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 606

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

_id	sigradi2021_130
id	sigradi2021_130
authors	Hiilesmaa, Laura, Galbes Breda de Lima, Eduardo, Chieppe Carvalho, Leonardo, Wenzel Martins, Gisele and Vizioli, Simone Helena Tanoue
year	2021
title	Heritage Education: Computational Design of the Virtual Exhibition at the Cultural and Scientific Divulgation Center of USP
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. 605–616
summary	During the current pandemic situation, in 2020/2021, there has been an increased need for easier remote access to cultural and heritage sites, especially on users’ smartphones and personal devices. The exhibition from the 40 years anniversary of the Cultural and Scientific Divulgation Center (CDCC) of the University of Sao Paulo (USP) was selected in order to accomplish the fundamental objectives of this study. The transition of its contents to digital media was enabled by three main technologies: 360° panoramic images, used broadly in the virtual tour; close-range photogrammetry for the creation of 3D models of objects, such as the bust of Dante Alighieri; and informative GIFs of the Transparent Woman of Dresden. As a result of the methodology proposed, this paper introduces a link with the virtual tour developed, presenting an important resource to spread a multidisciplinary knowledge about this meaningful built heritage of Sao Carlos (SP).
keywords	Fotogrametria, Imagens Panorâmicas 360°, Educaçao Patrimonial, Patrimônios Materiais, Tour Virtual 360°.
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	sigradi2021_49
id	sigradi2021_49
authors	Massara Rocha, Bruno, Alvarenga, Augusto and Bolssoni, Gabriela
year	2021
title	Open-Source Social Housing Architecture: Wikihouse “Sr. Manoel”
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. 91–102
summary	This is the first Wikihouse project to be built in a vulnerable community in Brazil. Brazil is a country with a large housing deficit concentrated in large metropolitan regions. The work is the result of an initiative to address part of this demand using the Wikihouse open-source system. The project was developed using the Design Science Research methodology in three stages: conception, prototyping and production of an experiential module on a 1:1 scale. The results demonstrated the need to develop a better structured design ecology to make the Wikihouse system viable in the Brazilian context. This design ecology concerns an integrated network of services that includes project development centers, prototyping spaces, mini-factories for production, pre-assembly and batch organization environments, logistics services, human resource management teams and integration with the community, in addition to registration, documentation and communication.
keywords	Wikihouse, habitaçao de interesse social, projeto de arquitetura, opensource, fabricaçao digital
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	sigradi2021_97
id	sigradi2021_97
authors	Pires, Júlio César Pinheiro, Avalone Neto, Olavo and Cenci, Laline Elisângela
year	2021
title	Color Selection System Based on Linear Regression and ANN
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. 327–338
summary	Color selection is one of several abilities necessary for architectural design. This study presents a web-based JavaScript application capable of foreseeing a color scheme combination that matches a client’s choice pattern based on previous choices made by them. It uses linear regression and Adapted Artificial Neural Network (ANN) for color and shade selection. First, it estimates users’ choice patterns through least mean squares and applies that in the generation of other patterns. It then considers the least square means through a weight factor for the training stage. This study presents the validation of the first process and the correlation between the application’s estimated results and users’ color match expectations. 81.9% of participants found estimated responses to be similar or very similar to the choices they would make; 88% found usage intuitive or very intuitive, and 88.6% agrees the application has some utility to their professional life.
keywords	Cores, regressao linear, sistema de informaçao, análise estatística, moodboard.
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	sigradi2021_287
id	sigradi2021_287
authors	Zauk, Fernando, Luz, Louise, Pires, Janice and Silva, Adriane Borda Almeida da
year	2021
title	(Parametric) Cinematography of Kogan’s Architecture: A Learning Object
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. 713–724
summary	This study describes the development of a learning object to introduce parametric design techniques together with design action. It identifies in Kogan's architecture appropriate design strategies to configure parametric exercises, such as controlling the types of dynamic textures derived from the effects of light and shadows produced by cobogós. An exercise that considers time and movement, references associated with the architect's cinematographic practices. To develop the object, we started with the interpretation of the knowledge structures involved: from knowledge itself (theories and technologies that identify connections between architecture, cinema, and the concept of parametry) to know-how (a visual programming capable of instrumentalizing for the referred control, by means of parametric design techniques). It was about making available and experiencing this structure, in a teaching/learning process, interpreted as a game that allows us to highlight Kogan's purposes in promoting multisensory experiences with the space of architecture.
keywords	representaçao, projeto, Marcio Kogan, cobogó, objeto de aprendizagem, desenho paramétrico
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	cdrf2021_231
id	cdrf2021_231
authors	Andrea Macruz, Ernesto Bueno, Gustavo G. Palma, Jaime Vega, Ricardo A. Palmieri, and Tan Chen Wu
year	2021
title	Measuring Human Perception of Biophilically-Driven Design with Facial Micro-expressions Analysis and EEG Biosensor
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_22
summary	This paper investigates the role technology and neuroscience play in aiding the design process and making meaningful connections between people and nature. Using two workshops as a vehicle, the team introduced advanced technologies and Quantified Self practices that allowed people to use neural data and pattern recognition as feedback for the design process. The objective is to find clues to natural elements of human perception that can inform the design to meet goals for well-being. A pattern network of geometric shapes that achieve a higher level of monitored meditation levels and point toward a positive emotional valence is proposed. By referencing biological forms found in nature, the workshops utilized an algorithmic process that explored how nature can influence architecture. To measure the impact, the team used FaceOSC for capture and an Artificial Neural Network for micro-expression recognition, and a MindWave sensor manufactured by NeuroSky, which documented the human response further. The methodology allowed us to establish a boundary logic, ranking geometric shapes that suggested positive emotions and a higher level of monitored meditation levels. The results pointed us to a deeper level of understanding relative to geometric shapes in design. They indicate a new way to predict how well-being factors can clarify and rationalize a more intuitive design process inspired by nature.
series	cdrf
email
last changed	2022/09/29 07:53

_id	ijac202119106
id	ijac202119106
authors	Del Campo, Matias; Alexandra Carlson, and Sandra Manninger
year	2021
title	Towards Hallucinating Machines - Designing with Computational Vision
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 1, 88–103
summary	There are particular similarities in how machines learn about the nature of their environment, and how humans learn to process visual stimuli. Machine Learning (ML), more specifically Deep Neural network algorithms rely on expansive image databases and various training methods (supervised, unsupervised) to “make sense” out of the content of an image. Take for example how students of architecture learn to differentiate various architectural styles. Whether this be to differentiate between Gothic, Baroque or Modern Architecture, students are exposed to hundreds, or even thousands of images of the respective styles, while being trained by faculty to be able to differentiate between those styles. A reversal of the process, striving to produce imagery, instead of reading it and understanding its content, allows machine vision techniques to be utilized as a design methodology that profoundly interrogates aspects of agency and authorship in the presence of Artificial Intelligence in architecture design. This notion forms part of a larger conversation on the nature of human ingenuity operating within a posthuman design ecology. The inherent ability of Neural Networks to process large databases opens up the opportunity to sift through the enormous repositories of imagery generated by the architecture discipline through the ages in order to find novel and bespoke solutions to architectural problems. This article strives to demystify the romantic idea of individual artistic design choices in architecture by providing a glimpse under the hood of the inner workings of Neural Network processes, and thus the extent of their ability to inform architectural design.The approach takes cues from the language and methods employed by experts in Deep Learning such as Hallucinations, Dreaming, Style Transfer and Vision. The presented approach is the base for an in-depth exploration of its meaning as a cultural technique within the discipline. Culture in the extent of this article pertains to ideas such as the differentiation between symbolic and material cultures, in which symbols are defined as the common denominator of a specific group of people.1 The understanding and exchange of symbolic values is inherently connected to language and code, which ultimately form the ingrained texture of any form of coded environment, including the coded structure of Neural Networks.A first proof of concept project was devised by the authors in the form of the Robot Garden. What makes the Robot Garden a distinctively novel project is the motion from a purely two dimensional approach to designing with the aid of Neural Networks, to the exploration of 2D to 3D Neural Style Transfer methods in the design process.
keywords	Artificial intelligence, design agency, neural networks, machine learning, machine vision
series	journal
email
last changed	2021/06/03 23:29

_id	caadria2021_130
id	caadria2021_130
authors	Han, Yoojin and Lee, Hyunsoo
year	2021
title	Exploring the Key Attributes of Lifestyle Hotels: A Content Analysis of User-Created Content on Instagram
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. 71-80
doi	https://doi.org/10.52842/conf.caadria.2021.1.071
summary	This study aims to investigate the key attributes of lifestyle hotels by analyzing user-created content on Instagram, an image-based social network service. In an era of uncertainty in the tourism and hospitality industry, it is inevitable that hotels must create a competitive identity. However, even with the significant growth of the lifestyle hotel segment, the concept of a lifestyle hotel is still vague. Therefore, to explore how to define, perceive, and interpret lifestyle hotels and to suggest their crucial attributes, this paper examines user-created content on Instagram. The data from 20,886 Instagram posts related to lifestyle hotels, including 2,209 locations, 43,586 hashtags, and 20,866 images, were analyzed using Vision AI, a social network analysis method and computer vision technology. The results of this study demonstrated that lifestyle hotels are perceived as design-focused branded hotels that represent the urban lifestyle and share both vacation and urban activities. Furthermore, the results reflected one of the latest hospitality trends-a holiday in an urban setting in addition to the primary purpose of traveling. Finally, this research suggests broader uses of big data and deep learning for analyzing how a place is consumed in a geospatial context.
keywords	Lifestyle Hotel; Hospitality Experiences; User-Created Content; Social Network Analysis; Vision AI
series	CAADRIA
email
last changed	2022/06/07 07:50

_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_166
id	sigradi2021_166
authors	Vivanco, Tomas, Valencia, Antonia and Yuan, Philip
year	2021
title	Methodological Implementation of Stylegans Algorithms and Its Change of Paradigm in the Education, Practice and Role of Designers
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. 55–66
summary	The integration of Artificial Intelligence algorithms into computational design processes promote a human-machine collaboration, transforming the role of conventional designers into meta-designer as a product of this collaboration. Specifically, StyleGAN's algorithms offer a novel approach to experimenting with shapes from previously designed images of products or objects. This article presents the application of a methodology for image experimentation to designers without previous knowledge of computation and programming. Each of the steps was developed through different cases for different speculative object production, using artificial intelligence algorithms, and reflecting - in an applied way - the designer's role as curator and co- creator of the creative process in conjunction with computing.
keywords	Stylegan, design methods, design education, artificial intelligence.
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	ecaade2021_159
id	ecaade2021_159
authors	Yazicioglu, Gülin and Gürsel Dino, Ipek
year	2021
title	From Streetscape to Data - Semantic segmentation for the prediction of outdoor thermal comfort
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. 555-562
doi	https://doi.org/10.52842/conf.ecaade.2021.1.555
summary	In recent years, the increasing pace of urbanization is expected to increase the temperatures in urban contexts and amplify the Urban Heat Island effect. This phenomenon has a negative impact on the urbanites' thermal comfort in outdoor spaces. Modeling and simulation-based approaches can precisely calculate outdoor thermal comfort; however, they are labor-intensive and high in computational cost. This difficulty might discourage decision-makers to consider outdoor thermal comfort conditions, which can affect their strategies at the beginning stage of design. This paper aims to propose a statistical model that can predict outdoor comfort using semantic segmentation of 2D street view images. Firstly, 78 panoramic street images of selected three streets in Istanbul are used to calculate the specific object classes that have an influence on outdoor temperature using semantic segmentation. Following, the streets' outdoor thermal comfort is calculated in Ladybug/Grasshopper. Lastly, two multi-variate regression models are built using the percentages of these object classes in each image and outdoor thermal comfort in given locations on the streets. Initial results show that the proposed regression models can predict UTCI with R2=0.78 and R2=0.80, indicating the semantic segmentation can support the calculation of outdoor comfort.
keywords	multivariate linear regression model; semantic segmentation; universal thermal climate index (UTCI)
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2021_167
id	ecaade2021_167
authors	Zhu, Zhelun, Coraglia, Ugo Maria, Simeone, Davide and Fioravanti, Antonio
year	2021
title	Spaces Identity Evaluation aNd Assignment - SIENA - A duck typing approach for automatic recognition and semantic enrichment of architectural spaces
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. 341-350
doi	https://doi.org/10.52842/conf.ecaade.2021.2.341
summary	This paper presents the development of SIENA - Space Identity Evaluation aNd Assignment - based on duck typing for automatic recognition and semantic enrichment of the architectural spaces. This method is known in computer science as a form of abductive reasoning and leverages on the observable features of an object in order to establish its recognition. As result, the spatial identity is object-oriented and can be dynamically defined. In this research, the duck typing approach has been achieved with the support of BIM methodology and graph database. The former allows information-based modeling of an architectural project while the latter makes possible the representation of the knowledge along with their relationships. Consequently, this research may have many possible applications, especially as a valid design support tool in the very first design stages. Furthermore, an efficient spatial identity detection could contribute to the development of further human-machine interactions and therefore a possible optimization of the design process.
keywords	Semantics; Graph database; Duck typing; Space identification
series	eCAADe
email
last changed	2022/06/07 07:57

_id	sigradi2021_50
id	sigradi2021_50
authors	Albuquerque, Dilson and Andrade, Max
year	2021
title	The Impacts of Collaboration and Cordination of Architectural and Engineering Projects Developed with BIM in Reducing Design Interferences
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. 783–794
summary	This paper addresses the importance and development of cultural transformations involving the design process in architecture and the advent of Building Information Modeling (BIM) in civil construction activities and how its implementation in a coordinated, collaborative and interoperable way contributes to a diagnosis of Clash Detection between diferentes design projects, before building construction, saving excessive costs and rework. Taking as its main reference the BIM Maturity Matrix of Succar (2009), the proposed BIM Project Integration Maturity Matrix contributes to the awareness of bringing designers and builders closer to design activities, to encourage the integration of design processes involving the building, to consolidate an environment of ease of communication between participants, the organization of documentation and, above all, prioritize the compatibility between projects to avoid conflicts, excess costs and rework, resulting in a higher quality of the final project.
keywords	Coordenaçao de projetos, detecçao de interferencias, Building Information Modeling, matriz de avaliaçao, projeto integrado
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	sigradi2021_302
id	sigradi2021_302
authors	Bueno, Ernesto, Reis Balsini, André and Verde Zein, Ruth
year	2021
title	Analysis by Algorithmic Modeling of Historiographical Data on Modern and Contemporary Brazilian Architecture
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. 737–748
summary	Are historiographic diagrams valid instruments for gauging the main constituent aspects of historiographic documentation of a body of architectural production? The paper aims to discuss the results obtained by algorithmic modeling and three-dimensional visualization of historiographic data. The analysis method proposes a diagrammatic approach to the research object, established from the fundamentals originally described by Zein (2020). The diagrams were created using the algorithmic modeling software Grasshopper, which allowed us to combine a precise recording of data with an original approach to its interpretation. From the data collected, Cartesian coordinates were established for the generation of curves and interpolation surfaces representative of the computed aspects of certain historiographic narratives. With wide application possibilities, the resulting algorithmic diagrams establish a new model for data analysis and visualization, which stands as a consistent alternative to other more commonly used digital bibliometric tools.
keywords	Análise de dados, Big Data, Visualizaçao de dados, Historiografia, Arquitetura moderna brasileira
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	sigradi2023_16
id	sigradi2023_16
authors	Carline Andrade Bastos, Bruno, Pereira Barcelos Ribeiro, Letícia, Celeste Santana Cunha, Aura, Monteiro Xavier de Lima, Mariana and Ribeiro Cardoso, Daniel
year	2023
title	Artificial Intelligence Applied to Ideation in Design
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 1325–1336
summary	This paper is based on two main concepts: Concept Design and Artificial Intelligence (A.I.). According to Leach (2021), people are surrounded by A.I. in various aspects of daily life. This circumstance highlights the importance of creative professionals to interpret A.I. as a Design tool. The objective of this paper is to evaluate how A.I. can be used in early stages of the ideation process for the development of an artifact. The methodological framework is exploratory-descriptive and was developed through a case study. The practical contribution is to exemplify the simultaneous use of AI and Design tools in a simulation of the creative phase of a furniture project, this result was diagrammed to represent a systematization of where each tool fits into the creative process. The theoretical contribution is to add to the debate around this subject.
keywords	Artificial intelligence, Concept Design, Creative processes, Design Methods, Ideation
series	SIGraDi
email
last changed	2024/03/08 14:08

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

_id	sigradi2021_93
id	sigradi2021_93
authors	Deon, Luisa, Isele, Priscila, Arena, Alana and Mussi, Andrea
year	2021
title	Codesign and Digital Fabrication: Applications in the Project Process with Visually Impaired People and Children
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. 981–992
summary	The Co-design method has great relevance in the inclusion of different classes of users in the Design Process (DP), such as Visually Impaired People (PwDS) and children. This work indicates results of three Co-design dynamics. Focus Group, guided tour, semi-structured interviews, questionnaires and workshops were carried out, as strategies for the inclusion of different users in the DP. The process of designing an inclusive signage board for PwDS is presented. Next, the project of inclusive playgrounds for visually impaired children. Finally, an activity carried out with basic education students, combining new technologies in the child's learning process. Participants were encouraged to express their knowledge through different tools that adapted to their reality. The results show the importance of including different methods, tools and resources to support the DP. In addition, Digital Fabrication and Prototyping are techniques that enhance Co-design, as they act as congratulators for communication between the designer and users.
keywords	Codesign, Fabricaçao Digital, Inclusao, Processo de Projeto. Projeto Colaborativo.
series	SIGraDi
email
last changed	2022/05/23 12:11

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

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

_id	sigradi2023_476
id	sigradi2023_476
authors	Ena, Valeria and Ferreira Magalhaes, Alex
year	2023
title	Ruling the Urban Block: a Discussion over Rio de Janeiro's New Master Plan Proposal Parameters.
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 373–384
summary	The paper aims to analyse the parameters for dimensioning the urban block in the context of the ongoing debate over Rio de Janeiro's new Master Plan (PLC N°44/2021). The analysis focuses on three main points: (1) the definition of the block, (2) the discrepancies found in this regard in the land parcelling system, and (3) the limitations that gated communities impose on the parameterisation of the block. The paper briefly relates the role of the master plan in Brazilian urban policy. Next, it points out the arguments that emerged during the public hearings over the new proposed master plan regarding block sizing. Then, it analyses Rio's urban law framework and the literature regarding the city's road network, cul-de-sac structures and gated communities, supported by the blocks and the streets georeferenced maps available at the Rio's Municipality and the Open Street Maps platform. Finally, it discusses the analysis outcomes with the arguments that emerged during the public hearings regarding block sizing.
keywords	Parametric Design, City parameters, Gated communities, Cul-de-sac, Street continuity
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	sigradi2021_162
id	sigradi2021_162
authors	Feitoza de Gois, Aline, Monteiro dos Santos, Marcela and Quezado Costa Lima, Mariana
year	2021
title	Information Design and Land Regularization: The Optimization Processes of Blueprints and Descriptive Memorials on the SIG Platform
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. 877–887
summary	Among many legal processes and political issues that hinder the Land Regularization of informal urban settlements, the delay in the production of technical documents (blueprints and descriptive memorials) and the number of errors in the systematization of information stand out. Thus, this work presents an information design methodology, aiming to optimize the documentation process through Geographic Information Systems (GIS). As a result, there was an average reduction in the production time of blueprints and memorials when compared to previous experiences of standard documentation. Errors that were still persistent were found exactly in processes that were not yet automated and needed a certain degree of mechanization. Therefore, even though the legal and political challenges seem insurmountable and need to be on the agenda, it is important to project possibilities for the technical barriers to the regularization of informal settlements, to which information design can contribute.
keywords	Regularizaçao Fundiária, Modelagem da Informaçao da Cidade, Segurança da posse, Sistemas de Informaçao Geográfica.
series	SIGraDi
email
last changed	2022/05/23 12:11

For more results click below: