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 94

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

_id	ecaade2021_203
id	ecaade2021_203
authors	Arora, Hardik, Bielski, Jessica, Eisenstadt, Viktor, Langenhan, Christoph, Ziegler, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Consistency Checker - An automatic constraint-based evaluator for housing spatial configurations
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 351-358
doi	https://doi.org/10.52842/conf.ecaade.2021.2.351
summary	The gradual rise of artificial intelligence (AI) and its increasing visibility among many research disciplines affected Computer-Aided Architectural Design (CAAD). Architectural deep learning (DL) approaches are being developed and published on a regular basis, such as retrieval (Sharma et al. 2017) or design style manipulation (Newton 2019; Silvestre et al. 2016). However, there seems to be no method to evaluate highly constrained spatial configurations for specific architectural domains (such as housing or office buildings) based on basic architectural principles and everyday practices. This paper introduces an automatic constraint-based consistency checker to evaluate the coherency of semantic spatial configurations of housing construction using a small set of design principles to evaluate our DL approaches. The consistency checker informs about the overall performance of a spatial configuration followed by whether it is open/closed and the constraints it didn't satisfy. This paper deals with the relation of spaces processed as mathematically formalized graphs contrary to existing model checking software like Solibri.
keywords	model checking, building information modeling, deep learning, data quality
series	eCAADe
email
last changed	2022/06/07 07:54

_id	caadria2016_343
id	caadria2016_343
authors	Asriana, Nova and Aswin Indraprastha
year	2016
title	Making Sense of Agent-based Simulation: Developing Design Strategy for Pedestrian-centric Urban Space
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 343-352
doi	https://doi.org/10.52842/conf.caadria.2016.343
summary	This study investigates the relationships of field observa- tion, multi-agent simulation and space-syntax theory in spatial config- uration for developing design strategy for a case study, a tourist hub area in Musi Riverside, Palembang. Having such potential advantage and to tackle existing social and urban issues, our study developed a design approach based on multi-agent simulation enhanced by space syntax theory. The goal of this study is a deep understanding of multi agent simulation through mechanism of validation using field obser- vation and by taking into account the existing urban features. The purpose is to develop design strategy of pedestrian-centric urban space to be functioned as a tourist hub based on computational modelling. Following the paths result of pedestrian flow by multi-agents simula- tion, we elaborated the analysis of facility programming by means of Space Syntax theory. It shows the ranking of facility programs based on their relative connectivity and integration. By merging this result, it assembles programs and their circulation spaces by means of compu- tational simulation. Experimenting in both fields show a novel ap- proach for pedestrian-centric design in urban scale, particularly since behavioural models rarely used in early stage of design process. It shows that multi-agent simulation should be coupled with field obser- vation.
keywords	Multi-agents simulation; network analysis; Space Syntax theory; design strategy; urban space
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	caadria2016_611
id	caadria2016_611
authors	Dritsas, Stylianos
year	2016
title	An Advanced Parametric Modelling Library for Architectural and Engineering Design
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 611-620
doi	https://doi.org/10.52842/conf.caadria.2016.611
summary	This paper presents a design computation system support- ing scientific computing methods relevant to architectural and engi- neering design under the paradigm of visual programming. The objec- tive of this research work is to expand and advance the palette of methods employed in academic and professional design environments. The tools contain methods for linear algebra, non-linear solvers, net- work analysis and algorithms for classical operational research prob- lems such as cutting and packing, clustering and routing. A few dec- ades ago the idea that computing would become so pervasive in the realm of architecture and engineering as it is today was confronted with deep scepticism. The thesis of this paper is that while it may be equally implausible that such methods are relevant today it may be the next natural evolution in the direction of design computation. The cur- rent state of the presented software package is still in early alpha ver- sion and it is available online for evaluation.
keywords	Design computation; parametric modelling; visual programming
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	caadria2016_539
id	caadria2016_539
authors	Lublasser, E.; J. Braumann, D. Goldbach and S. Brell-Cokcan
year	2016
title	Robotic Forming: Rapidly Generating 3D Forms and Structures through Incremental Forming
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 539-548
doi	https://doi.org/10.52842/conf.caadria.2016.539
summary	The past years have seen significant developments in the area of robotic design interfaces. Building upon visual programming environments, these interfaces now allow the creative industry to de- fine even complex fabrication processes in an easy, accessible way, while providing instant, production-immanent feedback. However, while these software tools greatly speed up the programming of robot- ic arms, many processes are still inherently slow: Subtractive process- es need to remove a large amount of material with comparably small tools, while additive processes are limited by the speed of the extruder and the properties of the extruded material. In this research we present a new method for incrementally shaping transparent polymer materi- als with a robotic arm, without requiring heat or dies for deep- drawing, thus allowing us to rapidly fabricate individual panels within a minimum of time.
keywords	Incremental forming; robotic fabrication; visual programming
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2016_881
id	caadria2016_881
authors	Silvestre, Joaquim; Yasushi Ikeda and Franc?ois Gue?na
year	2016
title	Artificial Imagination of Architecture with Deep Convolutional Neural Network
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 881-890
doi	https://doi.org/10.52842/conf.caadria.2016.881
summary	This paper attempts to determine if an Artificial Intelli- gence system using deep convolutional neural network (ConvNet) will be able to “imagine” architecture. Imagining architecture by means of algorithms can be affiliated to the research field of generative archi- tecture. ConvNet makes it possible to avoid that difficulty by automat- ically extracting and classifying these rules as features from large ex- ample data. Moreover, image-base rendering algorithms can manipu- late those abstract rules encoded in the ConvNet. From these rules and without constructing a prior 3D model, these algorithms can generate perspective of an architectural image. To conclude, establishing shape grammar with this automated system opens prospects for generative architecture with image-base rendering algorithms.
keywords	Machine learning; convolutional neural network; generative design; image-based rendering
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	sigradi2016_583
id	sigradi2016_583
authors	Chiarella, Mauro; Martini, Sebastián; Giraldi, Sebastián; Góngora, Nicolás; Picco, Camila
year	2016
title	Cultura Maker. Dispositivos, Prótesis Robóticas y Programación Visual en Arquitectura y Dise?o para eficiencia energética [Culture Maker. Devices, Prostheses Robotics and Visual Programming in Architecture and Design for energy efficiency.]
source	SIGraDi 2016 [Proceedings of the 20th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-7051-86-1] Argentina, Buenos Aires 9 - 11 November 2016, pp.961-968
summary	The Maker movement is the ability to be small and at the same time world; craftsmanship and innovative; high technology and low cost. The Maker movement is doing for physical products what the open source made by the software. The Maker culture emphasizes collaborative learning and distributed cognition. Its knowledge base repository and channels of exchange of ideas and information are: web sites; social networks; the Hackerspaces and Fab-Labs. Three experiences presented with devices; prostheses robotics and CNC machines, based on logical replacement; adaptation and generation. Its authors are undergraduate and graduate fellows Industrial Design and Architecture.
keywords	Maker culture; Prostheses Robotics; Visual Programming; Energy Efficiency; Adaptive Skin
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	sigradi2016_805
id	sigradi2016_805
authors	Cormack, Jordan; Sweet, Kevin S.
year	2016
title	Parametrically Fabricated Joints: Creating a Digital Workflow
source	SIGraDi 2016 [Proceedings of the 20th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-7051-86-1] Argentina, Buenos Aires 9 - 11 November 2016, pp.412-417
summary	Timber joinery for furniture and architectural purpose has always been identified as a skill or craft. The craft is the demonstration of hand machined skill and precision which is passed down or developed through the iteration of creation and refined reflection. Using digital fabrication techniques provides new, typically unexplored ways of creating and designing joints. It is as if these limitations which bind the ratio of complexity and use are stretched. This means that these joints, from a technical standpoint, can be more advanced than historically hand-made joints as digital machines are not bound by the limitations of the human. The research investigated in this paper explores the ability to create sets of joints in a parametric environment that will be produced with CNC machines, thus redefining the idea of the joint through contemporary tools of creation and fabrication. The research also aims to provide a seamless, digital workflow from the flexible, parametric creation of the joint to the final physical fabrication of it. Traditional joints, more simple in shape and assembly, were first digitally created to ease the educational challenges of learning a computational workflow that entailed the creation and fabrication of geometrically programmed joints. Following the programming and manufacturing of these traditional joints, more advanced and complex joints were created as the understanding of the capabilities of the software and CNC machines developed. The more complex and varied joints were taken from a CAD virtual environment and tested on a 3-axis CNC machine and 3D printer. The transformation from the virtual environment to the physical highlighted areas that required further research and testing. The programmed joint was then refined using the feedback from the digital to physical process creating a more robust joint that was informed by reality.
keywords	Joinery; digital fabrication; parametric; scripting; machining
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	acadia16_130
id	acadia16_130
authors	Koschitz, Duks; Ramagosa, Bernat; Rosenbaum, Eric
year	2016
title	Beetle Blocks: A New Visual Language for Designers and Makers
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 130-139
doi	https://doi.org/10.52842/conf.acadia.2016.130
summary	We are introducing a new teaching tool to show designers, architects, and artists procedural ways of constructing objects and space. Computational algorithms have been used in design for quite some time, but not all tools are very accessible to novice programmers, especially undergraduate students. ‘Beetle Blocks’ (beetleblocks.com) is a software environment that combines an easy-to-use graphical programming language with a generative model for 3D space, drawing on ‘turtle geometry,’ a geometry paradigm introduced by Abelson and Disessa, that uses a relative as opposed to an absolute coordinate system. With Beetle Blocks, designers are able to learn computational concepts and use them for their designs with more ease, as individual computational steps are made visually explicit. The beetle, the relative coordinate system, follows instructions as it moves about in 3D space. Anecdotal evidence from studio teaching in undergraduate programs shows that despite the early introduction of digital media and tools, architecture students still struggle with learning formal languages today. Beetle Blocks can significantly simplify the teaching of complex geometric ideas and we explain how this can be achieved via several examples. The blocks-based programming language can also be used to teach fundamental concepts of manufacturing and digital fabrication and we elucidate in this paper which possibilities are conducive for 2D and 3D designs. This project was previously implemented in other languages such as Flash, Processing and Scratch, but is now developed on top of Berkeley’s ‘Snap!’
keywords	generative design, design pedagogy, digital fabrication, tool-building, pedagogical tools
series	ACADIA
type	paper
email
last changed	2022/06/07 07:51

_id	ijac201614205
id	ijac201614205
authors	Leitao, Anto?nio; Ines Caetano and Hugo Correia
year	2016
title	Processing architecture
source	International Journal of Architectural Computing vol. 14 - no. 2, 147-157
summary	Programming promotes creative freedom but might require considerable effort to learn. The Processing language was created to simplify this learning process. Due to its graphical capabilities, the language has become very popular among the electronic arts and design communities. Unfortunately, this popularity could not be extended to the architecture community, which relies on traditional heavyweight computer-aided design and building information modeling applications that cannot be programmed using Processing. As a result, it becomes difficult for architects to take advantage of Processing. To solve this problem, we propose an implementation of Processing that runs in the context of the most used computer-aided design tools in architecture. Our implementation allows Processing to generate two- or three-dimensional models that are directly usable for architectural work. To this end, we also propose extensions to the language, including three-dimensional modeling primitives that dramatically simplify the effort needed for developing large and complex architectural models with Processing.
keywords	Generative Design, Programming, Processing, Architecture, 3D Modeling
series	journal
last changed	2016/06/13 08:34

_id	sigradi2016_508
id	sigradi2016_508
authors	Pazmino, Ana Veronica; Braga, Rodrigo; Pupo, Regiane
year	2016
title	Gest?o de projeto interdisciplinar: smart design, design de interaç?o, materializaç?o e projeto de alta complexidade [Management Interdisciplinary Project: Smart Design, Interaction Design, materialization and High Complexity Project]
source	SIGraDi 2016 [Proceedings of the 20th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-7051-86-1] Argentina, Buenos Aires 9 - 11 November 2016, pp.65-70
summary	This paper presents the management of interdisciplinary practice in design course at the Federal University of Santa Catarina in the design discipline with emphasis on interaction and technology. The work shows the project management used to facilitate the interrelation of design disciplines interaction, intelligent design and materialization through which the students developed an interactive product with the appropriation and application of programming knowledge with arduino, digital manufacturing and interaction. The results are qualitative in relation to students' learning and recommendations for an interdisciplinary design process in design courses.
keywords	Project management; interdisciplinarity; Intelligent Design; Interaction; Digital Manufacturing
series	SIGRADI
email
last changed	2021/03/28 19:59

_id	ascaad2016_052
id	ascaad2016_052
authors	Al-Badry, Sally; Cesar Cheng, Sebastian Lundberg and Georgios Berdos
year	2016
title	Living on the Edge - Reinventing the amphibiotic habitat of the Mesopotamian Marshlands
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 513-526
summary	The Mesopotamian Marshlands form one of the first landscapes where people started to transform and manipulate the natural environment in order to sustain human habitation. For thousands of years, people have transformed natural ecosystems into agricultural fields, residential clusters and other agglomerated environments to sustain long-term settlement. In this way, the development of human society has been intricately linked to the extraction, processing and consumption of natural resources. The Mesopotamian Marshlands, located in one of the hottest and most arid areas on the planet, formed a unique wetlands ecosystem, which apart from millions of people, sustained a very high number of wildlife and endemic species. Several historical, political, social and climatic changes, which densely occurred during the past century, completely destroyed the unique civilisation of the area, made all the wild flora and fauna disappear and forced hundreds of thousands of people to migrate. During the last decade, many efforts have been made to restore the marshlands. However, these efforts are lacking a comprehensive design strategy, coherent goals and deep understanding of the complex current geopolitical situation, making the restoration process an extremely difficult task. This work aims at providing strategies for recovering the Mesopotamian Marshlands, organising productive functions in order to sustain the local population and design a new inhabitation model, using advanced computational tools while taking into account the extreme climatic conditions and several unique cultural aspects. Part of the aim of this work is to advance the use of computation and explore the opportunities that digital tools afford in helping find solutions to complex design problems where various design variables need to be coordinated to satisfy the design goals. Today, advanced computation enables designers to use population consumption demands, ecological processes and environmental inputs as design parameters to develop more robust and resilient regional planning strategies. This work has the double aim of first, presenting a framework for re-inhabiting the Marshlands of Mesopotamia. Second, the work suggests a design methodology based on computer-aided design for developing and organising productive functions and patterns of human occupation in wetland environments.
series	ASCAAD
email
last changed	2017/05/25 13:34

_id	ijac201614202
id	ijac201614202
authors	Jutraz, Anja and Julie Le Moine
year	2016
title	Breaking out: New freedoms in urban (re)design work by adding immersive environments
source	International Journal of Architectural Computing vol. 14 - no. 2, 103-118
summary	Nowadays, urban planning and urban design are facing big changes in the use of different digital tools. Reaching out and engaging citizens and other stakeholders in urban design process are significant for good practice. Main problem discussed in this article is the lack of suitable tools/interfaces for instant collaboration between government, profession, and public. Article focuses on immersive environments, as full immersion could offer better notion of different proposals of urban design. As a case study, Immersive Terf is chosen; more exactly, article focuses on new approach and new development of tool Urban Redesign Terf. Deep immersive collaboration on design could free participant’s mind and increase level of freedom in design/planning process. Immersive environments have already been used in building information modeling (BIM) managment, but innovation part, presented here, are technological: significant changes in the software and walk-through big models, which is the base for urban design and urban planning process.
keywords	Urban planning, immersive environments, virtual worlds, digital tools, public participation
series	journal
last changed	2016/06/13 08:34

_id	ecaade2016_045
id	ecaade2016_045
authors	Lo, Tian Tian, Schnabel, Marc Aurel and Moleta, Tane
year	2016
title	A Simple System for Complex Mass Housing Design Collaborations - A system development framework
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 2, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 137-146
doi	https://doi.org/10.52842/conf.ecaade.2016.2.137
wos	WOS:000402064400013
summary	Through the lens of participatory mass housing the paper explores the conference theme of simplicity and complexity. A suitable home is a deep rooted desire in the heart of people, and everyone has their own vision of what is a suitable home. Yet the multi-faceted social needs of housing and how they are being designed and developed in mass housing buildings appear too complex and appear too costly that the process would involve direct user participations. The authors have developed a Computer Aided Participatory Housing Design System (CAPHDS) to allow end users (future occupants) become active stakeholders in the design process with the aid of computational design instruments. These tools allow end users to actively engage in the process. The paper describes how a mass housing design process can be broken down into a set of simple tasks that encourage the active engagement and joint development of end users and architects with the proposed design.
keywords	Participatory design; housing design system; computer-aided; bottom-up
series	eCAADe
email
last changed	2022/06/07 07:59

_id	acadia20_668
id	acadia20_668
authors	Pasquero, Claudia; Poletto, Marco
year	2020
title	Deep Green
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 668-677.
doi	https://doi.org/10.52842/conf.acadia.2020.1.668
summary	Ubiquitous computing enables us to decipher the biosphere’s anthropogenic dimension, what we call the Urbansphere (Pasquero and Poletto 2020). This machinic perspective unveils a new postanthropocentric reality, where the impact of artificial systems on the natural biosphere is indeed global, but their agency is no longer entirely human. This paper explores a protocol to design the Urbansphere, or what we may call the urbanization of the nonhuman, titled DeepGreen. With the development of DeepGreen, we are testing the potential to bring the interdependence of digital and biological intelligence to the core of architectural and urban design research. This is achieved by developing a new biocomputational design workflow that enables the pairing of what is algorithmically drawn with what is biologically grown (Pasquero and Poletto 2016). In other words, and more in detail, the paper will illustrate how generative adversarial network (GAN) algorithms (Radford, Metz, and Soumith 2015) can be trained to “behave” like a Physarum polycephalum, a unicellular organism endowed with surprising computational abilities and self-organizing behaviors that have made it popular among scientist and engineers alike (Adamatzky 2010) (Fig. 1). The trained GAN_Physarum is deployed as an urban design technique to test the potential of polycephalum intelligence in solving problems of urban remetabolization and in computing scenarios of urban morphogenesis within a nonhuman conceptual framework.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ascaad2016_049
id	ascaad2016_049
authors	Abdelsabour, Inas; Heba Farouk
year	2016
title	Impact of Using Structural Models on Form Finding - Incorporating Practical Structural Knowledge into Design Studio
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 483-492
summary	Physical Models as an architectural design tool, had major effect on architecture learning process. In structural form finding, it helped in improving visual design thinking to track form creation processes during form finding design stage. The aim is to study the impact of using physical models for second year architecture students in design studios learning. By analyzing and comparing students’ performance and progress; to clarify the effect of using physical models as a tool for designing progression, followed by analytical study on the students' structural models, in order to investigate the influence of models on their design educational progress. Research achieved that there were three basic phases the students pass through during form finding process when used manual physical models that improve the students' design capability.
series	ASCAAD
email
last changed	2017/05/25 13:33

_id	ascaad2016_047
id	ascaad2016_047
authors	Algeciras-Rodríguez, José
year	2016
title	Trained Architectonics
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 461-468
summary	The research presented here tests the capacity of artificial-neural-network (ANN) based multi-agent systems to be implemented in architectural design processes. Artificial Intelligence algorithms allow for a new approach to design, taking advantage of its generic functioning to produce meaningful outcomes. Experimentation within this project is based on Self-Organizing Maps (SOMs) and takes advantage of its behavior in topology to produce architectural geometry. SOMs as full stochastic processes involve randomness, uncertainty and unpredictability as key features to deal with during the design process. Following this behavior, SOMs are used to transmit information, which, instead of being copied, is reproduced after a learning (training) process. Pre-existent architectural objects are taken as learning models as they have been considered masterpieces. In this context, by defining the SOM input set, masterpieces become measurement elements and can be used to set a distance to the new element position in a comparatistic space. The characteristics of masterpieces get embedded within the code and are transmitted to 3D objects. SOM produced objects from a population with shared characteristics where the masterpiece position is its probabilistic center point.
series	ASCAAD
email
last changed	2017/05/25 13:33

_id	caadria2016_013
id	caadria2016_013
authors	Aschwanden, Gideon D.P.A.
year	2016
title	Neighbourhood detection with analytical tools
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 13-22
doi	https://doi.org/10.52842/conf.caadria.2016.013
summary	The increasing population size of cities makes the urban fabric ever more complex and more disintegrated into smaller areas, called neighbourhoods. This project applies methods from geoscience and software engineering to the process of identification of those neighbourhoods. Neighbourhoods, by nature, are defined by connec- tivity, centrality and similarity. Transport and geospatial datasets are used to detect the characteristics of places. An unsupervised learning algorithm is then applied to sort places according to their characteris- tics and detect areas with similar make up: the neighbourhood. The at- tributes can be static like land use or space syntax attributes as well as dynamic like transportation patterns over the course of a day. An un- supervised learning algorithm called Self Organizing Map is applied to project this high dimensional space constituting of places and their attributes to a two dimensional space where proximity is similarity and patterns can be detected – the neighbourhoods. To summarize, the proposed approach yields interesting insights into the structure of the urban fabric generated by human movement, interactions and the built environment. The approach represents a quantitative approach to ur- ban analysis. It reveals that the city is not a polychotomy of neigh- bourhoods but that neighbourhoods overlap and don’t have a sharp edge.
keywords	Data analytics; urban; learning algorithms; neighbourhood delineation
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	acadia16_362
id	acadia16_362
authors	Beesley, Philip; Ilgun, Zeliha, Asya; Bouron, Giselle; Kadish, David; Prosser, Jordan; Gorbet, Rob; Kulic, Dana; Nicholas, Paul; Zwierzycki, Mateusz
year	2016
title	Hybrid Sentient Canopy: An implementation and visualization of proprioreceptive curiosity-based machine learning
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 362-371
doi	https://doi.org/10.52842/conf.acadia.2016.362
summary	This paper describes the development of a sentient canopy that interacts with human visitors by using its own internal motivation. Modular curiosity-based machine learning behaviour is supported by a highly distributed system of microprocessor hardware integrated within interlinked cellular arrays of sound, light, kinetic actuators and proprioreceptive sensors in a resilient physical scaffolding system. The curiosity-based system involves exploration by employing an expert system composed of archives of information from preceding behaviours, calculating potential behaviours together with locations and applications, executing behaviour and comparing result to prediction. Prototype architectural structures entitled Sentient Canopy and Sentient Chamber developed during 2015 and 2016 were developed to support this interactive behaviour, integrating new communications protocols and firmware, and a hybrid proprioreceptive system that configured new electronics with sound, light, and motion sensing capable of internal machine sensing and externally- oriented sensing for human interaction. Proprioreception was implemented by producing custom electronics serving photoresistors, pitch-sensing microphones, and accelerometers for motion and position, coupled to sound, light and motion-based actuators and additional infrared sensors designed for sensing of human gestures. This configuration provided the machine system with the ability to calculate and detect real-time behaviour and to compare this to models of behaviour predicted within scripted routines. Testbeds located at the Living Architecture Systems Group/Philip Beesley Architect Inc. (LASG/PBAI, Waterloo/Toronto), Centre for Information Technology (CITA, Copenhagen) National Academy of Sciences (NAS) in Washington DC are illustrated.
keywords	intedisciplinary/collaborative design, intelligent environments, artificial intelligence, sensate systems
series	ACADIA
type	paper
email
last changed	2022/06/07 07:54

_id	ecaade2016_079
id	ecaade2016_079
authors	Cheng, Chi-Li and Hou, June-Hao
year	2016
title	Biomimetic Robotic Construction Process - An approach for adapting mass irregular-shaped natural materials
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 1, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 133-142
doi	https://doi.org/10.52842/conf.ecaade.2016.1.133
wos	WOS:000402063700015
summary	Beaver dams are formed by two main processes. One is that beavers select proper woods for constructing. The other one is that streams aggregate those woods to be assembled. Using this approach to construction structure is suitable for natural environment. In this paper, we attempt to develop a construction process which is suitable for all-terrain construction robot in the future. This construction process is inspired by beavers' construction behavior in nature. Beavers select proper sticks to make the structure stable. We predict that particular properties of sticks contribute gravity-driven assembly of wood structure. Thus, we implement the system with machine learning to find proper properties of sticks to improve selection mechanism of construction process. During this construction process, 3D scanner on robotic arm scans and recognizes sticks on terrain, and then robot will select proper sticks and place them. After placement, the system will scan and record the results for learning mechanism.
keywords	Biomimetic Design; Machine Learning; Natural Material; Point Cloud Analysis; Robotic Fabrication
series	eCAADe
email
last changed	2022/06/07 07:55

_id	ascaad2016_027
id	ascaad2016_027
authors	Cocho-Bermejo, Ana
year	2016
title	Time in Adaptable Architecture - Deployable emergency intelligent membrane
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 249-258
summary	The term "Parametricism" widespread mainly by Patrick Schumacher (Schumacher, 2008) is worthy of study. Developing the concept of Human Oriented Parametric Architecture, the need of implementing time as the lost parameter in current adaptive design techniques will be discussed. Morphogenetic processes ideas will be discussed through the principle of an adaptable membrane as a case study. A model implementing a unique Arduino[i] on the façade will control its patterns performance through an Artificial Neural Network that will understand the kind of scenario the building is in, activating a Genetic Algorithm that will optimize the insulation performance of the ETFE pillows. The system will work with a global behavior for façade pattern performance and with a local one for each pillow, giving the option of individual sun-shading control. Machine learning implementation will give the façade the possibility to learn from the efficacy of its decisions through time, eliminating the need of a general on-off behavior.
series	ASCAAD
email
last changed	2017/05/25 13:31

For more results click below: