable behaviours related to autonomous mobility, self-structuring, self-balancing, and spatial reconfiguration. Architectural robotic prototypes are physically developed with principles of embodied agency and facilitated variation. Physical properties and degrees of freedom are applied as constraints in a simulated physics-based environment where our simulation models are trained to achieve multiple objectives in changing environments. This holistic and generalizable approach to aligning deep reinforcement learning with physically reconfigurable robotic assembly systems takes into account both computational design and physical fabrication. Autonomous Robotic Tensegrity (ART) is presented as an extended case study project for developing our methodology. Our computational design system is developed in Unity3D with simulated multi-physics and deep reinforcement learning using Unity’s ML-agents framework. Topological rules of tensegrity are applied to develop assemblies with actuated tensile members. Single units and assemblies are trained for a series of policies using reinforcement learning in single-agent and multi-agent setups. Physical robotic prototypes are built and actuated to test simulated results.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:50

_id	acadia20_382
id	acadia20_382
authors	Hosmer, Tyson; Tigas, Panagiotis; Reeves, David; He, Ziming
year	2020
title	Spatial Assembly with Self-Play Reinforcement Learning
doi	https://doi.org/10.52842/conf.acadia.2020.1.382
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 382-393.
summary	We present a framework to generate intelligent spatial assemblies from sets of digitally encoded spatial parts designed by the architect with embedded principles of prefabrication, assembly awareness, and reconfigurability. The methodology includes a bespoke constraint-solving algorithm for autonomously assembling 3D geometries into larger spatial compositions for the built environment. A series of graph-based analysis methods are applied to each assembly to extract performance metrics related to architectural space-making goals, including structural stability, material density, spatial segmentation, connectivity, and spatial distribution. Together with the constraint-based assembly algorithm and analysis methods, we have integrated a novel application of deep reinforcement (RL) learning for training the models to improve at matching the multiperformance goals established by the user through self-play. RL is applied to improve the selection and sequencing of parts while considering local and global objectives. The user’s design intent is embedded through the design of partial units of 3D space with embedded fabrication principles and their relational constraints over how they connect to each other and the quantifiable goals to drive the distribution of effective features. The methodology has been developed over three years through three case study projects called ArchiGo (2017–2018), NoMAS (2018–2019), and IRSILA (2019-2020). Each demonstrates the potential for buildings with reconfigurable and adaptive life cycles.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaadesigradi2019_117
id	ecaadesigradi2019_117
authors	Kido, Daiki, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2019
title	Development of a Semantic Segmentation System for Dynamic Occlusion Handling in Mixed Reality for Landscape Simulation
doi	https://doi.org/10.52842/conf.ecaade.2019.1.641
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 641-648
summary	The use of mixed reality (MR) for landscape simulation has attracted attention recently. MR can produce a realistic landscape simulation by merging a three-dimensional computer graphic (3DCG) model of a new building on a real space. One challenge with MR that remains to be tackled is occlusion. Properly handling occlusion is important for the understanding of the spatial relationship between physical and virtual objects. When the occlusion targets move or the target's shape changes, depth-based methods using a special camera have been applied for dynamic occlusion handling. However, these methods have a limitation of the distance to obtain depth information and are unsuitable for outdoor landscape simulation. This study focuses on a dynamic occlusion handling method for MR-based landscape simulation. We developed a real-time semantic segmentation system to perform dynamic occlusion handling. We designed this system for use in mobile devices with client-server communication for real-time semantic segmentation processing in mobile devices. Additionally, we used a normal monocular camera for practice use.
keywords	Mixed Reality; Dynamic occlusion handling; Semantic segmentation; Deep learning; Landscape simulation
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	caadria2019_109
id	caadria2019_109
authors	Kim, Jinsung, Song, Jaeyeol and Lee, Jin-Kook
year	2019
title	Approach to Auto-recognition of Design Elements for the Intelligent Management of Interior Pictures
doi	https://doi.org/10.52842/conf.caadria.2019.2.785
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 785-794
summary	This paper explores automated recognition of elements in interior design pictures for an intelligent design reference management system. Precedent design references have a significant role to help architects, designer and even clients in general architecture design process. Pictures are one of the representation that could exactly show a kind of design idea and knowledge. Due to the velocity, variety and volume of reference pictures data with growth of references platform, it is hard and time-consuming to handle the data with current manual way. To solve this problem , this paper depicts a deep learning-based approach to figuring out design elements and recognizing the design feature of them on the interior pictures using faster-RCNN and CNN algorithms. The targets are the residential furniture such as a table and a seating. Through proposed application, input pictures can automatically have tagging data as follows; seating1(type: sofa, seating capacity: two-seaters, design style: classic)
keywords	Interior design picture; Design element; Design feature; Automated recognition; Design Reference management
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaadesigradi2019_339
id	ecaadesigradi2019_339
authors	Kinugawa, Hina and Takizawa, Atsushi
year	2019
title	Deep Learning Model for Predicting Preference of Space by Estimating the Depth Information of Space using Omnidirectional Images
doi	https://doi.org/10.52842/conf.ecaade.2019.2.061
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 61-68
summary	In this study, we developed a method for generating omnidirectional depth images from corresponding omnidirectional RGB images of streetscapes by learning each pair of omnidirectional RGB and depth images created by computer graphics using pix2pix. Then, the models trained with different series of images shot under different site and weather conditions were applied to Google street view images to generate depth images. The validity of the generated depth images was then evaluated visually. In addition, we conducted experiments to evaluate Google street view images using multiple participants. We constructed a model that estimates the evaluation value of these images with and without the depth images using the learning-to-rank method with deep convolutional neural network. The results demonstrate the extent to which the generalization performance of the streetscape evaluation model changes depending on the presence or absence of depth images.
keywords	Omnidirectional image; depth image; Unity; Google street view; pix2pix; RankNet
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	ecaadesigradi2019_060
id	ecaadesigradi2019_060
authors	Koenig, Reinhard and Schneider, Sven
year	2019
title	Evaluation of systems for video-based online teaching - Create your own MOOC or SPOC
doi	https://doi.org/10.52842/conf.ecaade.2019.1.109
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 109-116
summary	There are a lot of discussions about digitalizing university teaching and opening it to civil society. In this context, we investigate the current options for setting up and distributing video-based online courses. First, we make a review of a subjectively selected set of existing platforms and technologies for video-based online courses. Next, we discuss the needs of futures online teaching concepts and the corresponding challenges of digitalization for university teaching. We summarize essential aspects of the considered platforms, technologies, and today's examples in tables. The main result is an overview of systems that can be used to start your online teaching initiative with a small budget.
keywords	Online learning; video-based courses; MOOC; SPOC
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:51

_id	ecaadesigradi2019_135
id	ecaadesigradi2019_135
authors	Newton, David
year	2019
title	Deep Generative Learning for the Generation and Analysis of Architectural Plans with Small Datasets
doi	https://doi.org/10.52842/conf.ecaade.2019.2.021
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 21-28
summary	The field of generative architectural design has explored a wide range of approaches in the automation of design production, but these approaches have demonstrated limited artificial intelligence. Generative Adversarial Networks (GANs) are a leading deep generative model that use deep neural networks (DNNs) to learn from a set of training examples in order to create new design instances with a degree of flexibility and fidelity that outperform competing generative approaches. Their application to generative tasks in architecture, however, has been limited. This research contributes new knowledge on the use of GANs for architectural plan generation and analysis in relation to the work of specific architects. Specifically, GANs are trained to synthesize architectural plans from the work of the architect Le Corbusier and are used to provide analytic insight. Experiments demonstrate the efficacy of different augmentation techniques that architects can use when working with small datasets.
keywords	generative design; deep learning; artificial intelligence; generative adversarial networks
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	caadria2021_053
id	caadria2021_053
authors	Rhee, Jinmo and Veloso, Pedro
year	2021
title	Generative Design of Urban Fabrics Using Deep Learning
doi	https://doi.org/10.52842/conf.caadria.2021.1.031
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. 31-40
summary	This paper describes the Urban Structure Synthesizer (USS), a research prototype based on deep learning that generates diagrams of morphologically consistent urban fabrics from context-rich urban datasets. This work is part of a larger research on computational analysis of the relationship between urban context and morphology. USS relies on a data collection method that extracts GIS data and converts it to diagrams with context information (Rhee et al., 2019). The resulting dataset with context-rich diagrams is used to train a Wasserstein GAN (WGAN) model, which learns how to synthesize novel urban fabric diagrams with the morphological and contextual qualities present in the dataset. The model is also trained with a random vector in the input, which is later used to enable parametric control and variation for the urban fabric diagram. Finally, the resulting diagrams are translated to 3D geometric entities using computer vision techniques and geometric modeling. The diagrams generated by USS suggest that a learning-based method can be an alternative to methods that rely on experts to build rule sets or parametric models to grasp the morphological qualities of the urban fabric.
keywords	Deep Learning; Urban Fabric; Generative Design; Artificial Intelligence; Urban Morphology
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2020_259
id	caadria2020_259
authors	Rhee, Jinmo, Veloso, Pedro and Krishnamurti, Ramesh
year	2020
title	Integrating building footprint prediction and building massing - an experiment in Pittsburgh
doi	https://doi.org/10.52842/conf.caadria.2020.2.669
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 669-678
summary	We present a novel method for generating building geometry using deep learning techniques based on contextual geometry in urban context and explore its potential to support building massing. For contextual geometry, we opted to investigate the building footprint, a main interface between urban and architectural forms. For training, we collected GIS data of building footprints and geometries of parcels from Pittsburgh and created a large dataset of Diagrammatic Image Dataset (DID). We employed a modified version of a VGG neural network to model the relationship between (c) a diagrammatic image of a building parcel and context without the footprint, and (q) a quadrilateral representing the original footprint. The option for simple geometrical output enables direct integration with custom design workflows because it obviates image processing and increases training speed. After training the neural network with a curated dataset, we explore a generative workflow for building massing that integrates contextual and programmatic data. As trained model can suggest a contextual boundary for a new site, we used Massigner (Rhee and Chung 2019) to recommend massing alternatives based on the subtraction of voids inside the contextual boundary that satisfy design constraints and programmatic requirements. This new method suggests the potential that learning-based method can be an alternative of rule-based design methods to grasp the complex relationships between design elements.
keywords	Deep Learning; Prediction; Building Footprint; Massing; Generative Design
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2019_657
id	caadria2019_657
authors	Chen, Zhewen, Zhang, Liming and Yuan, Philip F.
year	2019
title	Innovative Design Approach to Optimized Performance on Large-Scale Robotic 3D-Printed Spatial Structure
doi	https://doi.org/10.52842/conf.caadria.2019.2.451
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 451-460
summary	This paper presents an innovative approach on designing large-scale spatial structure with automated robotic 3D-printing. The incipient design approach mainly focused on optimizing structural efficiency at an early design stage by transform the object into a discrete system, and the elements in this system contains unique structural parameters that corresponding to its topology results of stiffness distribution. Back in 2017, the design team already implemented this concept into an experimental project of Cloud Pavilion in Shanghai, China, and the 3D-printed spatial structure was partitioned into five zones represent different level of structure stiffness and filled with five kinds of unit toolpath accordingly. Through further research, an upgrade version, the project of Cloud Pavilion 2.0 is underway and will be completed in January 2019. A detailed description on innovative printing toolpath design in this project is conducted in this paper and explains how the toolpath shape effects its overall structural stiffness. This paper contributes knowledge on integrated design in the field of robotic 3D-printing and provides an alternative approach on robotic toolpath design combines with the optimized topological results.
keywords	3D-Printing; Robotic Fabrication; Structural Optimization; Discrete System; Toolpath Design
series	CAADRIA
email
last changed	2022/06/07 07:54

For more results click below: