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 617

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

_id	caadria2019_234
id	caadria2019_234
authors	Bamborough, Chris
year	2019
title	The Nature of Data in Early Modern Architectural Practice.
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 343-352
doi	https://doi.org/10.52842/conf.caadria.2019.2.343
summary	In contemporary data-driven society, forces of capital increasingly seek risk-averse decision making through data and digital calculation, aligned to this the discourse around design intelligence in architecture has begun to embrace the role of data and the technical non-human as much as the human. In parallel, the cultural understanding of data, in technologically mediated societies, has become tied to the digital representation of information experienced in everyday life, which in turn influences human practices. A problem exists in the dominance of scientific thought around data in architecture that exerts disciplinary bias towards quantity rather than quality. In contemporary digital practice, data is assumed to offer an objective characterisation of the world and have faithful representation through the mechanisms of the computer. From this shift, a macro question exists concerning the influence of data's conceptualisation on the physical products of architecture. To contribute to this overall question this paper considers the register of data in early modernism identified as a moment when scientific abstraction and the mapping capacity of the machine combine to afford recognisable data practices and infrastructures.
keywords	Data; Design Practice; Infrastructure; History; Theory
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	ecaadesigradi2019_249
id	ecaadesigradi2019_249
authors	Chiarella, Mauro, Gronda, Luciana and Veizaga, Martín
year	2019
title	RILAB - architectural envelopes - From spatial representation (generative algorithm) to geometric physical optimization (scientific modeling)
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 17-24
doi	https://doi.org/10.52842/conf.ecaade.2019.3.017
summary	Augmented graphical thinking operates by integrating algorithmic, heuristic, and manufacturing processes. The Representation and Ideation Laboratory (RILAB-2018) exercise begins with the application of a parametric definition developed by the team of teachers, allowing for the construction of structural systems by the means of the combination of segmental shells and bending-active. The main objetive is the construction of a scientific model of simulation for bending-active laminar structures has brought into reality trustworthy previews for architectural envelopes through the interaction of parametrized relational variables. This way we put designers in a strategic role for the building of the pre-analysis models, allowing more preciseness at the time of picking and defining materials, shapes, spaces and technologies and thus minimizing the decisions based solely in the definition of structural typological categories, local tradition or direct experience. The results verify that the strategic integration of models of geometric physical optimization and spatial representation greatly expand the capabilities in the construction of the complex system that operates in the act of projecting architecture.
keywords	architectural envelopes; augmented graphic thinking; geometric optimization; bending-active
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	cf2019_059
id	cf2019_059
authors	Ma, Lisha ; Xiaofang Yuan, Yu Wu and Wuzhen Zhu
year	2019
title	A National Pattern Generation Method Based on Cultural Design Genetic Derivation
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 500
summary	It is a great challenge to digitally generate emotionally satisfying patterns with national style characteristics to meet diversified consumer demands for national patterns. As the core of national culture’s gestation, growth and development, cultural genes can realize cultural inheritance and maintain national identity . From the view of design, the basic feature elements of cultural genes are extracted by original national pattern deconstruction and semantically summarized to form specific cultural design genes suitable for the rapid design of national pattern. Further, the topology principle and ComputerAided design is introduced to simultaneously generate pattern shapes using Self-Crossing and Cross-Crossing transformation by shape grammar. Then, the pattern elements are arranged according to the initial ethnic pattern composition rules to generate new series of ethnic patterns. Finally, Chinese Tibetan pattern is patterned as an example to demonstrate that this research can creates patterns faster and in line with the user's intent.
keywords	National pattern, Cultural design gene, Pattern deconstruction, Shape grammar, Computer-Aided design
series	CAAD Futures
email
last changed	2019/07/29 14:18

_id	ijac201917201
id	ijac201917201
authors	Trilsbeck, Matthew; Nicole Gardner, Alessandra Fabbri, Matthias Hank Haeusler, Yannis Zavoleas and Mitchell Page
year	2019
title	Meeting in the middle: Hybrid clay three-dimensional fabrication processes for bio-reef structures
source	International Journal of Architectural Computing vol. 17 - no. 2, 148-165
summary	Despite the relative accessibility of clay, its low cost and reputation as a robust and sustainable building material, clay three-dimensional printing remains an under-utilized digital fabrication technique in the production of architectural artefacts. Given this, numerous research projects have sought to extend the viability of clay three-dimensional digital fabrication by streamlining and automating workflows through computational methods and robotic technologies in ways that afford agency to the digital and machinic processes over human bodily skill. Three-dimensional printed clay has also gained prominence as a resilient material well suited to the design and fabrication of artificial reef and habitat- enhancing seawall structures for coastal marine environments depleted and disrupted by human activity, climate change and pollution. Still, these projects face similar challenges when three-dimensional printing complex forms from the highly plastic and somewhat unpredictable feed material of clay. In response, this article outlines a research project that seeks to improve the translation of complex geometries into physical clay artefacts through additive three- dimensional printing processes by drawing on the notion of digital craft and giving focus to human–machine interaction as a collaborative practice. Through the case study of the 1:1 scale fabrication of a computationally generated bio-reef structure using clay as a feed material and a readily available Delta Potterbot XLS-2 ceramic printer, the research project documents how, by exploiting the human ability to intuitively handle clay and adapt, and the machine’s ability to work efficiently and with precision, humans and machines can fabricate together . With the urgent need to develop more sustainable building practices and materials, this research contributes valuable knowledge of hybrid fabrication processes towards extending the accessibility and viability of clay three-dimensional printing as a resilient material and fabrication system.
keywords	Clay three-dimensional printing, digital fabrication, hybrid fabrication, digital craft, human–machine interaction
series	journal
email
last changed	2019/08/07 14:04

_id	acadia19_60
id	acadia19_60
authors	Yousif, Shermeen; Yan, Wei
year	2019
title	Application of an Automatic Shape Clustering Method
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 60-69
doi	https://doi.org/10.52842/conf.acadia.2019.060
summary	Despite their prevalence and extensive applications, generative and design optimization systems lack effective organizational methods of the excessive number of design options they produce, which is problematic for designers’ interaction. Ideally, a diverse and organized set of designs can mediate successful designers’ evaluation and exploration of the design space. Cluster analysis, a big-data management strategy, offers a solution. Yet, there is a need for investigating appropriate methods for applying cluster-analysis to a dataset of geometric shapes. Therefore, we have recently developed and published a new approach, the Shape Clustering using K-Medoids (SC-KM) method as an articulation mechanism in generative systems. The method involves shape description, shape difference measure calculation, and implementation of the K-Medoids clustering algorithm. The focus of this work is on incorporating the method into a generative system with parametric building shape generation and design optimization. The method organizes a dataset of shapes into clusters where shapes within the cluster share similarities yet differ from other clusters, and each cluster is signified by one representative shape. The SC-KM method contributes to an organized design presentation and facilitates designers’ examination of their designs’ geometric qualities.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:57

_id	cf2019_013
id	cf2019_013
authors	Boychenko, Kristina
year	2019
title	Agency of Interactive Architecture in socio-technological relationship through Actor-Network Theory
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 102
summary	With fast development of new technologies built environment transitioned from a silent background of activities performed by users to another participant of those activities. Agency of interactive architecture is based on interpretation of input data, like users’ actions, their response to the spatial agency, data from environment or other actors, and changing its performance accordingly. Architectural components, environmental conditions and people are all treated as agents and closely correspond to Actor-Network Theory (ANT). This theory generally aims to reveal the complexities of socio-technological world. ANT incorporates a principle of generalized symmetry, it means that human and nonhuman (artifacts, organization structures, etc.) actors are incorporated into the same conceptual framework and assigned equal level of agency. By analysis of the agency of Interactive Architecture through ANT the paper provides insight on social role of this new emerging type of space and its influence on other participants on socio-technological relationship.
keywords	Interactive architecture, Communication, Agency, Social, ActorNetwork Theory
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	cf2019_021
id	cf2019_021
authors	Cheng, Chi-Li and June-Hao Hou
year	2019
title	A Method of Mesh Simplification for Drone 3D Modeling with Architectural Feature Extraction
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 169
summary	This paper proposes a method of mesh simplification for 3D terrain or city models generated photogrammetrically from drone captured images, enabled by the ability of extracting the architectural features. Compare to traditional geometric computational method, the proposed method recognizes and processes the features from the architectural perspectives. In addition, the workflow also allows exporting the simplified models and geometric features to open platforms, e.g. OpenStreetMap, for practical usages in site analysis, city generation, and contributing to the open data communities.
keywords	Mesh Reconstruction, photogrammetry, mesh simplification, procedural mode, machine learning
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	ecaadesigradi2019_561
id	ecaadesigradi2019_561
authors	Cress, Kevan and Beesley, Philip
year	2019
title	Architectural Design in Open-Source Software - Developing MeasureIt-ARCH, an Open Source tool to create Dimensioned and Annotated Architectural drawings within the Blender 3D creation suite.
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 621-630
doi	https://doi.org/10.52842/conf.ecaade.2019.1.621
summary	MeasureIt-ARCH is A GNU GPL licensed, dimension, annotation, and drawing tool for use in the open source software Blender. By providing free and open tools for the reading and editing of architectural drawings, MeasurIt-ARCH allows works of architecture to be shared, read, and modified by anyone. The digitization of architectural practice over the last 3 decades has brought with it a new set of inter-disciplinary discourses for the profession. An attempt to utilise 'Open-Source' methodologies, co-opted from the world of software development, in order to make high quality design more affordable, participatory and responsible has emerged. The most prominent of these discussions are embodied in Carlo Raitti and Mathew Claudel's manifesto 'Open-Source Architecture' (Ratti 2015) and affordable housing initiatives like the Wikihouse project (Parvin 2016). MeasurIt-ARCH aims to be the first step towards creating a completely Open-Source design pipeline, by augmenting Blender to a level where it can be used produce small scale architectural works without the need for any proprietary software, serving as an exploratory critique on the user experience and implementations of industry standard dimensioning tools that exist on the market today.
keywords	Blender; Open-Source; Computer Aided Design ; OSArc
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_id	acadia19_130
id	acadia19_130
authors	Devadass, Pradeep; Heimig, Tobias; Stumm, Sven; Kerber, Ethan; Cokcan, Sigrid Brell
year	2019
title	Robotic Constraints Informed Design Process
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 130-139
doi	https://doi.org/10.52842/conf.acadia.2019.130
summary	Promising results in efficiently producing highly complex non-standard designs have been accomplished by integrating robotic fabrication with parametric design. However, the project workflow is hampered due to the disconnect between designer and robotic fabricator. The design is most often developed by the designer independently from fabrication process constraints. This results in fabrication difficulties or even non manufacturable components. In this paper we explore the various constraints in robotic fabrication and assembly processes, analyze their influence on design, and propose a methodology which bridges the gap between parametric design and robotic production. Within our research we investigate the workspace constraints of robots, end effectors, and workpieces used for the fabrication of an experimental architectural project: “The Twisted Arch.” This research utilizes machine learning approaches to parameterize, quantify, and analyze each constraint while optimizing how those parameters impact the design output. The research aims to offer a better planning to production process by providing continuous feedback to the designer during early stages of the design process. This leads to a well-informed “manufacturable” design.
keywords	Robotic Fabrication and Assembly, Mobile Robotics, Machine Learning, Parametric Design, Constraint Based Design.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:55

_id	cf2019_014
id	cf2019_014
authors	Ferrando, Cecilia; Niccolo Dalmasso, Jiawei Mai, Daniel Cardoso Llach
year	2019
title	Architectural Distant Reading Using Machine Learning to Identify Typological Traits Across Multiple Buildings
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, pp. 114-127
summary	This paper introduces an approach to architectural “distant reading”: the use of computational methods to analyze architectural data in order to derive spatial insights from—and explore new questions concerning—large collections of architectural work. Through a case study comprising a dataset of religious buildings, we show how we may use machine learning techniques to identify typological and functional traits from building plans. We find that spatial structure, rather than local features, is particularly effective in supporting this type of analysis. Further, we speculate on the potential of this computational method to enrich architectural design, research, and criticism by, for example, enabling new ways of thinking about architectural concepts such as typology in ways that reflect gradual variations, rather than sharp distinctions.
keywords	Architectural Analytics, Machine Learning, Classification, Religious buildings, Space Syntax
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	ecaadesigradi2019_305
id	ecaadesigradi2019_305
authors	Kabošová, Lenka, Worre Foged, Isak, Kme, Stanislav and Katunský, Dušan
year	2019
title	Building envelope adapting from and to the wind flow
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 131-138
doi	https://doi.org/10.52842/conf.ecaade.2019.2.131
summary	The paper presents research for wind-responsive architecture. The main objective is the digital design methodology incorporating the dynamic, fluctuating wind flow into the shape-generating process of architectural envelopes. These computational studies are advanced and informed through physical prototyping models, allowing a hybrid method approach. The negative impacts of the wind at the building scale (wind loads), as well as urban scale (wind discomfort), can be avoided and even transformed into an advantage by incorporating the local wind conditions to the process of creating architectural envelopes with adaptive structures. The paper proposes a tensegrity-membrane system which, when exposed to the dynamic wind flow, enables a local passive shape adaptation. Thus, the action of the wind pressure transforms the shape of the building envelope to an unsmoothed, dimpled surface. As a consequence, the aerodynamic properties of the building are modified, which contributes to reducing wind suction and drag force. Moreover, the slight shape change materializes and articulates the immaterial wind phenomena. For a better understanding of the dynamic geometric properties, one unit of the wind-responsive envelope is tested through simulations, and through physical prototypes. The idea and material-geometric studies are subsequently applied in a specific case study, including a designed building envelope in an industrial silo cluster in Stockholm.
keywords	adaptive envelope; tensegrity; wind flow; digital designing; shape-change
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	caadria2019_143
id	caadria2019_143
authors	Kato, Yuri and Matsukawa, Shohei
year	2019
title	Development of Generating System for Architectural Color Icons Using Google Map Platform and Tensorflow-Segmentation
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 81-90
doi	https://doi.org/10.52842/conf.caadria.2019.2.081
summary	In this research, the goal is to develop a generating system for architectural color icons using Google Map Platform and Tensorflow-Segmentation. There has been no case of developing a system that allows users to visualize the color tendency of buildings as architectural color icons for each building element from images of various regions. It is considered meaningful to be able to create criteria for decision making in architecture and the urban design by developing a system to clarify the current state of the architectural colors. It will contribute a rise in the consciousness of landscape conservation and be essential for the design of architectures and public objects. This paper includes the explanation of development method, use experiments, and consideration of five problems among architectural color icons creation. It is assumed that the accuracy of the present system will be better as the technology improves.
keywords	Google street view; machine learning; image segmentation; color palette; color analysis
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	caadria2019_183
id	caadria2019_183
authors	Macken, Marian, Mulla, Sarosh and Paterson, Aaron
year	2019
title	Inhabiting the Drawing - 1:1 in time and space
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. 505-514
doi	https://doi.org/10.52842/conf.caadria.2019.1.505
summary	One of the fundamental characteristics of architectural drawing is its use of scale. Since the Renaissance - during which architectural production shifted from the construction site to paper - this scalar understanding began by using bodily measurements. In developing designs, the architect projects future occupation of the drawing with their eyes and hands moving over both its physical surface and represented space. The different relationship established between the digital drawer and the body has been criticised; Paul Emmons argues that CAD's full scale - or rather scale-less - capabilities omit this bodily presence of the drawer (Emmons, 2005). Due to the use of full scale data recording, the drawer zooms in and out to consider aspects, severing the drawing's relation to the operator's body. This paper explores ways in which the body and drawings intersect, beyond Emmons definition, and hence considers the influence of the method of drawing on perceptions of scale and the inhabitation of digital drawings. It uses ongoing collaborative research projects and exhibitions to explore the inhabitation of digital drawing at full scale. These works highlight the fundamental importance of the line within architecture, not as demarcation, divider or indexical reference, but as a traces of bodily projections.
keywords	architectural drawing; architectural scale; full scale drawing; post factum documentation
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ijac201917104
id	ijac201917104
authors	Matthews, Linda and Gavin Perin
year	2019
title	Exploiting ambiguity: The diffraction artefact and the architectural surface
source	International Journal of Architectural Computing vol. 17 - no. 1, 103-115
summary	In the contemporary ‘envisioned’ environment, Internet webcams, low- and high-altitude unmanned aerial vehicles and satellites are the new vantage points from which to construct the image of the city. Armed with hi-resolution digital optical technologies, these vantage points effectively constitute a ubiquitous visioning apparatus serving either the politics of promotion or surveillance. Given the political dimensions of this apparatus, it is important to note that this digital imaging of public urban space refers to the human visual system model. In order to mimic human vision, a set of algorithm patterns are used to direct numerous ‘soft’ and ‘hard’ technologies. Mimicry thus has a cost because this insistence on the human visual system model necessitates multiple transformative moments in the production and transmission pipeline. If each transformative moment opens a potential vulnerability within the visioning apparatus, then every glitch testifies to the artificiality of the image. Moreover, every glitch potentially interrupts the political narratives be communicated in contemporary image production and transmission. Paradoxically, the current use of scripting to create glitch-like images has reimagined glitches as a discrete aesthetic category. This article counters this aestheticisation by asserting glitching as a disruption in communication. The argument will rely on scaled tests produced by one of the authors who show how duplicating the digital algorithmic patterns used within the digital imaging pipeline on any exterior building surface glitches the visual data captured within that image. Referencing image-based techniques drawn from the Baroque and contemporary modes of camouflage, it will be argued that the visual aberrations created by these algorithm-based patterned facades can modify strategically the ‘emission signature’ of selected parts of the urban fabric. In this way, the glitch becomes a way to intercede in the digital portrayal of city.
keywords	Surveillance, algorithms, diffraction, pattern, disruptive, optics
series	journal
email
last changed	2019/08/07 14:04

_id	ecaadesigradi2019_354
id	ecaadesigradi2019_354
authors	Mendes Correia, Ricardo and Guerreiro, Rosalia
year	2019
title	The Roots of 4IR in Architecture - A military drawing machine used for space perception in architecture
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 397-406
doi	https://doi.org/10.52842/conf.ecaade.2019.1.397
summary	This paper analyses how architecture became a pioneer discipline in digital interactivity research. It describes how that pioneer research derives from a lineage of researchers whose work spans more than two decades beginning in the early fifties. Military funds enabled the creation of the first computer graphic interfaces that evolved into a "drawing machine", the first interactive CAD, that made possible the role of architecture as a pioneering discipline in interactivity research. It is expected to demonstrate that the same architecture that nowadays uses mainly interactive digital design was one of first disciplines to research interactivity addressing a gap in the study of the link between architecture and interactivity.
keywords	CAD; interactivity research; architectural design; ;
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	caadria2019_126
id	caadria2019_126
authors	Ng, Jennifer Mei Yee, Khean, Nariddh, Madden, David, Fabbri, Alessandra, Gardner, Nicole, Haeusler, M. Hank and Zavoleas, Yannis
year	2019
title	Optimising Image Classification - Implementation of Convolutional Neural Network Algorithms to Distinguish Between Plans and Sections within the Architectural, Engineering and Construction (AEC) Industry
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 795-804
doi	https://doi.org/10.52842/conf.caadria.2019.2.795
summary	Modern communication between built environment professionals are governed by the effective exchange of digital models, blueprints and technical drawings. However, the increasing quantity of such digital files, in conjunction with inconsistent filing systems, increases the potential for human-error upon their look-up and retrieval. Further, current methods are manual, thus slow and resource intensive. Evidently, the architectural, engineering and construction (AEC) industry lacks an automated classification system capable of systematically identifying and categorising different drawings. To intercede, we aim to investigate artificially intelligent solutions capable of automatically identifying and retrieving a wide set of AEC files from a company's resource library. We present a convolutional neural network (CNN) model capable of processing large sets of technical drawings - such as sections, plans and elevations - and recognise their individual patterns and features, ultimately minimising laboriousness.
keywords	Convolutional Neural Network; Artificial Intelligence; Machine Learning; Classification; Filing architectural drawings.
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_550
id	ecaadesigradi2019_550
authors	Rhee, Jinmo, Cardoso Llach, Daniel and Krishnamurti, Ramesh
year	2019
title	Context-rich Urban Analysis Using Machine Learning - A case study in Pittsburgh, PA
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 343-352
doi	https://doi.org/10.52842/conf.ecaade.2019.3.343
summary	This paper reports on the analytical potential of machine learning methods for urban analysis. It documents a new method for data-driven urban analysis based on diagrammatic images describing each building in a city in relation to its immediate urban context. By statistically analyzing architectural and contextual features in this new dataset, the method can identify clusters of similar urban conditions and produce a detailed picture of a city's morphological structure. Remapping the clusters from data to 2D space, our method enables a new kind of urban plan that displays gradients of urban similarity. Taking Pittsburgh as a case study we demonstrate this method, and propose "morphological types" as a new category of urban analysis describing a given city's specific set of distinct morphological conditions. The paper concludes with a discussion of the implications of this method and its limitations, as well as its potentials for architecture, urban studies, and computation.
keywords	Urban Morphology; Machine Learning; Architectural Contexts; Urban Analysis; GIS
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_id	ecaadesigradi2019_327
id	ecaadesigradi2019_327
authors	Silva, Daniela, Paio, Alexandra and Sousa, José Pedro
year	2019
title	Reprogramming Practice - Revising design thinking through digital fabrication
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 379-386
doi	https://doi.org/10.52842/conf.ecaade.2019.1.379
summary	Questioning the importance and impact of design thinking methodologies in the architectural design studios is a backbone of architectural education in twenty first century. 3D printing and digital manufacturing are disruptive technologies that are changing architects and designers daily lives. These trends require new skills, based on a deep understanding of digital continuum from design to production, from generation to fabrication. This continuity transcends the merely instrumental contributions of a person-machine relationship to praxis, has begun to evolve as a medium that supports a continuous logic of design thinking and making. Design thinking methodologies associated with digital fabrication emerged as a leading technological and design issue of digital research and design. As designers, we are witnessing a no frontier between computational design and digital fabrication. For this paper is taken into consideration the work of two architecture studios that share a unique background on new methodologies by embracing the digital technology in their own practice. Their work reflects on new design methodologies facing the expansion of digital technology in architectural practice. This paper discusses the possibility of new design thinking methods driven by digital fabrication.
keywords	Design thinking; Digital Fabrication; AEC; Collaborative Design; Architectural Practice
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_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
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
doi	https://doi.org/10.52842/conf.ecaade.2023.2.327
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	ecaadesigradi2019_658
id	ecaadesigradi2019_658
authors	Stouffs, Rudi
year	2019
title	Predicates and Directives for a Parametric-associative Matching Mechanism for Shapes and Shape Grammars
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 403-412
doi	https://doi.org/10.52842/conf.ecaade.2019.2.403
summary	Predicates and directives are proposed to extend the versatility and expressivity of a shape rule specification 'language'. Specifically, a predicate serves to express a condition on the application of a parametric-associative shape rule that cannot simply be explicated within the left-hand side shape. A directive, on the other hand, is a value specification that is required when applying a parametric-associative shape rule, where this value specification cannot be derived from or expressed within the right-hand-side shape. We discuss the benefits of a set of predicates and directives to address seemingly simple requests that might actually be hard to express otherwise. Specifically, we elaborate on the motivation for introducing predicates and directives, and demonstrate the various predicates and directives in more detail, including their implementation.
keywords	shape rule; shape grammar; predicate; directive; parametric-associative rule
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

For more results click below: