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 576

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

_id	ecaade2017_305
id	ecaade2017_305
authors	Luther, Mark B.
year	2017
title	The Application of Daylighting Software for Case-study Design in Buildings
doi	https://doi.org/10.52842/conf.ecaade.2017.1.629
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 629-638
summary	The application of different software, whether simple or complex, can each play a significant role in the design and decision-making on daylighting for a building. This paper, discusses the task to be accomplished, in real case studies, and how various lighting software programs are used to achieve the desired information. The message iterated throughout the paper is one that respects, and even suggests, the use of even the simplest software, that can guide and inform design decisions in daylighting. Daylighting can be complex since the position of the sun varies throughout the day and year as well as do the sky conditions for a particular location. Just because we now have the computing capacity to model every single minute of a day throughout a year, doesn't justify its task. Several projects; an architecture studio, a university office building, a school library and a gymnasium all present different tasks to be achieved. The daylighting problems, the objects and the software application and their outcomes are presented in this paper. Over a decade of projects has led to reflecting upon the importance of computing in daylighting, its staged approach and the result that it can achieve if properly applied.
keywords	Daylighting Design; Daylighting Analysis; Radiosity; Ray-tracing
series	eCAADe
email
last changed	2022/06/07 07:51

_id	cf2017_415
id	cf2017_415
authors	Tschetwertak, Julia; Schneider, Sven; Hollberg, Alexander; Donath, Dirk; Ruth, Jürgen
year	2017
title	A Matter of Sequence: Investigating the Impact of the Order of Design Decisions in Multi-Stage Design Processes
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, p. 415.
summary	The design as a process is not a new topic in architecture, yet some theories are widely unexplored, such as the multi-stage decision-making (MD) process. This design method provides multiple solutions for one design problem and is characterized by design stages. By adding new building components in every stage, multiple solutions are created for each design solution from the previous stage. If the MD process is to be applied in architectural practice, fundamental and theoretical knowledge about it becomes necessary. This paper investigates the impact of sequence of design stages on the design solutions in the MD process. A basic case study provides the necessary data for comparing different sequences and gaining fundamental knowledge of the MD process. The study contains a parametric model for building generation, a parametric Life Cycle Assessment tool and an optimization mechanism based on Evolutionary Algorithms.
keywords	Multi-stage decision-making process, Design process, Life Cycle Performance, Design Automation
series	CAAD Futures
email
last changed	2017/12/01 14:38

_id	ecaade2017_199
id	ecaade2017_199
authors	Al-Douri, Ph.D., Firas
year	2017
title	Computational and Modeling Tools - How effectively are Urban Designers and Planners using them Across the Design Development Process?
doi	https://doi.org/10.52842/conf.ecaade.2017.1.409
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 409-418
summary	Literature suggests that despite the increasing range and variety of computational tools and technologies, they have not really been employed for designing as extensively as it might be. This is due in part to the numerous challenges and impediments limiting their effective usage such as the methodological, procedural, and substantive factors and limitations, and skepticism about their impact of usage on the design process and outcome. The gap in our understanding of how advanced computational tools could support the design activities and design decision-making has expanded considerably to become a new area of inquiry with considerable room for the expansion of knowledge. This research is a single-case study that has been pursued in two phases: literature review and survey followed by analysis and discussion of the empirical results. The empirical observations were compared to the theoretical propositions and with results of similar research to highlight the areas and the extent to what the IT tools' usage have influenced the outcome of the design process. The comparison has helped highlight, explain, and justify the mechanism and improvements in the design outcome. Please write your abstract here by clicking this paragraph.
keywords	Computational urban design; Urban Design Practice
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ijac202018203
id	ijac202018203
authors	Beattie , Hamish; Daniel Brown and Sara Kindon
year	2020
title	Solidarity through difference: Speculative participatory serious urban gaming (SPS-UG)
source	International Journal of Architectural Computing vol. 18 - no. 2, 141-154
summary	This article discusses the methodology and results of the Maslow’s Palace workshops project, which engages with current debates surrounding the democratisation of digital urban design technology and stakeholder decision making, through the implementation of a speculative oriented approach to serious gaming. The research explores how serious games might be used to help marginalised communities consider past, future and present community experiences, reconcile dissimilar assumptions, generate social capital building and design responses and prime participants for further long-term design engagement processes through a new approach called Speculative Participatory Serious Urban Gaming. Empirical material for this research was gathered from a range of case study workshops prepared with three landfill-based communities and external partners throughout 2017. Results show the approach helped participants develop shared norms, values and collective understandings of sensitive topics and develop ideas for future action through ‘collective tinkering.
keywords	Participatory design, urban design, social capital, serious games
series	journal
email
last changed	2020/11/02 13:34

_id	caadria2019_388
id	caadria2019_388
authors	Beattie, Hamish, Brown, Daniel and Kindon, Sara
year	2019
title	Functional Fiction to Collective Action - Values-Based Participatory Urban Design Gaming
doi	https://doi.org/10.52842/conf.caadria.2019.1.737
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 737-746
summary	This paper discusses the methodology and results of the Maslow's Palace workshops project, which engages with current debates surrounding the democratisation of digital urban design technology and stakeholder decision making, through the implementation of a speculative oriented approach to serious gaming. The research explores how serious games might be used to help marginalised communities consider past, future and present community experiences, reconcile dissimilar assumptions, generate social capital building and design responses and prime participants for further long term design engagement processes. Empirical material for this research was gathered from a range of case study workshops prepared with three landfill-based communities and external partners throughout 2017. Results show the approach helped participants develop shared norms, values and understandings of sensitive topics and develop ideas for future action through "collective tinkering".
keywords	Participatory design; urban design; social capital; serious games; slum upgrading
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	caadria2017_070
id	caadria2017_070
authors	Chen, Nai Chun, Xie, Jenny, Tinn, Phil, Alonso, Luis, Nagakura, Takehiko and Larson, Kent
year	2017
title	Data Mining Tourism Patterns - Call Detail Records as Complementary Tools for Urban Decision Making
doi	https://doi.org/10.52842/conf.caadria.2017.685
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 685-694
summary	In this study we show how Call Detail Record (CDR) can be used to better understand the travel patterns of visitors. We show how Origin-Destination (OD) Interactive Maps can provide transportation information through CDR. We then use aggregation of CDR to show the differences between the travel patterns of visitors from different countries and of different lengths of stay. We also show that visitors move differently during event periods and non-event periods, reflecting the importance of real-time data available by CDR. From CDR, we can gain more detailed and complete information about how tourists move compared to traditional surveys, which can be used to aid smarter transportation systems and urban resource planning.
keywords	Machine Learning; Call Detail Record; Original-Destination Matrix; Urban Design Tool
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	cf2017_101
id	cf2017_101
authors	Chen, Nai Chun; Zhang, Yan; Stephens, Marrisa; Nagakura, Takehiko; Larson, Kent
year	2017
title	Urban Data Mining with Natural Language Processing: Social Media as Complementary Tool for Urban Decision Making
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, pp. 101-109.
summary	The presence of web2.0 and traceable mobile devices creates new opportunities for urban designers to understand cities through an analysis of user-generated data. The emergence of “big data” has resulted in a large amount of information documenting daily events, perceptions, thoughts, and emotions of citizens, all annotated with the location and time that they were recorded. This data presents an unprecedented opportunity to gauge public opinion about the topic of interest. Natural language processing with social media is a novel tool complementary to traditional survey methods. In this paper, we validate these methods using tourism data from Trip-Advisor in Andorra. “Natural language processing” (NLP) detects patterns within written languages, enabling researchers to infer sentiment by parsing sentences from social media. We applied sentiment analysis to reviews of tourist attractions and restaurants. We found that there were distinct geographic regions in Andorra where amenities were reviewed as either uniformly positive or negative. For example, correlating negative reviews of parking availability with land use data revealed a shortage of parking associated with a known traffic congestion issue, validating our methods. We believe that the application of NLP to social media data can be a complementary tool for urban decision making.
keywords	Short Paper, Urban Design Decision Making, Social Media, Natural Language Processing
series	CAAD Futures
email
last changed	2017/12/01 14:37

_id	caadria2017_155
id	caadria2017_155
authors	Cichocka, Judyta Maria, Browne, Will Neil and Rodriguez, Edgar
year	2017
title	Optimization in the Architectural Practice - An International Survey
doi	https://doi.org/10.52842/conf.caadria.2017.387
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 387-396
summary	For several years great effort has been devoted to the study of Architectural Design Optimization (ADO). However, although in the recent years ADO has attracted much attention from academia, optimization methods and tools have had a limited influence on the architectural profession. The aim of the study is to reveal users' expectations from the optimization tools and define limitations preventing wide-spread adaptation of the optimization solvers in the architectural practice. The paper presents the results of the survey "Optimization in the architectural practice" conducted between December 2015 and February 2016 on 165 architectural trainees and practising architects from 34 countries. The results show that there is a need for an interactive multi-objective optimization tool, as 78% respondents declared that a multi-objective optimization is more necessary in their practice than a single objective one and 91% of them acknowledged the need for choice of promising solutions during optimization process. Finally, it has been found that daylight, structure and geometry are three top factors which architects are interested in optimizing.
keywords	Architectural Design Optimization; Optimizaiton Techniques; Generic Solvers; Multi-criteria Decision Making
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	cf2017_137
id	cf2017_137
authors	Ensari, Elif; Kobas, Bilge; Sucuo?lu, Can
year	2017
title	Computational Decision Support for an Airport Complex Roof Design: A Case Study of Evolutionary Optimization for Daylight Provision and Overheating Prevention
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, pp. 137-149.
summary	This study focuses on generating geometric design alternatives for an airport roof structure with an evolutionary design method based on optimizing solar heat gain and daylight levels. The method incorporates a parametric 3D model of the building, a multi objective genetic algorithm that was linked with the model to iteratively test for various geometric solutions, a custom module that was developed to simulate solar conditions, and external energy simulation environments that was used to validate the outcomes. The integral outcome was achieved through an iterative workflow of many software tools, and the study is significant in dealing with several space typologies at the same time, taking real-life constraints such as applicability, ease of operation, construction loads into consideration, and satisfying design and aesthetic requirements of the architectural design team.
keywords	Evolutionary algorithms, daylight and energy performance, multi-objective optimization
series	CAAD Futures
email
last changed	2017/12/01 14:37

_id	cf2017_596
id	cf2017_596
authors	Fukuda, Tomohiro; Nada, Hideki; Adachi, Haruo; Shimizu, Shunta; Takei, Chikako; Sato, Yusuke; Yabuki, Nobuyoshi; Motamedi, Ali
year	2017
title	Integration of a Structure from Motion into Virtual and Augmented Reality for Architectural and Urban Simulation: Demonstrated in Real Architectural and Urban Projects
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, p. 596.
summary	Computational visual simulations are extremely useful and powerful tools for decision-making. The use of virtual and augmented reality (VR/AR) has become a common phenomenon due to real-time and interactive visual simulation tools in architectural and urban design studies and presentations. In this study, a demonstration is performed to integrate Structure from Motion (SfM) into VR and AR. A 3D modeling method is explored by SfM under realtime rendering as a solution for the modeling cost in large-scale VR. The study examines the application of camera parameters of SfM to realize an appropriate registration and tracking accuracy in marker-less AR to visualize full-scale design projects on a planned construction site. The proposed approach is applied to plural real architectural and urban design projects, and results indicate the feasibility and effectiveness of the proposed approach.
keywords	Architectural and urban design, Visual simulation, Virtual reality, Augmented reality, Structure from motion.
series	CAAD Futures
email
last changed	2017/12/01 14:38

_id	ecaade2017_029
id	ecaade2017_029
authors	Gadelhak, Mahmoud, Lang, Werner and Petzold, Frank
year	2017
title	A Visualization Dashboard and Decision Support Tool for Building Integrated Performance Optimization
doi	https://doi.org/10.52842/conf.ecaade.2017.1.719
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 719-728
summary	Analyzing the results of multi-objective optimization and building performance simulation can be a very tedious process that requires navigating between different software and tools. There is a clear scarcity in visualization tools that combine methods for big data analysis and design decision support tools that integrate detailed information for each design and parameter. Having a single visualization tool that provides methods to both visualize and analyze a large amount of data, understand the relation between objectives and variables, and having the ability to compare and analyze the preferred designs thoroughly can support the process of design decision making. In this paper, previous attempts to develop better data visualization tools for both integrated building simulation and optimization outputs were analyzed, then guidelines and a visualization tool prototype that can be effective in decision making and analyzing multi-objective optimizations results was presented.
keywords	Multi-objective optimization; Building Performance Simulation; Simulation; Visualization tools
series	eCAADe
email
last changed	2022/06/07 07:50

_id	ecaade2017_255
id	ecaade2017_255
authors	Heinrich, Mary Katherine, Ayres, Phil and Bar-Yam, Yaneer
year	2017
title	A Multiscale Model of Morphological Complexity in Cities - Characterising Emergent Homogeneity and Heterogeneity
doi	https://doi.org/10.52842/conf.ecaade.2017.2.561
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 561-570
summary	Approaches from complex systems science can support design decision-making by extracting important information about key dependencies from large, unstructured data sources. This paper presents an initial case study applying such approaches to city structure, by characterising low-level features and aggregate properties of artifact morphology in urban areas. First, shape analysis is used to describe microscale artifact clusters, analysed in aggregate to characterise macroscale homogeneity and heterogeneity. The characterisation is used to analyse real-world example cities, from both historic maps and present-day crowdsourced data, testing against two performance evaluation criteria. Next, the characterisation is used to generate simple artificial morphologies, suggesting directions for future development. Finally, results and extensions are discussed, including real-world applications for decision support.
keywords	Complex systems; morphology; shape analysis; urban planning
series	eCAADe
email
last changed	2022/06/07 07:49

_id	ecaade2017_274
id	ecaade2017_274
authors	Lanham, Thomas, Shaifa, Irvin, Poustinchi, Ebrahim and Luhan, Gregory
year	2017
title	Craft and Digital Consequences - Micro-Hybrid Explorations at (Full) Scale
doi	https://doi.org/10.52842/conf.ecaade.2017.2.327
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 327-336
summary	This paper presents a comprehensive project-based research investigation that uses both drawing and modeling to challenge conventional design space. Situated at the University of Kentucky-College of Design Applied Computation Center (CoDACC) in Lexington, KY, this independent undergraduate research project reveals an immersive framework that develops, evaluates, and assesses both graphic and three-dimensional information at full scale. This research provides a framework that seamlessly negotiates analog and digital means of communication and prototyping. This paper outlines the micro-hybrid design process to frame topics germane to today's increasingly complex built environment. The paper also includes the micro-hybrid decision-making matrix and discusses the evaluation of the produced artifacts. The research demonstrates how the micro-hybrid process can reveal both the craft and consequences related to design experimentation and construction. Further, the micro-hybrid process has been shown to deepen a student's understanding of the composition of materials and a student's awareness of forces and structural loads, which in turn has produced a deeper appreciation for the principles of structures and an improved mastery of manufacturing jointing details.
keywords	Digital; Pedagogy; Fabrication; Experimentation; Simulation
series	eCAADe
email
last changed	2022/06/07 07:52

_id	ecaade2017_019
id	ecaade2017_019
authors	Liu, Yuezhong, Stouffs, Rudi and Tablada, Abel
year	2017
title	Rethinking the Urban Design Process from a Data Perspective
doi	https://doi.org/10.52842/conf.ecaade.2017.1.449
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 449-460
summary	Urban design always requires the processing of large amounts of data from multi-disciplinary sources during the decision-making stages. However, unfamiliar multi-disciplinary data sets can only lead to confusion and uncertainty. This research proposes a data-driven approach for supporting the urban design process. A hybrid data mining method is used to cluster, classify and rank solution-instances according to geometrical properties and energy performance. An urban design case study is used to demonstrate the proposed method with respect to two performance issues: solar heat gains and natural ventilation. The result shows that the method addressing both familiar and unfamiliar data can effectively guide the designer during the design process.
keywords	energy performance; S3VM; decision tree; familiar and unfamiliar
series	eCAADe
email
last changed	2022/06/07 07:59

_id	ecaade2017_077
id	ecaade2017_077
authors	Mekawy, Mohammed and Petzold, Frank
year	2017
title	Exhaustive Exploration of Modular Design Options to Inform Decision Making
doi	https://doi.org/10.52842/conf.ecaade.2017.2.107
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 107-114
summary	Europe is facing an increasing demand for new construction, which is pushing the industry away from traditional construction technology towards prefabrication and Mass-Customization. However, prefabrication-based construction requires a more efficient, better informed decision making process due to the increased difficulty of on-site variations. Furthermore, the lack of means to navigate the whole spectrum of solutions for a given design problem using traditional tools, and the absence of the manufacturer's input in the early phases of the project can present significant challenges for the efficiency of the design and construction process. As a way to face these challenges, this paper presents an approach, realized as an Autodesk Dynamo-for-Revit package called Box Module Generator (BMG), which enables the exhaustive generation of configurations for a given building based on a construction scheme that utilizes Box Prefabricates. The output can be sorted, dissected and explored by users in various ways and the building geometry can be generated automatically in a Building Information Modeling environment. This makes it possible for the projects' stakeholders to browse thousands of potential design alternatives, which would otherwise be very hard to explore manually, or using traditional parametric modelers.
keywords	Prefabrication; Box Prefabricates; Design Tools; Design Automation; Building Information Modeling; Dynamo
series	eCAADe
email
last changed	2022/06/07 07:58

_id	cf2017_630
id	cf2017_630
authors	Muehlbauer, Manuel; Song, Andy; Burry, Jane
year	2017
title	Towards Intelligent Control in Generative Design
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, pp. 630-647.
summary	This position paper proposes and defines the nature of a framework, which explores ways of integrating control system (CS) with machine intelligence for generative design (GD). This paper elaborates about the implications of and the potential for impact on GD. The framework described in this work can be used as an active tool to drive design processes and support decision making process in early stages of architectural design. This type of system can be either automated in nature or adaptive to regular user input as part of interactive design mechanisms. The module of CS in the framework would allow additional guidance during design and therefore reduce the need of manual input to enable a semi-automated design practice for lengthy generative processes. This study on GD reveals emergent properties of the framework, for example the introduction of intelligent control allows guidance of GD to meet specified performance criteria and intended aesthetic expressions with reduced need for user interaction.
keywords	Semi-Automated Design, Evolutionary Architecture, Generative Design, Architectural Optimisation, Artificial Intelligence
series	CAAD Futures
email
last changed	2017/12/01 14:38

_id	ecaade2017_269
id	ecaade2017_269
authors	Rahmani Asl, Mohammad, Das, Subhajit, Tsai, Barry, Molloy, Ian and Hauck, Anthony
year	2017
title	Energy Model Machine (EMM) - Instant Building Energy Prediction using Machine Learning
doi	https://doi.org/10.52842/conf.ecaade.2017.2.277
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 277-286
summary	In the process of building design, energy performance is often simulated using physical principles of thermodynamics and energy behaviour using elaborate simulation tools. However, energy simulation is computationally expensive and time consuming process. These drawbacks limit opportunities for design space exploration and prevent interactive design which results in environmentally inefficient buildings. In this paper we propose Energy Model Machine (EMM) as a general and flexible approximation model for instant energy performance prediction using machine learning (ML) algorithms to facilitate design space exploration in building design process. EMM can easily be added to design tools and provide instant feedback for real-time design iterations. To demonstrate its applicability, EMM is used to estimate energy performance of a medium size office building during the design space exploration in widely used parametrically design tool as a case study. The results of this study support the feasibility of using machine learning approaches to estimate energy performance for design exploration and optimization workflows to achieve high performance buildings.
keywords	Machine Learning; Artificial Neural Networks; Boosted Decision Tree; Building Energy Performance; Parametric Modeling and Design; Building Performance Optimization
series	eCAADe
email
last changed	2022/06/07 08:00

_id	ecaade2023_259
id	ecaade2023_259
authors	Sonne-Frederiksen, Povl Filip, Larsen, Niels Martin and Buthke, Jan
year	2023
title	Point Cloud Segmentation for Building Reuse - Construction of digital twins in early phase building reuse projects
doi	https://doi.org/10.52842/conf.ecaade.2023.2.327
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. 327–336
summary	Point cloud processing has come a long way in the past years. Advances in computer vision (CV) and machine learning (ML) have enabled its automated recognition and processing. However, few of those developments have made it through to the Architecture, Engineering and Construction (AEC) industry. Here, optimizing those workflows can reduce time spent on early-phase projects, which otherwise could be spent on developing innovative design solutions. Simplifying the processing of building point cloud scans makes it more accessible and therefore, usable for design, planning and decision-making. Furthermore, automated processing can also ensure that point clouds are processed consistently and accurately, reducing the potential for human error. This work is part of a larger effort to optimize early-phase design processes to promote the reuse of vacant buildings. It focuses on technical solutions to automate the reconstruction of point clouds into a digital twin as a simplified solid 3D element model. In this paper, various ML approaches, among others KPConv Thomas et al. (2019), ShapeConv Cao et al. (2021) and Mask-RCNN He et al. (2017), are compared in their ability to apply semantic as well as instance segmentation to point clouds. Further it relies on the S3DIS Armeni et al. (2017), NYU v2 Silberman et al. (2012) and Matterport Ramakrishnan et al. (2021) data sets for training. Here, the authors aim to establish a workflow that reduces the effort for users to process their point clouds and obtain object-based models. The findings of this research show that although pure point cloud-based ML models enable a greater degree of flexibility, they incur a high computational cost. We found, that using RGB-D images for classifications and segmentation simplifies the complexity of the ML model but leads to additional requirements for the data set. These can be mitigated in the initial process of capturing the building or by extracting the depth data from the point cloud.
keywords	Point Clouds, Machine Learning, Segmentation, Reuse, Digital Twins
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2017_145
id	caadria2017_145
authors	Kalantari, Saleh, Poustinchi, Ebrahim and Ahmadi, Nooshin
year	2017
title	Human-Computer Interaction in the Form-Making Process
doi	https://doi.org/10.52842/conf.caadria.2017.529
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 529-538
summary	Many elements of architectural design are becoming automated, and the boundaries between design, construction, and use are increasingly blurred. These developments have produced concerns that our design processes might outrun "human factors" in our search for novelty and automation. At the same time, however, this new technology can also improve our opportunities to develop human-centric environments. This paper describes the creation of an interactive form-making exhibit called ROBOBBLE, and the use of this installation to engage users in design while collecting data about their architectural preferences. The ultimate goal of the ongoing project is to learn more about human form creation and architectural evaluations, and to integrate those findings into computational design algorithms and pre-design toolkits. A pilot study was conducted to test ROBOBBLE as a data-collection platform and to evaluate interactive form-making engagement among a small group of students. The platform was shown to be successful in engaging all of the participants in this pilot study and expanding their creative design capacities over time. Future work using ROBOBBLE for larger population studies has the potential to produce detailed data about a wide variety of design preferences, and to incorporate this data directly into computational design process.
keywords	Human-Computer Interaction; Form-Making; Human Data; Design Process
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2017_144
id	ecaade2017_144
authors	Lange, Christian J.
year	2017
title	Elements \| robotic interventions II
doi	https://doi.org/10.52842/conf.ecaade.2017.1.671
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 671-678
summary	Reviewing the current research trends in robotic fabrication around the world, the trajectory promises new opportunities for innovation in Architecture and the possible redefinition of the role of the Architect in the industry itself. New entrepreneurial, innovative start-ups are popping up everywhere challenging the traditional model of the architect. However, it also poses new questions and challenges in the education of the architect today. What are the appropriate pedagogical methods to instill enthusiasm for new technologies, materials, and craft? How do we avoid the pure application of pre-set tools, such as the use of the laser cutter has become, which in many schools around the world has caused problems rather than solving problems? How do we teach students to invent their tools especially in a society that doesn't have a strong background in the making? The primary focus of this paper is on how architectural CAAD/ CAM education through the use of robotic fabrication can enhance student's understanding, passion and knowledge of materiality, technology, and craftsmanship. The paper is based on the pedagogical set-up and method of an M. Arch I studio that was taught by the author in fall 2016 with the focus on robotic fabrication, materiality, traditional timber construction systems, tool design and digital and physical craftsmanship.
keywords	CAAD Education, Digital Technology, Craftsmanship, Material Studies, Tool Design, Parametric Modeling, Robotic Fabrication
series	eCAADe
email
last changed	2022/06/07 07:52

For more results click below: