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 775

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

_id	ecaade2023_10
id	ecaade2023_10
authors	Sepúlveda, Abel, Eslamirad, Nasim and De Luca, Francesco
year	2023
title	Machine Learning Approach versus Prediction Formulas to Design Healthy Dwellings in a Cold Climate
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 359–368
doi	https://doi.org/10.52842/conf.ecaade.2023.2.359
summary	This paper presents a study about the prediction accuracy of daylight provision and overheating levels in dwellings when considering different methods (machine learning vs prediction formulas), training, and validation data sets. An existing high-rise building located in Tallinn, Estonia was considered to compare the best ML predictive method with novel prediction formulas. The quantification of daylight provision was conducted according to the European daylight standard EN 17037:2018 (based on minimum Daylight Factor (minDF)) and overheating level in terms of the degree-hour (DH) metric included in local regulations. The features included in the dataset are the minDF and DH values related to different combinations of design parameters: window-to-floor ratio, level of obstruction, g-value, and visible transmittance of the glazing system. Different training and validation data sets were obtained from a main data set of 5120 minDF values and 40960 DH values obtained through simulation with Radiance and EnergyPlus, respectively. For each combination of training and validation dataset, the accuracy of the ML model was quantified and compared with the accuracy of the prediction formulas. According to our results, the ML model could provide more accurate minDF/DH predictions than by using the prediction formulas for the same design parameters. However, the amount of room combinations needed to train the machine-learning model is larger than for the calibration of the prediction formulas. The paper discuss in detail the method to use in practice, depending on time and accuracy concerns.
keywords	Optimization, Daylight, Thermal Comfort, Overheating, Machine Learning, Predictive Model, Dwellings, Cold Climates
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_54
id	ecaade2023_54
authors	Abdulmajeed, Abdulwahab, Agkathidis, Asterios, Dounas, Theo and Lombardi, Davide
year	2023
title	Mass-customisation of dwellings in the Middle East:developing a design-to-fabrication framework to resolve the housing crisis in Saudi Arabia
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 157–164
doi	https://doi.org/10.52842/conf.ecaade.2023.2.157
summary	The Saudi government is taking the initiative to modernise the country and address critical challenges. One of its primary goals is to relieve the housing deficit. One of the challenges in supplying the houses is that potential inhabitants have denied and refused to accept them due to their design failing to meet their demands. Furthermore, the government suffers from providing high-quality housing in line with people’s needs because only a few enterprises can meet the client’s needs, but only at the price of lengthy planning and building times, in addition to increased construction expenses. This research aims to propose a mass customisation design-to-fabrication workflow, which targets environmental optimisation, reduction of construction time and reduced cost and incorporates client involvement. Our research method includes conducting a survey with Saudi Arabian architecture firms to collect data about contemporary clients’ needs, analysing and reviewing mass-customisation tools & techniques, developing a bespoke algorithm capable of mass-customising housing and evaluating the algorithm through design experiments. Our findings present the advantages and challenges of our tool as well as a shape grammar of mass customised floor plan solutions.
keywords	Mass Customisation, Parametric Design, Housing Design
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_14
id	ecaade2023_14
authors	Karoji, Gen
year	2023
title	A Data-Oriented Optimization Framework
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 127–136
doi	https://doi.org/10.52842/conf.ecaade.2023.2.127
summary	Design optimization using the Multi-Objective Evolutionary Algorithm (MOEA) has still been studied, progressed well, and used to improve building performance. Besides, floor plan generation that is the problem of fitting several rooms into an outline given beforehand has recently been studied well using machine learning models. Although the building performance and a floor plan intimately relate, they are rarely combined in one optimization framework. A separation of these problems often forces users to manually explore accurate floor plans in a solution space or limit optimizing the building performance following certain machine learning methods and its dataset. We mainly focused on these issues and developed a custom-made model that contains association rule mining and the cosine similarity formula extracted from machine learning methods. This model of lazy learning is added to an MOEA-based optimization framework and outputs the total cosine similarity between each generated floor plan and the referred plans dynamically selected from our dataset, and the framework maximizes it. We applied this framework to a case study on generating eco-conscious office building designs that will enable them to convert easily in the future. This paper elaborates on how to create a dataset and formulation for optimization, and we emphasize the plausibility of floor plan generation. Finally, we demonstrated the efficiency of the framework by comparing the performance indicators of optimization.
keywords	Floor Plan Generation, Association Rule Mining, Lazy Learning, Design Optimization, Resilient Design
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_60
id	ecaade2023_60
authors	Mostafavi, Fatemeh and Khademi, Seyran
year	2023
title	Micro-Climate Building Context Visualization
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 9–18
doi	https://doi.org/10.52842/conf.ecaade.2023.2.009
summary	Residential buildings are responsible for a considerable share of energy consumption and carbon emission. To decarbonize by 2050, as agreed in the Paris Climate Accord, immediate action for lowering the environmental impact of the building sector is needed. Environmental building design is a promising path, particularly during the early-stage design when design decisions are more impactful and long-lasting. One of the initial steps in the building design process is site assessment, during which the building context and environmental factors are to be evaluated. The surrounding environment plays a critical role in the building's energy performance and the thermal, visual, and acoustic comfort of its occupants. We choose quantitative approaches to study the complexity of the environmental design with respect to the building context by analyzing environmental cues embedded in architectural drawings that have been given less attention in previous studies. Nevertheless, disclosing site-specific geolocation data of buildings, more specifically residential type, is often challenging due to privacy issues. Therefore, there is a lack of context-related metadata in the current architectural datasets. Whereas simulation data are more available and provide a wealth of contextual information, however, it is less appealing for architects to interpret design patterns from extensive simulation figures. This research focuses on developing an interpretable visualization of the building’s micro-climate context from environmental simulation data without direct access to the geolocation of the site. The environmental context visualization is created from daylight, view, and noise from 3088 multifamily housing presented in the Swiss Buildings data set, merely based on available simulation data. The presented pipeline in this study facilitates the employment of existing simulation data in the built environment datasets while circumventing the concerns associated with geolocation data exposure. Further, the generated visualizations may be used to develop computer vision models for environmental assessments of building layout design.
keywords	Building Context, Environmental Design, Data Visualization, Big Data, Decarbonizing
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_234
id	caadria2023_234
authors	Chundeli, Faiz Ahmed and Berger, Tania
year	2023
title	Thermal Performance Evaluation of Low-Income Housing Units Using Numerical Simulation
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 645–654
doi	https://doi.org/10.52842/conf.caadria.2023.1.645
summary	The thermal performance of buildings is measured as heat energy transfer between the buildings and the surrounding environment, and there are several heat exchange possibilities. This paper presents the thermal performance of 12 non-air-conditioned low-income single dwellings in warm-humid climates. The Building and material characteristics of the dwellings, including field measurements of the 12 cases, were meticulously documented through a primary survey. The critical indicator for assessing and evaluating the performance of the dwelling unit was hourly simulated indoor temperature data for an entire year. Further, potential planning and design components, viz. building orientation, roof and wall insulation, window size, property & locations, clerestory window, increased floor-to-ceiling height, site setback, and roof profile, were iterated to improve the thermal performance of low-income dwellings. Indoor temperatures as high as 45.9 C were recorded, the mean indoor temperature for the summer months (March-July) was over 34.64 C, and it was always higher than 30 C for the rest of the month. The findings show that the inhabitants are subjected to temperatures exceeding 34 degrees Celsius for more than half of the year. The paper concludes with some suggested design measures to improve the thermal performance of low-income houses. The study also emphasizes the importance of refined early design phase assessment and decision-making to improve the indoor thermal environment.
keywords	Thermal performance, low-income housing, building simulation, heatwaves, natural ventilation
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ecaade2023_204
id	ecaade2023_204
authors	Lacroix, Igor, Güzelci, Orkan Zeynel and Sousa, José Pedro
year	2023
title	Evolutive Dataset for Social Housing Design Projects through Artificial Intelligence: From pixel to BIM through deep learning
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 629–638
doi	https://doi.org/10.52842/conf.ecaade.2023.2.629
summary	Establishing an evolutive dataset for architectural rationalization of social housing is technically achievable through artificial intelligence based on deep learning (DL). However, concerning the sensitive quality of social housing, the application of such technology needs to preserve the human factor and relate ethically to architectural design. A reference on this subject is historic Portuguese research from the 1960s and the 1970s. By then, pioneering research at the National Laboratory of Civil Engineering (LNEC), based in Lisbon, explored early computing methods to aid the design process by considering deontological concerns. The authors studied these works to refactor those goals and concerns of technological application and sociological interaction with current digital technologies. When digitizing their processes of creating architectural design instruments for social housing a problem emerged with parsing a dataset of floor plans and using it to generate building information models. Thus, a DL process was explored to achieve an evolutive dataset in the most automated way at the architectural level. The paper presents the implementation of a DL process that recognizes floor plans of social housing and consequently enables the development of an instrument for direct architectural rationalization.
keywords	Artificial Intelligence, Machine Learning, Deep Learning, BIM, Social Housing, Evolutive Dataset
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_299
id	sigradi2023_299
authors	Mussi, Andrea, Souza, Helena and Yabar, Ruth
year	2023
title	Co-Design Between 21st Century Designers and People with Visual Impairment: The Building Plan of The New Passofundense Blind Association’s Headquarter
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. 1195–1206
summary	This paper relates the co-design process of a building design with visually impaired people. Using participatory methods, members of an association for visually impaired people could participate actively in the conception design of the future Association headquarters. Through digital fabrication, floor plan representations accessible to blind people were made to establish a common language between visually impaired people and designers. The research, which aims to promote innovation in assistive technologies through digital fabrication, highlights the maturation of the tactile model as a communication tool in the building design process and demonstrates the creation of an inclusive approach in architecture processes and products.
keywords	Co-design, Design Building, Visual Impairment, Inclusive Design, Tactile Model.
series	SIGraDi
email
last changed	2024/03/08 14:08

_id	ascaad2023_125
id	ascaad2023_125
authors	Shata, Dina; Omrani, Sara; Drogemuller, Robin; Denman, Simon; Wagdy, Ayman
year	2023
title	Segmented Rooftop Dataset Generation: A Simplified Approach for Harnessing Solar Power Potential Using Aerial Imagery and Point Cloud Data
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 134-153.
summary	With rising global energy demands and climate change concerns, solar energy has gained traction as a sustainable source. However, optimal utilization of solar systems relies on accurately determining rooftop solar potential. This research presents a simplified methodology to generate a comprehensive dataset of segmented rooftops using publicly available aerial imagery and light detection and ranging (LiDAR) point cloud data. The primary objective is to enable precise prediction of solar photovoltaic (PV) capacity on residential rooftops by extracting key geometric features. The proposed approach first preprocesses raw LiDAR data to isolate building points and generates 3D mesh models of rooftops. A mesh analysis technique computes surface normal and tilt angles, stored as RGB images. Masks derived from the 3D meshes are combined with high-resolution aerial photos to extract cropped rooftop image segments. This overcomes the limitations of manually labelling imagery or relying on scarce 3D city models. The resulting dataset provides critical training and validation inputs for developing machine learning models to assess rooftop solar potential. An initial sample dataset of over 1100 residential rooftops in Brisbane, Australia was created to demonstrate the methodology's effectiveness. The workflow is structured, scalable and replicable, facilitating expansion across larger regions to generate big datasets encompassing diverse rooftop configurations. Overall, this research presents an efficient automated solution to harness essential dataset for training Deep Learning models. It holds significant potential to drive solar PV prediction, enabling the optimization of renewable energy systems and progressing sustainability goals.
series	ASCAAD
email
last changed	2024/02/13 14:41

_id	ascaad2023_055
id	ascaad2023_055
authors	Yildiz, Berfin; Çagdaº, Gülen; Zincir, lbrahim
year	2023
title	Deep Architectural Floor Plan Generation: An Approach for Open-Planned Residential Spaces
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 685-705.
summary	This research investigates the collaborative potential of artificial intelligence and deep learning in architectural design, focusing on comprehending and synthesizing the complex relationships within architectural floor plans. The primary question addressed is whether deep learning algorithms can effectively generate residential floor plans characterized by open-planned architectural spaces. To address this, the study introduces a novel model employing generative adversarial networks (GANs) to create open-planned layouts within residential floor plans. Open-planned spaces refers to a design approach in which interior spaces within a structure are intentionally devoid of traditional partitioning elements such as walls and doors. The layout typically features interconnected and visually continuous spaces that flow seamlessly from one area to another. The research contributes by addressing a gap in the literature through the exploration of functional space differentiations within residences characterized by open plan arrangement without walls as a separating element. Furthermore, the study extends this investigation by applying the proposed methodology to angular and circular plans as well as orthogonal plan sets. In the generative model created with GAN, the space functions are defined and labelled with the RGB color codes assigned to them. For the RGB label representation of the open-plan layout, gradient coloring prepared. By using this method, it was investigated whether the generation of the plans was realized with an open-plan structure by examining the gradient generation results. In the generative model, the footprint of the plan is given as an input for the algorithm to produce by adhering to an outer boundary. Accordingly, it is aimed to learn how the network can be arranged within the given boundaries. The Pix2pix method was used for this generative model, which is defined as the problem of obtaining images from images. The model results advance the AI-driven understanding of architectural design by providing architects with an innovative tool to explore open-plan spatial solutions.
series	ASCAAD
email
last changed	2024/02/13 14:34

_id	cdrf2023_305
id	cdrf2023_305
authors	Wang Yueyang, Philip F. Yuan
year	2023
title	A Parametric Approach Towards Carbon Net Zero in Agricultural Planning
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_26
summary	This paper presents a new tool called the Space Data Generator, which is a parametric tool for organizing open spaces in rural areas. It can optimize the layout of buildings, solar panels, and agricultural planting spaces. While architects have been exploring ways to achieve net-zero carbon emissions in building design, it is equally important to attain a feasible carbon-neutral goal in rural areas. This is particularly crucial as 40% of the world’s population resides in rural areas, and transitioning towards a more sustainable and efficient economy can bring about not only moral but also economic benefits through proper management [1]. The Space Date Generator offers a powerful spatial planning approach for optimizing and planning agricultural resources on any given land. This innovative tool utilizes a combination of remote sensing to generate precise maps of the land, providing a comprehensive understanding of its terrain and potential agricultural resources. With this information, farmers and land managers can make informed decisions about crop selection, irrigation, and fertilizer application, among other factors. By using the Space Date Generator, they can optimize the use of available resources and maximize crop yields, ultimately increasing profitability and sustainability in agriculture [2]. Overall, the Space Date Generator is a valuable tool for any farmer or land manager looking to make the most of their land and resources. Its ability to provide detailed and accurate data on the land’s potential agricultural resources can help to streamline decision-making processes and ultimately lead to more efficient and sustainable land use practices. 1. The Space data generator uses the collected site coordinate information, geographical status (including stones, lakes, and water patterns), and the planted plants’ price as input. 2. Divide the site into small squares, then configure enough solar panels in the optimal sunlight area of the site to meet the user’s needs, and then plant crops on the remaining land. 3. The Space data generator will analyze the number of calories a household needs each year as a percentage. If there is a surplus, the excess food can be allocated to generate economic outcomes on the market. The land area at hand will be subdivided based on its sun ratio, which is a relatively straightforward process. However, we are also interested in determining the value of excess vegetation that may grow in the allocated space. In this regard, the Space Data Generator can prove to be a valuable tool, not only for this particular scenario but also in other types of agricultural settings such as those involving a mix of livestock and crops. Additionally, it may be possible to use this tool to calculate the optimal harvesting of various plant species at different points in the seasonal cycle. The Space Date Generator has the potential to offer valuable references for optimizing agricultural schemes. However, it must provide users with completely accurate results. Unfortunately, it currently cannot measure crucial factors such as soil type and moisture level, which are essential for agricultural planning. Despite this limitation, the Space Data Generator is a flexible tool that can be modified as research advances, allowing for more inputs to be added to improve its accuracy. Moreover, the Space Data Generator can provide guidance in various other areas based on the specific needs of the user. For instance, it can offer guidelines for traffic and urban design, among other demands. By leveraging this technology, users can access more precise and relevant information, enhancing their decisionmaking capabilities. As such, the Space Data Generator represents a valuable tool for various industries and sectors.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_452
id	ecaade2023_452
authors	Yin, Haixin, Wei, Jinzi and García del Castillo y López, Jose Luis
year	2023
title	Speedy Façade
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 409–418
doi	https://doi.org/10.52842/conf.ecaade.2023.2.409
summary	AI-assisted urban design software can streamline development processes by focusing on massing studies that satisfy legal provisions, providing high-quality and optimized estimations. However, designer-oriented technical tools for urban and architectural design prevent some stakeholders, such as policymakers and citizens, from participating in the design process, potentially leading to poorly negotiated proposals, delaying their execution, and causing social deadweight loss. This paper presents Speedy Facade, a framework to enable the active participation of all stakeholders, by converting human verbal descriptions into textured 3D building facades inside traversable urban models. Speedy Facade consists of (1.) an interactive user interface for verbal inputs and keyword selections, (2.) an augmented reality environment with projected façade reference images that can be modified by mask projection selections and regenerations, and (3.) an editable three-dimensional model for experience and design development. The paper discusses the implementation approach and contribution to the urban design process of this work and showcases its applications, and prospects for future expansion.
keywords	Machine Learning, Urban Design, Immersive Modeling, Building Façade, Digital 3D Modeling
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_138
id	ecaade2023_138
authors	Crolla, Kristof and Wong, Nichol
year	2023
title	Catenary Wooden Roof Structures: Precedent knowledge for future algorithmic design and construction optimisation
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 611–620
doi	https://doi.org/10.52842/conf.ecaade.2023.1.611
summary	The timber industry is expanding, including construction wood product applications such as glue-laminated wood products (R. Sikkema et al., 2023). To boost further utilisation of engineered wood products in architecture, further development and optimisation of related tectonic systems is required. Integration of digital design technologies in this endeavour presents opportunities for a more performative and spatially diverse architecture production, even in construction contexts typified by limited means and/or resources. This paper reports on historic precedent case study research that informs an ongoing larger study focussing on novel algorithmic methods for the design and production of lightweight, large-span, catenary glulam roof structures. Given their structural operation in full tension, catenary-based roof structures substantially reduce material needs when compared with those relying on straight beams (Wong and Crolla, 2019). Yet, the manufacture of their non-standard geometries typically requires costly bespoke hardware setups, having resulted in recent projects trending away from the more spatially engaging geometric experiments of the second half of the 20th century. The study hypothesis that the evolutionary design optimisation of this tectonic system has the potential to re-open and expand its practically available design solution space. This paper covers the review of a range of built projects employing catenary glulam roof system, starting from seminal historic precedents like the Festival Hall for the Swiss National Exhibition EXPO 1964 (A. Lozeron, Swiss, 1964) and the Wilkhahn Pavilions (Frei Otto, Germany, 1987), to contemporary examples, including the Grandview Heights Aquatic Centre (HCMA Architecture + Design, Canada, 2016). It analysis their structural concept, geometric and spatial complexity, fabrication and assembly protocols, applied construction detailing solutions, and more, with as aim to identify methods, tools, techniques, and construction details that can be taken forward in future research aimed at minimising construction complexity. Findings from this precedent study form the basis for the evolutionary-algorithmic design and construction method development that is part of the larger study. By expanding the tectonic system’s practically applicable architecture design solution space and facilitating architects’ access to a low-tech producible, spatially versatile, lightweight, eco-friendly, wooden roof structure typology, this study contributes to environmentally sustainable building.
keywords	Precedent Studies, Light-weight architecture, Timber shell, Catenary, Algorithmic Optimisation, Glue-laminated timber
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_112
id	ecaade2023_112
authors	Aguilera, Andrea V., Zhang, Yu and Shea, Kristina
year	2023
title	Mobile Augmented Reality for Aided Manual Assembly of Compressed Earth Block Dwellings
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 19–28
doi	https://doi.org/10.52842/conf.ecaade.2023.2.019
summary	This paper investigates how augmented reality (AR) can instruct and assist in assembling an earthen structure consisting of a limited set of geometrically different interlocking blocks. By adapting a visual-inertial object tracking software, to the assembly process of a mortarless, compressed earth block (CEB) dome, the construction site no longer needs physical templates and manuals. This enables the builders to have real-time tracking with visual feedback to actively adjust according to the optical guidance during the course of assembly. Two identical dome structures are built with the same set of earth blocks, one with AR and one without. The results show that using AR can significantly improve construction efficiency for complex, dry-stacked structures as it acts as assembly guidance and provides insight into the limits of the tracking tolerances. Further, this paper discusses the limitations and challenges and can provide an outlook for further research scaling up the production to construct a habitable dwelling. Starting with just a pile of dirt and a mobile phone, the demonstrator exhibits the compatibility of local, sustainable materials and digital, efficient processes.
keywords	Compressed Earth Blocks, Augmented Reality, Interlocking Blocks, Earth Building, Dry-Stack Assembly, Sustainable Construction
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_227
id	ecaade2023_227
authors	Moorhouse, Jon and Freeman, Tim
year	2023
title	Towards a Genome for Zero Carbon Retrofit of UK Housing
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 197–206
doi	https://doi.org/10.52842/conf.ecaade.2023.2.197
summary	The United Kingdom has some of the worst insulated housing stock in Northern Europe. This is in part due to the age of housing in the UK, with over 90% being built before 1990 [McCrone 2017, Piddington 2020]. Moreover, 85% of current UK housing will still be in use in 2050 by which stage their Government are targeting Net Carbon Zero [Eyre 2019]. Domestic energy use accounts for around 25% of UK carbon emissions. The UK will need to retrofit 20 million dwellings in order to meet this target. If this delivery were evenly spread, it would equate to over 2,000 retrofit completions each day. Government-funded initiatives are stimulating the market, with upwards of 60,000 social housing retrofits planned for 2023, but it is clear that a system must be developed to enable the design and implementation of housing-stock improvement at a large scale.This paper charts the 20-year development of a digital approach to the design for low-carbon domestic retrofit by architects Constructive Thinking Studio Limited and thence documents the emergence of a collaborative approach to retrofit patterns on a National scale. The author has led the Research and Development stream of this practice, developing a Building Information Modelling methodology and integrated Energy Modelling techniques to optimise design for housing retrofit [Georgiadou 2019, Ben 2020], and then inform a growing palette of details and a database of validated solutions [Moorhouse 2013] that can grow and be used to predict options for future projects [D’Angelo 2022]. The data is augmented by monitoring energy and environmental performance, enabling a growing body of knowledge that can be aligned with existing big data to simulate the benefits of nationwide stock improvement. The paper outlines incremental case studies and collaborative methods pivotal in developing this work The proposed outcome of the work is a Retrofit Genome that is available at a national level.
keywords	Retrofit, Housing, Zero-Carbon, BIM, Big Data, Design Genome
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_89
id	ecaade2023_89
authors	Ahmadpanah, Hooshiar, Haidar, Adonis and Latifi, Seyed Mostafa
year	2023
title	BIM and Machine Learning (ML) Integration in Design Coordination: Using ML to automate object classification for clash detection
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 619–628
doi	https://doi.org/10.52842/conf.ecaade.2023.2.619
summary	Amongst the countless benefits of BIM, clash detection appears to be one of the most recognized ones. This is due to the automated manner in which clashes can be detected in the design stage in comparison to the cumbersome drawing-based clash detection applied in traditional design coordination. When BIM clash detection software, such as Navisworks or Solibri, is used, thousands of clashes can be detected automatically, and a report is generated containing a list of all the clashes with an image of each clash. In most cases, a large number of irrelevant/ignorable clashes can be found, making it extremely difficult and time-consuming to classify those clashes in order to assign responsibilities to manage those clashes, and more importantly specifying which clashes are relevant and which are not. Therefore, finding an automated machine-enabled method to classify clashes into relevant and irrelevant appears to be indispensable. This paper provides the first step towards this automation by developing a Machine Learning (ML) algorithm capable of recognizing the types of elements from images that are originated from the clash detection report. To achieve this, a Deep Learning (DL) algorithm called ‘YOLO’, that is based on object recognition, is developed, and a set of various images indicating different kinds of clashes are used as the dataset. Using the “Makesense” platform, the images are labeled into different categories to feed the algorithm. The algorithm was able to recognize trusses and beams from the images saved in the data set, which is the first step towards object classification. The paper contributes to the knowledge by, firstly, enabling the clashes to be classified based on images rather than numeric information data, and secondly, by applying the DL algorithm that is used in many author industries in the context of clash detection within a construction project.
keywords	BIM, Clash Detection, Machine Learning (ML), Deep Learning, Image Recognition
series	eCAADe
email
last changed	2023/12/10 10:49

_id	sigradi2023_396
id	sigradi2023_396
authors	Akdogan, Merve, Alaçam, Sema and Töreyin, Behçet Ugur
year	2023
title	A Bayesian Model for Optimizing Thermal Comfort and Indoor Air Quality
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. 349–360
summary	This study focuses on the usage of a probabilistic approach on determining the best course of action in a specific environment within the domain of architecture. More specifically, Bayesian decision theory is applied on a simplified problem of maintaining thermal comfort and air quality. An already existing comprehensive dataset is used and narrowed down for the purpose of the study. Environment measurements (indoor and outdoor temperature, indoor CO2 level and air humidity) are taken as input variables and user preferences (open or closed window) are taken as outputs in order to address the problem as a binary classification problem. The paper can be regarded as a preliminary study on the usage of probabilistic approaches in the discipline of architecture.
keywords	Predictive Modeling, Binary Classification, Bayesian Decision Theory, Occupant-Building Interaction, Thermal Comfort
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	caadria2023_57
id	caadria2023_57
authors	Alva, Pradeep, Mosteiro-Romero, Martin, Pei, Wanyu, Bartolini, Andrea, Yuan, Chao and Stouffs, Rudi
year	2023
title	Bottom-Up Approach for Creating an Urban Digital Twin Platform and Use Cases
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 605–614
doi	https://doi.org/10.52842/conf.caadria.2023.1.605
summary	Smart city initiatives have been a driving force for city-level dataset collection and the development of data-driven applications that benefit effective city management. There is a need to demonstrate use cases for effective city management using the available dataset. Urban Digital Twin (UDT) is a 3D city model that can integrate multi-disciplines and improve systems operability on a digital platform. However, UDTs are developed within organisations, and there is only limited availability of authoritative open 3D datasets to explore the potential of UDT concepts. This paper reports a methodology for creating a UDT platform for visualising and querying city energy data. We demonstrate a bottom-up approach to constructing an integrated 3D city dataset and create a query system for rapid access and navigation of the 3D city dataset through a visualisation platform using Cesium Ion. Various use cases are explored based on the dataset, such as building material stock management, energy demand simulation, electric vehicles (EV) demand and flexibility, and estimation of greenhouse gas (GHG) emissions. These use cases can help decision-makers and stakeholders involved in city planning and management. Furthermore, it provides a guideline for developers willing to create UDT applications for smart city initiatives.
keywords	Energy modelling, City dataset, Urban analytics, Building Stock Management, Decarbonisation
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ecaade2023_51
id	ecaade2023_51
authors	Aman, Jayedi, Kim, Jong Bum and Verniz, Debora
year	2023
title	AI-Integrated Urban Building Energy Simulation: A framework to forecast the morphological impact on daylight availability
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 369–378
doi	https://doi.org/10.52842/conf.ecaade.2023.2.369
summary	The research presents a computational framework to investigate the relationship between urban morphology and environmental performance metrics of buildings. Understanding how buildings interact with their surroundings is crucial in optimizing environmental performance. Current urban building energy simulation methods (UBES) often overlook the complex interaction between urban morphology and environmental performance across a diverse set of attributes, resulting in inaccuracies. The proposed framework integrates machine learning (ML) with physics-based simulations and includes Parametric Building Information Modeling, iterative physics-based simulations, Multi-Objective Optimization, and a graph neural network. The framework leverages the detailed analysis capabilities of physics-based simulations and the data processing strengths of ML to analyze urban morphological attributes. Evaluations indicate that the framework enhances prediction accuracy while considering the influence of urban morphology on environmental performance.
keywords	Urban Morphology, Urban Building Energy Modeling, Graph Neural Networks, Sustainable Urban Development, Environmental Performance, Multi-objective Optimization
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia23_v2_520
id	acadia23_v2_520
authors	Ampanavos, Spyridon; Bernal, Marcelo; Okhoya, Victor
year	2023
title	Daylight ML: A General-Purpose Deep-Learning Surrogate Model for Annual Daylight Distribution
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-0-3]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 520-531.
summary	Building performance simulation, such as daylight evaluation can lead to better quality designs. However, time constraints are currently limiting its use for design exploration. Surrogate modeling can offer drastic speed improvements to simulation processes, but existing models are either project specific or offer limited flexibility to design inputs, while requiring a significant initial investment for their training. This research introduces a method for predicting spatial distribution of annual daylight metrics using a raytrac- ing-based encoding of the inputs, and a deep-learning surrogate model. The method can operate on spaces of any shape. Using synthetic data, surrogate models for Atlanta, Georgia, and Boston, Massachusetts, were trained, and achieved low average errors on the test set for all daylight metrics considered. Furthermore, models trained on simple datasets of rectangular spaces were able to predict accurate results for L-shaped, circular, and courtyard-shaped spaces, and for sensors that had twice the density of the ones in the training set. Overall, the results suggest that trained models can be used to evaluate the daylight quality of any project or design within their respective locations.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:13

_id	sigradi2023_110
id	sigradi2023_110
authors	Bagheriyar, Erfan and Uzun, Can
year	2023
title	Assessment of the Circulation Impact of Furniture in Industrial Buildings through Space Syntax
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. 421–432
summary	This paper explores the impact of furniture and machines on spatial organization and circulation systems in industrial buildings using space syntax analysis. While space syntax research covers various settings, industrial buildings have received limited attention. This study aims to address this gap by examining how machines and furniture influence spatial organization and circulation in two industrial buildings: A Nitrile Glove manufacturing facility and a textile manufacturing factory. The furnished and unfurnished floor plans were analyzed using space syntax software, DepthMapX, with connectivity and agent-based analyses. The results indicate that unfurnished plans have centrally located connectivity values, whereas furnished plans create subspaces with varying connectivity. Agent-based analysis reveals that unfurnished spaces have high density in the center, while furnished spaces distribute density more evenly, resulting in more uniform circulation. This study concludes that industrial building spatial configurations result from a combination of architectural design and the placement of machines and furniture.
keywords	Industrial Building, Space Syntax, Connectivity, Agent-Based Analysis, Furnished-Unfurnished plans
series	SIGraDi
email
last changed	2024/03/08 14:07

For more results click below: