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 604

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

_id	caadria2021_001
id	caadria2021_001
authors	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.)
year	2021
title	CAADRIA 2021: Projections, Volume 2
doi	https://doi.org/10.52842/conf.caadria.2021.2
source	PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, 764 p.
summary	Rapidly evolving technologies are increasingly shaping our societies as well as our understanding of the discipline of architecture. Computational developments in fields such as machine learning and data mining enable the creation of learning networks that involve architects alongside algorithms in developing new understanding. Such networks are increasingly able to observe current social conditions, plan, decide, act on changing scenarios, learn from the consequences of their actions, and recognize patterns out of complex activity networks. While digital technologies have already enabled architecture to transcend static physical boxes, new challenges of the present and visions for the future continue to call for both innovative responses integrating emerging technologies into experimental architectural practice and their critical reflection. In this process, the capability of adapting to complex social and environmental challenges through learning, prototyping and verifying solution proposals in the context of rapidly shifting realities has become a core challenge to the architecture discipline. Supported by advancing technologies, architects and researchers are creating new frameworks for digital workflows that engage with new challenges in a variety of ways. Learning networks that recognize patterns from massive data, rapid prototyping systems that flexibly iterate innovative physical solutions, and adaptive design methods all contribute to a flexible and networked digital architecture that is able to learn from both past and present to evolve towards a promising vision of the future.
series	CAADRIA
last changed	2022/06/07 07:49

_id	caadria2021_000
id	caadria2021_000
authors	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.)
year	2021
title	CAADRIA 2021: Projections, Volume 1
doi	https://doi.org/10.52842/conf.caadria.2021.1
source	PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, 768 p.
summary	Rapidly evolving technologies are increasingly shaping our societies as well as our understanding of the discipline of architecture. Computational developments in fields such as machine learning and data mining enable the creation of learning networks that involve architects alongside algorithms in developing new understanding. Such networks are increasingly able to observe current social conditions, plan, decide, act on changing scenarios, learn from the consequences of their actions, and recognize patterns out of complex activity networks. While digital technologies have already enabled architecture to transcend static physical boxes, new challenges of the present and visions for the future continue to call for both innovative responses integrating emerging technologies into experimental architectural practice and their critical reflection. In this process, the capability of adapting to complex social and environmental challenges through learning, prototyping and verifying solution proposals in the context of rapidly shifting realities has become a core challenge to the architecture discipline. Supported by advancing technologies, architects and researchers are creating new frameworks for digital workflows that engage with new challenges in a variety of ways. Learning networks that recognize patterns from massive data, rapid prototyping systems that flexibly iterate innovative physical solutions, and adaptive design methods all contribute to a flexible and networked digital architecture that is able to learn from both past and present to evolve towards a promising vision of the future.
series	CAADRIA
last changed	2022/06/07 07:49

_id	caadria2021_399
id	caadria2021_399
authors	Alsalman, Osama, Erhan, Halil, Haas, Alyssa, Abuzuraiq, Ahmed M. and Zarei, Maryam
year	2021
title	Design Analytics and Data-Driven Collaboration in Evaluating Alternatives
doi	https://doi.org/10.52842/conf.caadria.2021.2.101
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. 101-110
summary	Evaluation of design ideas is an important task throughout the life cycle of design development in the AEC industry. It involves multiple stakeholders with diverse backgrounds and interests. However, there is limited computational support which through this collaboration is facilitated, in particular for projects that are complex. Current systems are either highly specialized for designers or configured for a particular purpose or design workflow overlooking other stakeholders' needs. We present our approach to motivating participatory and collaborative design decision-making on alternative solutions as early as possible in the design process. The main principle motivating our approach is giving the stakeholders the control over customizing the data presentation interfaces. We introduce our prototype system D-ART as a collection of customizable web interfaces supporting design data form and performance presentation, feedback input, design solutions comparisons, and feedback compiling and presentation. Finally, we started the evaluation of these interfaces through an expert evaluation process which generally reported positive results. Although the results are not conclusive, they hint towards the need for presenting and compiling feedback back to the designers which will be the main point of our future work.
keywords	Design Analytics; Collaboration; Visualizations
series	CAADRIA
email
last changed	2022/06/07 07:54

_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	sigradi2021_312
id	sigradi2021_312
authors	Dickinson, Susannah and Ida, Aletheia
year	2021
title	Dynamic Interscalar Methods for Adaptive Design Futures
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. 41–53
summary	This paper addresses our current environmental and political climate directly, disseminating work from a research-based, upper-level architecture studio located at the border of Mexico and the United States. Dynamic digital tools and methods were developed to connect multiple scales of spatialized data. Additional field tools, including electromagnetic field (EMF) meters, environmental sensors, and micro-photography, enabled real-time dynamics to be combined with photogrammetry, satellite and GIS data. The selected outcomes utilize the methodological framework in different ways. Three presiding significant outcomes demonstrated from this work include: 1) micro-macro scale inquiry through spatio-temporal data collection and fieldwork; 2) parametric digital tools for emergent design optimization linking natural and artificial systems; and 3) human-machine-nature interactions for cultural awareness, participation, and activism. Collectively, these three functions of the methodology shift practice towards an alter-disciplinary logic to enable adaptive design outcomes that are responsive to a range of issues presented through site-specific climate change dynamics.
keywords	Parametric Generative Design, Sustainable Design, Simulation, Bio-Inspired Design, Digital Pedagogy
series	SIGraDi
email
last changed	2022/05/23 12:10

_id	caadria2021_013
id	caadria2021_013
authors	Haeusler, M. Hank, Butler, Andrew, Gardner, Nicole, Sepasgozar, Samad and Pan, Shan
year	2021
title	Wasted ... Again - Or how to understand waste as a data problem and aiming to address the reduction of waste as a computational challenge
doi	https://doi.org/10.52842/conf.caadria.2021.1.371
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. 371-380
summary	The global construction industry is the single largest consumer of materials on the planet. Of that material consumption anywhere between 10-20% will end up in landfills as waste. Currently, there are three approaches to tackle this problem - reduce, reuse, and recycle. Concentrating purely on the challenge of reducing waste this research aims to address the problem of waste in the construction industry by addressing it in the preliminary design stage. It does so by asking the research question if computational design offers opportunities towards lean construction or to achieve Zero Waste by understanding waste as a data management challenge. For our research materials are specified in databases outlining geometrical and quantitative information either in material supplier databases (homepage) or in architecture and construction databases via Revit or Grasshopper. Consequently, one can collect via web scraping, investigate via databases, inspect and compare via Grasshopper and Python these databases to understand if one can transform data into information towards material use and consequently into knowledge on waste production and reduction. This investigation, its proposed hypothesis, methodology, implications, significance, and evaluation are presented in the paper.
keywords	Construction industry; waste reduction; databases; web scraping; computational design
series	CAADRIA
email
last changed	2022/06/07 07:49

_id	ecaade2021_010
id	ecaade2021_010
authors	Huang, Yurong, Butler, Andrew, Gardner, Nicole and Haeusler, M. Hank
year	2021
title	Lost in Translation - Achieving semantic consistency of name-identity in BIM
doi	https://doi.org/10.52842/conf.ecaade.2021.2.009
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. 9-20
summary	Custom room naming in architectural projects can vary considerably depending on the user. Having multiple and diverse names for the same room is particularly problematic for information retrieval processes in BIM-based projects. Current best practice includes either team agreement on naming labels in BIM or manual renaming to align with an office-wide standard. Both remain laborious and flawed and lead to compounding errors. This research explores how an automated naming-standardization workflow can enhance the interoperability of object-based modeling in a BIM environment and make information retrieval more reliable for a project life cycle. This paper presents research on (1) building a custom corpus specialized for architectural terminology to fit into the BIM environment and (2) devising a standard-naming system titled WuzzyNaming to save manual work for BIM users in maintaining room-name consistency. Our presented workflow applied natural language processing (NLP) technique and Fuzzy logic to perform the semantic analysis and automate the BIM room-name standardization.
keywords	Building information modeling; Natural Language Processing; Data interoperability; Naming convention; Fuzzy logic
series	eCAADe
email
last changed	2022/06/07 07:50

_id	acadia21_92
id	acadia21_92
authors	Imai, Nate; Conway, Matthew
year	2021
title	Data Waltz
doi	https://doi.org/10.52842/conf.acadia.2021.092
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. 92-99.
summary	This paper explores the impacts of the Internet of Things (IoT) on the field of interactive architecture and the ways this novel technology enables realignments toward inclusive and critical practices in the design of computational systems across different scales. Specifically, it examines how the integration of IoT in the design of architectural surfaces can encourage interaction between local and remote users and increase accessibility amongst contributors. Beginning with a survey of media facades and the superimposition of architectural surfaces with projected images, the paper outlines a historical relationship between buildings and the public realm through advancements in technology. The paper next reveals ways in which IoT can transform the field of interactive architecture through the documentation and analysis of a project that stages an encounter between local and remote Wikipedia contributors. The installation creates a feedback loop for engaging Wikipedia in real-time, allowing visitors to follow and produce content from their interactions with the gallery’s physical environment. Light, sound, and fabric contextualize the direction and volume of real-time user-generated event data in relation to the gallery’s location, creating an interface that allows participants to dance with dynamic bodies of knowledge. By incorporating IoT with the field of interactive architecture, this project creates a framework for designing computational systems responsive to multiple scales and expanding our understanding of computational publics.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_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	caadria2021_305
id	caadria2021_305
authors	Keshavarzi, Mohammad, Afolabi, Oladapo, Caldas, Luisa, Yang, Allen Y. and Zakhor, Avideh
year	2021
title	GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
doi	https://doi.org/10.52842/conf.caadria.2021.1.091
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. 91-100
summary	The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design and general 3D deep learning tasks.
keywords	Computational Geometry; Generative Modeling; 3D Manipulation; Texture Synthesis
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ijac202119311
id	ijac202119311
authors	Kovacs, Adam Tamas; Micsik, Andras
year	2021
title	BIM quality control based on requirement linked data
source	International Journal of Architectural Computing 2021, Vol. 19 - no. 3, 431–448
summary	This article discusses a BIM Quality Control Ecosystem that is based on Requirement Linked Data in order to create a framework where automated BIM compliance checking methods can be widely used. The meaning of requirements is analyzed in a building project context as a basis for data flow analysis: what are the main types of requirements, how they are handled, and what sources they originate from. A literature review has been conducted to find the present development directions in quality checking, besides a market research on present, already widely used solutions. With the conclusions of these research and modern data management theory, the principles of a holistic approach have been defined for quality checking in the Architecture, Engineering and Construction (AEC) industry. A comparative analysis has been made on current BIM compliance checking solutions according to our review principles. Based on current practice and ongoing research, a state-of-the-art BIM quality control ecosystem is proposed that is open, enables automation, promotes interoperability, and leaves the data governing responsibility at the sources of the requirements. In order to facilitate the flow of requirement and quality data, we propose a model for requirements as Linked Data and provide example for quality checking using Shapes Constraint Language (SHACL). As a result, an opportunity is given for better quality and cheaper BIM design methods to be implemented in the industry.
keywords	Compliance check, quality assurance, quality control, linked data, requirement, BIM
series	journal
email
last changed	2024/04/17 14:29

_id	sigradi2021_197
id	sigradi2021_197
authors	Landenberg, Raquel, Hernandez, Silvia Patricia, Pochini, Olga and Boccolini, Sara M.
year	2021
title	From Digital to Real: Inmotics and Parametricism for Urban Transformation
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. 1005–1016
summary	Our research team develops sustainable and inclusive typologies of micro-architecture. These micro-architectures, aided by cutting-edge technologies, give room to more inclusiveness and functional-ductility. We are convinced that nothing is static, there is not just a single possible future. Because of that, we generate real/virtual architectures that do not respond only to a single type of user, place or use. In this case, we introduce a typological model focused on health and wellness services, currently under development by parametric design. Located in the city of Córdoba, Argentina and placed near public parks (where many citizens practice sports and recreational outdoor activities)). We use energy-efficient local technology to power devices that adapt to local weather; moreover, the equipment provides performance data via audio, visual and tactile outputs, and in adjustable-position devices.
keywords	Palabras clave. Inmótica, inclusividad, microarquitectura, ductilidad, sutentabilidad
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	ecaade2021_290
id	ecaade2021_290
authors	Nicholas, Paul, Chen, Yu, Borpujari, Nihit, Bartov, Nitsan and Refsgaard, Andreas
year	2021
title	A Chained Machine Learning Approach to Motivate Retro-Cladding of Residential Buildings
doi	https://doi.org/10.52842/conf.ecaade.2021.1.055
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. 55-64
summary	This paper investigates how a novel approach to visualisation could help address the challenge of motivating residential retrofitting. Emerging retrofitting research and practice emphasises retro-cladding - the upgrading of the exterior facade of a building - using a modular approach. We present a machine-learning based approach aimed to motivate residential retrofitting through the generation of images and cost/benefit information describing climatically specific additions of external insulation and green roof panels to the façade of a Danish type house. Our approach chains a series of different models together, and implements a method for the controlled navigation of the principle generative styleGAN model. The approach is at a prototypical stage that implements a full workflow but does not include numerical evaluation of model predictions. Our paper details our processes and considerations for the generation of new datasets, the specification and chaining of models, and the linking of climatic data to travel through the latent space of a styleGAN model to visualise and provide a simple cost benefit report for retro-cladding specific to the local climates of five different Danish cities.
keywords	Retrofitting; Machine Learning; Generative Adversarial Networks; Synthetic Datasets
series	eCAADe
type	normal paper
email
last changed	2022/06/07 07:58

_id	ecaade2021_108
id	ecaade2021_108
authors	Romero, Rosaura Noemy Hernandez and Pak, Burak
year	2021
title	Understanding Design Justice in a Bottom-up Housing through Digital Actor-Network Mapping - The case of solidary mobile housing in Brussels
doi	https://doi.org/10.52842/conf.ecaade.2021.1.131
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. 131-140
summary	This paper is a study of an ongoing housing project in Brussels (SMH) which involves bottom-up spatial occupation and 'making' by activists, activist architects, social workers and citizens. The particular focus of this paper is on the critical spatial agency of the citizens, activist-architects and artefacts for enabling architectural design justice (ADJ) in the SMH. Building on the Actor-Network Theory of Latour (2005) we developed an analytic method called Actor Link Mapping and Analysis (ALMA) which involves data collection from a wide range of network actors, the generation of a variety of digital network maps, making computational analysis, followed by workshops and interviews to discuss the findings. ALMA was used to recognize potential assets which are essential for design justice practices and networks. The analysis revealed the limits to community control of design processes and practices as well as limits to the conceptual links surrounding socio-spatial equality, thus limits to design justice in the SMH project. Our research also revealed a plethora of new roles and agencies in bottom-up housing production which were essential to understanding the dynamics and power distribution among the different actors.
keywords	Network Mapping; Network Analysis; Housing; Co-creation; Design Justice; Actor-Network Theory
series	eCAADe
email
last changed	2022/06/07 07:56

_id	acadia21_308
id	acadia21_308
authors	Rossi, Gabriella; Chiujdea, Ruxandra; Colmo, Claudia; El Alami, Chada; Nicholas, Paul; Tamke, Martin; Ramsgaard Thomsen, Mette
year	2021
title	A Material Monitoring Framework
doi	https://doi.org/10.52842/conf.acadia.2021.308
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. 308-317.
summary	Through 3d printing, cellulose-based biopolymers undergo a two-staged hybrid fabrication process, where initial rapid forming is followed by a slower secondary stage of curing. During this curing large quantities of water are evaporated from the material which results in anisotropic deformations. In order to harness the potential of 3d printing biopolymers for architectural applications, it is necessary to understand this extended timeline of material activity and its implications on critical architectural factors related to overall element shrinkage, positional change of joints, and overall assembly tolerance. This paper presents a flexible multi-modal sensing framework for the understanding of complex material behavior of 3d printed cellulose biopolymers during their transient curing process. We report on the building of a Sensor Rig, that interfaces multiple aspects of the curing of our cellulose-slurry print experiments, using a mix of image-based, marker-based, and pin-based protocols for data collection. Our method uses timestamps as a common parameter to interface various modes of curing monitoring through multi-dimensional time slices. In this way, we are able to uncover underlying correlations and affects between the different phenomena occuring during curing. We report on the developed data pipelines enabling the Monitoring Framework and its associated software and hardware implementation. Through graphical Exploratory Data Analysis (EDA) of 3 print experiments, we demonstrate that geometry is the main driver for behavior control. This finding is key to future architectural-scale explorations.
series	ACADIA
type	paper
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
doi	https://doi.org/10.52842/conf.caadria.2021.2.569
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
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	caadria2021_151
id	caadria2021_151
authors	Son, Kihoon and Hyun, Kyung Hoon
year	2021
title	A Framework for Multivariate Data based Floor Plan Retrieval and Generation
doi	https://doi.org/10.52842/conf.caadria.2021.1.281
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. 281-290
summary	Spatial designers explore various design references in the design process. These design references significantly impact the quality of design outcomes and the process. Therefore, it is crucial to provide useful designs through the retrieval or generation process to spatial designers. To do this, a methodology must be developed to identify and quantify the floor plans multivariate design data. Through quantifying various design data, the retrieval and generation process can provide appropriate designs in many ways. This study proposed a new floor plan design framework for retrieval and generation with newly quantified design data. For validation of this framework, we conducted a floor plan retrieval and generation process. Newly quantified design data show usability in both processes. We also compare our framework with previous studies for validation. The comparison results show that our framework utilizes the most diverse design data of the floor plan.
keywords	Design quantification; Multivariate data; Floor plan design; Design retrieval; Design generation
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2021_243
id	caadria2021_243
authors	Stojanovic, Djordje and Vujovic, Milica
year	2021
title	Contactless and context-aware decision making for automated building access systems
doi	https://doi.org/10.52842/conf.caadria.2021.2.193
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. 193-202
summary	In the current context of the COVID-19 pandemic, contactless solutions are becoming increasingly important to making buildings more resilient to the spread of infectious diseases in complementing social distancing and disinfection procedures for disease prevention. The presented study focuses on contactless technology and its role beyond automated interaction with the built environment by examining how it expedited space use and could improve compliance with sanitary norms. We introduce a conceptual framework for the intelligent operation of automated doors in an educational facility, enabled by the network of sensory devices and the application of computational techniques. Our research indicates how versatile data gathered by RFID systems, in conjunction with data extracted from occupancy schedules and sanitary protocols, can be used to enable the intelligent and context-aware application of disease prevention measures. In conclusion, we discuss the benefits of the proposed concept and its role beyond the need for social distancing after the pandemic.
keywords	Human-Building Interaction; Interactive Environments; Responsive Environments; Occupancy Scheduling; Occupational Density
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	cdrf2021_242
id	cdrf2021_242
authors	Waishan Qiu , Wenjing Li, Xun Liu, and Xiaokai Huang
year	2021
title	Subjectively Measured Streetscape Qualities for Shanghai with Large-Scale Application of Computer Vision and Machine Learning
doi	https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_23
source	Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)
summary	Recently, many new studies emerged to apply computer vision (CV) to street view imagery (SVI) dataset to objectively extract the view indices of various streetscape features such as trees to proxy urban scene qualities. However, human perceptions (e.g., imageability) have a subtle relationship to visual elements which cannot be fully captured using view indices. Conversely, subjective measures using survey and interview data explain more human behaviors. However, the effectiveness of integrating subjective measures with SVI dataset has been less discussed. To address this, we integrated crowdsourcing, CV, and machine learning (ML) to subjectively measure four important perceptions suggested by classical urban design theory. We first collected experts’ rating on sample SVIs regarding the four qualities which became the training labels. CV segmentation was applied to SVI samples extracting streetscape view indices as the explanatory variables. We then trained ML models and achieved high accuracy in predicting the scores. We found a strong correlation between predicted complexity score and the density of urban amenities and services Point of Interests (POI), which validates the effectiveness of subjective measures. In addition, to test the generalizability of the proposed framework as well as to inform urban renewal strategies, we compared the measured qualities in Pudong to other five renowned urban cores worldwide. Rather than predicting perceptual scores directly from generic image features using convolution neural network, our approach follows what urban design theory suggested and confirms various streetscape features affecting multi-dimensional human perceptions. Therefore, its result provides more interpretable and actionable implications for policymakers and city planners.
series	cdrf
last changed	2022/09/29 07:53

_id	caadria2021_328
id	caadria2021_328
authors	Wells, Cameron, Schnabel, Marc Aurel, Moleta, Tane and Brown, Andre
year	2021
title	Beauty is in the Eye of the Beholder - Improving the Human-Computer Interface within VRAD by the active and two-way employment of our visual senses
doi	https://doi.org/10.52842/conf.caadria.2021.2.355
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. 355-364
summary	Whether it is via traditional methods with pen and paper or contemporary techniques such as 3D digital modelling and VR drawing, the eye typically plays a mostly passive or consuming role within the design process. By incorporating eye-tracking deeper within these methods, we can begin to discern this technologys possibilities as a method that encompasses the visual experience as an active input. Our research, however, developed the Eye-Tracking Voxel Environment Sculptor (EVES) that incorporates eye-tracking as there design actor. Through EVES we can extend eye-tracking as an active design medium. The eye-tracking data garnered from the designer within EVES is directly utilised as an input within a modelling environment to manipulate and sculpt voxels. In addition to modelling input, eye-tracking is also explored in its usability in the Virtual Reality User Interface. Eye-tracking is implemented within EVES to this extent to test the limits and possibilities of eye-tracking and the Human-Computer Interface within the realm of Virtual Reality Aided Design.
keywords	Human-Computer Interface (HCI); Eye-Tracking; Virtual Reality; modelling; sketching
series	CAADRIA
email
last changed	2022/06/07 07:58

For more results click below: