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 797

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

_id	ecaade2023_71
id	ecaade2023_71
authors	Austern, Guy, Yosifof, Roei and Fisher-Gewirtzman, Dafna
year	2023
title	A Dataset for Training Machine Learning Models to Analyze Urban Visual Spatial Experience
doi	https://doi.org/10.52842/conf.ecaade.2023.2.781
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. 781–790
summary	Previous studies have described the effects of urban attributes such as the Spatial Openness Index (SOI) on pedestrians’ experience. SOI uses 3-dimensional ray casting to quantify the volume of visible space from a single viewpoint. The higher the SOI value, the higher the perceived openness and the lower the perceived density. However, the ray casting simulation on an urban-sized sampling grid is computationally intensive, making this method difficult to use in real-time design tools. Convolutional Neural Networks (CNN), have excellent performance in computer vision in image processing applications. They can be trained to predict the SOI analysis for large urban fabrics in real-time. However, these supervised learning models need a substantial amount of labeled data to train on. For this purpose, we developed a method to generate a large series of height maps and SOI maps of urban fabrics in New York City and encoded them as images using colour information. These height map - SOI analysis image pairs can be used as training data for a CNN to provide rapid, precise visibility simulations on an urban scale.
keywords	Visibility Analysis, Machine Learning, CNN, Perceived Density
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_446
id	caadria2023_446
authors	Guida, George
year	2023
title	Multimodal Architecture: Applications of Language in a Machine Learning Aided Design Process
doi	https://doi.org/10.52842/conf.caadria.2023.2.561
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. 561–570
summary	Recent advances in Natural Language Processing (NLP) and Diffusion Models (DMs) are leading to a significant change in the way architecture is conceived. With capabilities that surpass those of current generative models, it is now possible to produce an unlimited number of high-quality images (Dhariwal and Nichol 2021). This opens up new opportunities for using synthetic images and marks a new phase in the creation of multimodal 3D forms, central to architectural concept design stages. Presented here are three methodologies of generation of meaningful 2D and 3D designs, merging text-to-image diffusion models Stable Diffusion, and DALL-E 2 with computational methods. These allow designers to intuitively navigate through a multimodal feedback loop of information originating from language and aided by artificial intelligence tools. This paper contributes to our understanding of machine-augmented design processes and the importance of intuitive user interfaces (UI) in enabling new dialogues between humans and machines. Through the creation of a prototype of an accessible UI, this exchange of information can empower designers, build trust in these tools, and increase control over the design process.
keywords	Machine Learning, Diffusion Models, Concept Design, Semantics, User Interface, Design Agency
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	sigradi2023_179
id	sigradi2023_179
authors	He, Mingyi, Su, Zixin, Xie, Yantong and Tu, Han
year	2023
title	Linguistic Landscape Research on the Relationship of Urban Language and Commerce Based on Large-scale Street View Images
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. 1737–1748
summary	Urban linguistic landscape studies examine visible written languages in urban areas, revealing socio-economic information, such as the place identity of minority groups and the localization processes of exotic language varieties. However, studies mainly utilize qualitative analysis or small-scale image acquisition without integrating socioeconomic quantitative analysis. Our research aims to expand the quantitative indicators of linguistic landscape in city-wide scale to explore the relationship between detailed quantitative text analysis and consumer prices in spatially differentiated and temporally controlled urban street view images. We examine such correlation through street view images scrapping of historical Baidu Street View images, semantic segmentation machine learning tools, and Optical Character Recognition. Our study reveals a negative correlation between linguistic landscape indicators in street signage and consumption levels. This research provides quantitative methods for large-scale and repeatable study of linguistic landscape, introducing a novel perspective on linguistic landscape evidence for further urban economic development and urban segmentation.
keywords	Cultural landscapes and new technologies, Linguistic landscape, Machine learning, Urban economy, Street view
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	ijac202321108
id	ijac202321108
authors	Newton, David William
year	2023
title	Identifying correlations between depression and urban morphology through generative deep learning
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 1, pp. 136–157
summary	Mental health disorders, such as depression, have been estimated to account for the largest proportion of global disease burden. Existing research has established significant correlations between the built environment and mental health. This research, however, has relied on traditional statistical methods that are not amenable to working with large remote sensing image-based datasets. This research addresses this challenge and contributes new knowledge and a novel method for using generative deep learning for urban analysis and synthesis tasks involving mental health. The research specifically investigates three mental state measures: depression, anxiety, and the perception of safety. The experimental results demonstrate the efficacy of the process—providing a new method to find correlational signals, while providing insights on the correlation between specific urban design features and the incidence of depression.
keywords	generative deep learning, depression, urban planning, generative adversarial network
series	journal
last changed	2024/04/17 14:30

_id	architectural_intelligence2023_5
id	architectural_intelligence2023_5
authors	Qiaoming Deng, Xiaofeng Li, Yubo Liu & Kai Hu
year	2023
title	Exploration of three-dimensional spatial learning approach based on machine learning–taking Taihu stone as an example
doi	https://doi.org/https://doi.org/10.1007/s44223-023-00023-2
source	Architectural Intelligence Journal
summary	Under the influence of globalization, the transformation of traditional architectural space is vital to the growth of local architecture. As an important spatial element of traditional gardens, Taihu stone has the image qualities of being “thin, wrinkled, leaky and transparent” The “transparency” and “ leaky” of Taihu stone reflect the connectivity and irregularity of Taihu stone’s holes, which are consistent with the contemporary architectural design concepts of fluid space and transparency. Nonetheless, relatively few theoretical studies have been conducted on the spatial analysis and design transformation of Taihu stone. Using machine learning, we attempt to extract the three-dimensional spatial variation pattern of Taihu stone in this paper. This study extracts 3D spatial features for experiments using artificial neural networks (ANN) and generative adversarial networks (GAN). In order to extract 3D spatial variation patterns, the machine learning model learns the variation patterns between adjacent sections. The trained machine learning model is capable of generating a series of spatial sections with the spatial variation pattern of the Taihu stone. The purpose of the experimental results is to compare the performance of various machine learning models for 3D space learning in order to identify a model with superior performance. This paper also presents a novel concept for machine learning to master continuous 3D spatial features.
series	Architectural Intelligence
email
last changed	2025/01/09 15:00

_id	caadria2023_282
id	caadria2023_282
authors	Qin, Bowen and Zheng, Hao
year	2023
title	An Image-Based Machine Learning Method for Urban Features Prediction With Three-Dimensional Building Information
doi	https://doi.org/10.52842/conf.caadria.2023.1.109
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. 109–118
summary	Machine learning has been proven to be a very efficient tool in urban analysis, using models trained with big data. We have seen research that applies a generative adversarial network (GAN) to train models, feeding the street map and visualized urban characteristics to predict certain urban features. However, in most cases, the input map is a two-dimensional (2D) map that only stores the land type data (e.g., building, street, green space), hence reducing building information to only the ground-floor area. The identities of buildings with similar floor areas can be hugely different, which may contribute to the prediction errors in previous machine-learning models. In this research, we emphasize the importance of the use of an image-based neural network to analyze the relationship between urban features and the constructed environment. We compare the model that uses traditional street color maps as the input set, against a new input set with more detailed building data. Once trained, the model with the enhanced input set yields output at a higher level of accuracy in certain areas. We apply the new model framework to three selected urban features predictions: rental price, building energy cost, and food sanitary ratio. A broad range of new research could be conduct with our new framework.
keywords	Artificial Intelligence, Generative adversarial network, Urban features, Building elevation, Open-source data, Prediction
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ascaad2023_134
id	ascaad2023_134
authors	Salman, Huda; Dounas, Theodoros; Clarke, Connor
year	2023
title	Fluency of Creative Ideas in the Digital Age: Exploring Emergent AI Influences on Design Methodology and Visual Thinking in Architectural Education
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. 815-832.
summary	Research has explored the concept of originality in visual thinking and architectural education, using different methods. The new state of Artificial Intelligence (AI) in architectural design represents another shift from traditional modes of architectural design and education, into a more authentic approach to the digital age. An experiment is designed to highlight the originality of this approach in design thinking and its futuristic trends and impact on education and creativity studies. The intent of the study we present here is twofold: one to revisit key design studies of design exploration and secondly to explore students' design activity while interacting with text-to-image diffusion machine learning (ML) generative models such as Midjourney, DALL-E and Stable Diffusion, as these might have the potential to change the way that architectural students approach the concept stages of designing projects and products. In addition, we are interested in how the new shift in interfaces and modes of stimulus will influence the students' design process and perceptions. Participants in the design process are final year students who had spent at least four years in a school of architecture and can be classified as semi-experienced designers. Further within the evaluation also lies a critique of the diffusion ML tools themselves as producers of architectonic images, rather than complete concepts for architecture that encapsulate spatial, formal, structural arrangements of elements.
series	ASCAAD
email
last changed	2024/02/13 14:41

_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_052
id	ascaad2023_052
authors	Yinan, Chen; Jia, Xibei; Tu, Han; Ou, Yiwei; Zhou, Xinren
year	2023
title	City Diversity: How Do Architectural Uses, Ages, and Styles Affect the Public? A Case Study in Manhattan Through Social Media 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. 463-486.
summary	Jane Jacobs proposed that urban diversity yields numerous advantages, encompassing economic and cultural prosperity, heightened individual security, and augmented urban vibrancy. However, what is the specific correlation between city diversity and public sentiment? Does a higher level of diversity always result in a more positive public attitude? Our study endeavors to reassess Jacobs’ theory of city diversity by leveraging urban data from multiple sources. Our research primarily concentrates on two categories of data. The first category pertains to city diversity data, encompassing building uses, building ages, and architectural styles, which were predicted through machine learning tools with image classification. The second category is public sentiment data collected from Twitter. We gathered tweets and measured the levels of positivity, negativity, and neutrality expressed by the public using natural language processing tools. Through spatial distribution analysis and correlation analysis of environmental and social media data, we revealed the relationship between city diversity and public sentiment. The results indicate that higher city diversity correlates with both more positive and negative sentiments among individuals, diminishing their neutral and indifferent attitudes in the Manhattan area. This serves to demonstrate that city diversity can exert a comprehensive influence on public sentiment, thereby validating and enriching Jane Jacobs’ theory. Consequently, we advocate for a more nuanced and discerning approach towards city diversity within the context of contemporary urban agendas.
series	ASCAAD
email
last changed	2024/02/13 14:34

_id	ecaade2023_31
id	ecaade2023_31
authors	Canli, Ilkim, Gursel Dino, Ipek and Kalkan, Sinan
year	2023
title	Useful Daylight Illuminance Prediction Under Data Imbalance in an Urban Context
doi	https://doi.org/10.52842/conf.ecaade.2023.2.599
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. 599–608
summary	Optimal daylight illumination can aid sustainable design by improving occupants’ psychological and physical health, visual and thermal comfort and decreasing electrical lighting energy usage in buildings. However, dense urban areas can result in restricted daylight access in buildings. Therefore, daylight analysis considering surrounding buildings is important for implementing daylighting strategies. Useful Daylight Illuminance (UDI) is a performance metric that can quantify the annual illuminance levels within certain illumination classes (UDIfell-short, UDIsupplementary, UDIautonomous, and UDIexceeded). UDI can be predicted using machine-learning (ML) methods. However, the calculated data is typically unevenly distributed, generally following a power-law distribution, which causes ML models to underperform for UDI classes with less data. Simulations can be utilized to increase the less dispersed data in the dataset; however, at the urban scale, the computational cost of collecting simulation data for daylighting analysis makes it difficult to augment data with simulations. To undertake this challenge, in this study, SMOTE (Synthetic Minority Oversampling Technique) was applied to augment data to increase the prediction performance of the ML model. The results showed that augmenting the data in the classes which are unevenly distributed leads to an increase in ML model prediction performance. This method shows that SMOTE can be used to increase the performance of ML models during UDI estimation at the urban scale.
keywords	Daylight Illumination, Machine Learning Prediction, Useful Daylight Illuminance, Data Imbalance
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_205
id	ecaade2023_205
authors	Meeran, Ahmed and Joyce, Sam
year	2023
title	Rethinking Airport Spatial Analysis and Design: A GAN based data driven approach using latent space exploration on aerial imagery for adaptive airport planning
doi	https://doi.org/10.52842/conf.ecaade.2023.2.501
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. 501–510
summary	Airports require long term planning, balancing estimations of future demand against available airfield land and site constraints. This is becoming more critical with climate change and the transition to sustainable aviation fuelling infrastructure. This paper demonstrates a novel procedure using Satellite Imagery and Generative Learning to aid in the comparative analysis and early-stage airfield design. Our workflow uses a GAN trained on 2000 images of airports transforming them into a high-dimensional latent space capturing the typologies’ large-scale features. Using a process of projection and dimensional-reduction methods we can locate real-world airport images in the generative latent space and vice-versa. With this capability we can perform comparative “neighbour” analysis at scale based on spatial similarity of features like airfield configuration, and surrounding context. Using this low-dimensional 3D ‘airport designs space’ with meaningful markers provided by existing airports allows for ‘what if’ modelling, such as visualizing an airport on a site without one, modifying an existing airport towards another target airport, or exploring changes in terrain, such as due to climate change or urban development. We present this method a new way to undertake case study, site identification and analysis, as well as undertake speculative design powered by typology informed ML generation, which can be applied to any typologies which could use aerial images to categorize them.
keywords	Airport Development, Machine Learning, GAN, High Dimensional Analysis, Parametric Space Exploration, tSNE, Latent Space Exploration, Data Driven Planning
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_281
id	ecaade2023_281
authors	Prokop, Šimon, Kubalík, Jiøí and Kurilla, Lukáš
year	2023
title	Neural Networks for Estimating Wind Pressure on Complex Double-Curved Facades
doi	https://doi.org/10.52842/conf.ecaade.2023.2.639
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. 639–647
summary	Due to their complex geometry, it is challenging to assess wind effects on the freeform, double-curved building facades. The traditional building code EN 1991-1-4 (730035) only accounts for basic shapes such as cubes, spheres, and cylinders. Moreover, even though wind tunnel measurements are considered to be more precise than other methods, they are still limited by the number of measurement points that can be taken. This limitation, combined with the time and resources required for the analysis, can limit the ability to fully capture detailed wind effects on the whole complex freeform shape of the building. In this study, we propose the use of neural network models trained to predict wind pressure on complex double-curved facades. The neural network is a powerful data-driven machine learning technique that can, in theory, learn an approximation of any function from data, making it well-suited for this application. Our approach was empirically evaluated using a set of 31 points measured in the wind tunnel on a 3D printed model in 1:300 scale of the real architectural design of a concert hall in Ostrava. The results of this evaluation demonstrate the effectiveness of our neural network method in estimating wind pressures on complex freeform facades.
keywords	wind pressure, double-curved façade, neural network
series	eCAADe
email
last changed	2023/12/10 10:49

_id	acadia23_v2_596
id	acadia23_v2_596
authors	Ran, Wuwu; Yin, Lu; Yu, Jie
year	2023
title	Machine Learning-driven Comparative Study: Morphological Taxonomy in Screen-Based Building Clusters
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 596-605.
summary	Our framework employs a convolutional autoencoder model to integrate urban morphology data and attribute vectors of screen-based buildings, generating final feature vectors that are subsequently used for clustering and comparative analysis. We carried out empirical testing of our methods using data from the cities of Chongqing and Shanghai in China. This comparative study identifies various categories of screen clusters, and demonstrates the framework’s effectiveness. The primary objective of this research is to elucidate the similarities and differences among screen-based building clusters, aiming to provide architects and urban designers with a more comprehensive understanding of the typological and topological characteristics of augmented space syntax. Through this approach, we hope to contribute to the development of more effective design strategies and policies for the implementation and integration of screen-based building clusters in urban environments.
series	ACADIA
type	paper
email
last changed	2024/12/20 09:13

_id	caadria2023_359
id	caadria2023_359
authors	Wang, Xiao, Tang, Peng and Cai, Chenyi
year	2023
title	Traditional Chinese Village Morphological Feature Extraction and Cluster Analysis Based on Multi-source Data and Machine Learning
doi	https://doi.org/10.52842/conf.caadria.2023.1.179
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. 179–188
summary	This study of traditional village morphology provides a possible entry point for understanding the growth patterns of settlements for sustainable development. This study proposes a hybrid data-driven approach to support quantitative morphological descriptions and to further morphology-related studies using open-source map data and deep learning approaches. We construct a dataset of 6819 traditional villages on the Chinese official list with geometrical, geographic and related no-material information. The images containing village buildings combined with roads or other environments are represented in binary to explore the integrated influence of these elements. The neural network is implemented to quantify the morphological features into feature vectors. After dimension reduction, cluster analysis is conducted by calculating the distance between the feature vectors to reveal five main types of Chinese traditional village patterns. The proposed method considers their overall spatial form and other factors such as size, transportation, graphical structure, and density. At the same time, it explores a framework using machine learning in the conservation and renewal work. And it also shows the possibility of data-driven methods for design and decision making.
keywords	Cluster analysis, traditional village, morphology, multi-source data, machine learning, rural development
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ecaade2023_226
id	ecaade2023_226
authors	Yau, Ho Man, Dounas, Theodoros, Jabi, Wassim and Lombardi, Davide
year	2023
title	Timber joints analysis and design using Shape and Graph Grammar-based Machine Learning approach
doi	https://doi.org/10.52842/conf.ecaade.2023.1.569
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. 569–578
summary	Timber joints had been applied as one of the primary methods across different cultures of building construction. The technique of crafting timber joints uses simple geometry to connect different components without the need of adhesives or fixings. Digitalisation and computational design method provided a new approach to developing complex timber joint connections. By combining this traditional technique with computational design methods, shape, and graph grammar opened new opportunities in reinterpreting timber joint designs. In this paper, we proposed a timber joints’ synthetic dataset preparation using shape grammar and graph grammar for machine learning applications. The research focused on designing a prototype of a shape grammar extraction system and graph extraction system manually and using Topologic in Sverchok, Blender, with a discussion on how to shape grammar applications help to analysis and create a larger database for future machine learning development of this project.
keywords	Shape grammar, Graph grammar, Timber structures, Parametric design, Machine learning
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
doi	https://doi.org/10.52842/conf.ecaade.2023.2.619
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
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	ecaade2023_328
id	ecaade2023_328
authors	Andreou, Alexis, Kontovourkis, Odysseas, Solomou, Solon and Savvides, Andreas
year	2023
title	Rethinking Architectural Design Process using Integrated Parametric Design and Machine Learning Principles
doi	https://doi.org/10.52842/conf.ecaade.2023.2.461
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. 461–470
summary	Artificial Intelligence (AI) has the potential to process vast amounts of subjective and conflicting information in architecture. However, it has mostly been used as a tool for managing information rather than as a means of enhancing the creative design process. This work proposes an innovative way to enhance the architectural design process by incorporating Machine Learning (ML), a type of Artificial Intelligence (AI), into a parametric architectural design process. ML would act as a mediator between the architects' inputs and the end-users' needs. The objective of this work is to explore how Machine Learning (ML) can be utilized to visualize creative designs by transforming information from one form to another - for instance, from text to image or image to 3D architectural shapes. Additionally, the aim is to develop a process that can generate comprehensive conceptual shapes through a request in the form of an image and/or text. The suggested method essentially involves the following steps: Model creation, Revisualization, Performance evaluation. By utilizing this process, end-users can participate in the design process without negatively affecting the quality of the final product. However, the focus of this approach is not to create a final, fully-realized product, but rather to utilize abstraction and processing to generate a more understandable outcome. In the future, the algorithm will be improved and customized to produce more relevant and specific results, depending on the preferences of end-users and the input of architects.
keywords	End-users, Architects, Mass personalization, Visual programming, Neural Network Algorithm
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_60
id	caadria2023_60
authors	Bai, Zishen and Peng, Chengzhi
year	2023
title	Convolutional Neural Network (CNN) Supported Urban Design to Reduce Particle Air Pollutant Concentrations
doi	https://doi.org/10.52842/conf.caadria.2023.1.505
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. 505–514
summary	PM2.5 has become a significant factor contributing to the haze outbreak in mainland China, which has negative impacts for public health. The current agility of CFD-based modelling to reveal in real-time the changes in PM2.5 concentrations in response to (proposed) changes in urban form limits its practical applications in the design processes. To support urban design for better air quality (AQ), this study presents a machine learning approach to test: (1) that the spatial distribution of PM2.5 concentrations measured in an urban area reflects the area’s capacity to disperse particle air pollution; (2) that the PM2.5 concentration measurements can be linked to certain urban form attributes of that area. A Convolutional Neural Network algorithm called Residual Neural Network (ResNet) was trained and tested using the ChinaHighPM2.5 and urban form datasets. The result is a ResNet-AQ predictor for the city centre area in Beijing which had one of the highest air pollution levels within the Beijing-Tianjin-Hebei region. The urban area covered by the ResNet-AQ predictor contains 4,000 grid cells (approx. 25.3 km x 25.3 km), of which 1,200 (30%) cells were selected randomly for testing. The ResNet-AQ prediction accuracy achieved 87.3% after 100 iterations. An end-use scenario is presented to show how a social housing project can be supported by the AQ predictor to achieve better urban air quality performance.
keywords	PM2.5, urban form indicators, image classification, Convolutional Neural Network, open urban data
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ecaade2023_125
id	ecaade2023_125
authors	Baºarir, Lale, Çiçek, Selen and Koç, Mustafa
year	2023
title	Demystifying the patterns of local knowledge: The implicit relation of local music and vernacular architecture
doi	https://doi.org/10.52842/conf.ecaade.2023.2.791
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. 791–800
summary	As the zeitgeist suggests, the development of novel design output using Artificial Neural Networks (ANNs) is becoming an important milestone in the architectural design discourse. With the recent encounter of the computational design realm with the diffusion models, it becomes even easier to generate 2D and 3D design outputs. Yet, the utilization of machine learning tools within design computing domains is confined to generating or classifying visual and encoded data. However, it is critical to evaluate the untapped potentials of machine learning technologies in terms of illuminating the implicit correlations and links underlying distinct concepts and themes across a wide range of technical domains. With the ongoing research project named “Local Intelligence", we hypothesized that the local knowledge of a certain location might be conceptualized as a distributed network to connect different forms of local knowledge. As the first case of the project, we tried to reinstate a commonality between the local music and vernacular architecture, for which we trained generative adversarial network (GAN) models with the visual spectrograms translated from the audio data of the local songs and images of vernacular architectural instances from a defined geography. The two multi-modal GAN models differ in terms of the inherent convolutional layers and data pairing process. The outcomes demonstrated that both GAN models can learn how to depict vernacular architectural features from the rhythmic pattern of the songs in various patterns. Consequently, the implicit relations between music and architecture in the initial findings come one step closer to being demystified. Thus, the process and generative outcomes of the two models are compared and discussed in terms of the legibility of the architectural features, by taking the original vernacular architectural image dataset as the ground truth.
keywords	Local Intelligence, Machine Learning, Generative Adversarial Network (GAN), Local Music, Vernacular Architecture
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_137
id	ecaade2023_137
authors	Blaas, Quintin, Pelosi, Antony and Brown, Andre
year	2023
title	Reconsidering Artificial Intelligence as Co-Designer
doi	https://doi.org/10.52842/conf.ecaade.2023.2.559
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. 559–566
summary	The research in this paper is presented from the perspective of a designer interested in investigating using artificial intelligence, specifically machine learning, to act as a co-pilot during architectural design phases. Significant recent interest has been evident in, for instance, rapidly developing text-to-image and intelligent chat AI areas. However, we have a particular focus and have undertaken a series of feasibility experiments to explore the potential for enabling a designer's exploitation of machine learning, and consequently in effect, using machine learning as a co-designer. We conclude that the industry would need to develop certain protocols to take advantage of the opportunities available through such an AI-assisted approach.
keywords	Artificial Intelligence, Design Data, Algorithmic Design, Design Process, Co-Designing
series	eCAADe
email
last changed	2023/12/10 10:49

For more results click below: