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 572

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

_id	ddss2004_d-269
id	ddss2004_d-269
authors	Beetz, J., J. van Leeuwen, and B. de Vries
year	2004
title	Towards a Multi Agent System for the Support of Collaborative Design
source	Van Leeuwen, J.P. and H.J.P. Timmermans (eds.) Developments in Design & Decision Support Systems in Architecture and Urban Planning, Eindhoven: Eindhoven University of Technology, ISBN 90-6814-155-4, p. 269-280
summary	In this paper we are drafting the outline of a framework for a Multi Agent System (MAS) for the support of Collaborative Design in the architectural domain. The system we are proposing makes use of Machine Learning (ML) techniques to infer personalized knowledge from observing a users’ action in a generic working environment using standard tools such as CAD packages. We introduce and discuss possible strategies to combine Concept Modelling (CM)-based approaches using existing ontologies with statistical analysis of action sequences within a domain specific application. In a later step, Agent technologies will be used to gather additional related information from external resources such as examples of similar problems on the users hard disk, from corresponding work of team-members within an intranet or from advises of expert from different knowledge domains, themselves represented by agents. As users deny or reward resulting proposals offered by the agent(s) through an interface the system will be enhanced over time using methods like Reinforced Learning.
keywords	Multi Agent Systems, Design & Decision Support Systems, Collaborative Design, Human Computer Interfaces, Machine learning, Data Mining
series	DDSS
last changed	2004/07/03 22:13

_id	avocaad_2003_19
id	avocaad_2003_19
authors	Rudi Stouffs, Maia Engeli and Bige Tunçer
year	2003
title	Mediated discourse as a form of architectonic intervention
source	LOCAL VALUES in a NETWORKED DESIGN WORLD - ADDED VALUE OF COMPUTER AIDED ARCHITECTURAL DESIGN, Stellingwerff, Martijn and Verbeke, Johan (Eds.), (2004) DUP Science - Delft University Press, ISBN 90-407-2507-1.
summary	We are currently exploring the concept of mediated discourse in relation to an architectonic intervention and urban transformation project in an educational project and elective course. Led by faculty and artists, students are offered the ability to experiment with various media in the design and development of a multidisciplinary discourse. A web-based elearning environment also allows the students’ activities to form part of a larger discourse that takes place among all participants, including the public. In this paper, we describe the concept of mediated discourse and the various dimensions we distinguish, we present the educational project and its various aspects and participants’ roles, we consider the internationalisation of this educational project in a future instance of the course, and we describe the characteristics of the web environment in the context of an educational and software development project for a multimedia learning environment to support group work and discourse.
keywords	Architecture, Local values, Globalisation, Computer Aided Architectural Design
series	AVOCAAD
email
last changed	2006/01/16 21:38

_id	ddss2004_ra-161
id	ddss2004_ra-161
authors	Bandini, S., S. Manzoni, and G. Vizzari
year	2004
title	Crowd Modeling and Simulation
source	Van Leeuwen, J.P. and H.J.P. Timmermans (eds.) Recent Advances in Design & Decision Support Systems in Architecture and Urban Planning, Dordrecht: Kluwer Academic Publishers, ISBN: 1-4020-2408-8, p. 161-175
summary	The paper introduces a Multi Agent Systems (MAS) approach to crowd modelling and simulation, based on the Situated Cellular Agents (SCA) model. This is a special class of Multilayered Multi Agent Situated System (MMASS), exploiting basic elements of Cellular Automata. In particular SCA model provides an explicit spatial representation and the definition of adjacency geometries, but also a concept of autonomous agent, provided with an internal architecture, an individual state and behaviour. The latter provides different means of space-mediated interaction among agents: synchronous, between adjacent agents, and asynchronous among at-a-distance entities. Heterogeneous entities may be modelled through the specification of different agent types, defining different behaviours and perceptive capabilities. After a brief description of the model, its application to simple crowd behaviours will be given, and an application providing the integration of a bidimensional simulator based on this model and a 3D modelling application (3D Studio) will also be described. The adoption of this kind of system allows the specification and simulation of an architectural design with reference to the behaviour of entities that will act in it. The system is also able to easily produce a realistic visualization of the simulation, in order to facilitate the evaluation of the design and the communication with involved decision-makers. In fact, while experts often require only abstract and analytical results deriving from a quantitative analysis of simulation results, other people involved in the decision-making process related to the design may be helped by qualitative aspects better represented by other forms of graphical visualization.
keywords	Multi-Agent Systems, 3D modelling, Simulation
series	DDSS
last changed	2004/07/03 22:13

_id	410caadria2004
id	410caadria2004
authors	Chiung-Hui Chen, Hui-Tin Lin, Mao-Lin Chiu
year	2004
title	A Scenario-Based Agent System for Digital City Interaction
source	CAADRIA 2004 [Proceedings of the 9th International Conference on Computer Aided Architectural Design Research in Asia / ISBN 89-7141-648-3] Seoul Korea 28-30 April 2004, pp. 693-706
doi	https://doi.org/10.52842/conf.caadria.2004.693
summary	Urban design involves coordination and communication for collecting consensus among citizens and developing the design strategy and spatial program. While these are web-based systems for representing the real world actions, there is lack of human interaction for receiving feedbacks during the process. Therefore, the purpose of this study is to introduce the agents into the participatory design process (PDP) based on scenarios. This paper has developed a webbased system prototype to demonstrate how the agent can interact with users and how the interface facilitates incremental design. We present a participatory design project in an old street to illustrate how the Scenario-Based Agent System (SBAS) model functions in a real application. Meanwhile, four issues will be discussed in regarding with building a learning interaction agent as an actor.
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	avocaad_2003_18
id	avocaad_2003_18
authors	Henri Achten, Jos van Leeuwen and Sverker Fridqvist
year	2003
title	Communicating Concepts for Shared Understanding: A Multi-Agent Approach
source	LOCAL VALUES in a NETWORKED DESIGN WORLD - ADDED VALUE OF COMPUTER AIDED ARCHITECTURAL DESIGN, Stellingwerff, Martijn and Verbeke, Johan (Eds.), (2004) DUP Science - Delft University Press, ISBN 90-407-2507-1.
summary	Capturing and sharing design concepts is necessary if we want to support the design process by means of Information & Communication Technology (ICT). Standardized concepts are important for support at the end of the design process when designs need to conform to set standards and norms, and in order to enable communication, but are less useful in the early design stages. We propose an approach that takes into account a more developmental attitude that will be better suited for design support and the sharing of design concepts. In this approach, design concepts are formalised by means of a technology called concept modelling. Capturing and exchange of concepts are based on a multi-agent approach. The whole of concepts that are used in a domain or for a design task can be considered a design ontology. In this paper we outline the motivations for the research, outline the basic approach in the research work, and identify the major challenges and research problems that need to be tackled.
keywords	Architecture, Local values, Globalisation, Computer Aided Architectural Design
series	AVOCAAD
email
last changed	2006/01/16 21:38

_id	509caadria2004
id	509caadria2004
authors	Jaewook Lee, Yongwook Jeong, Seung Wook Kim, Yehuda E. Kalay
year	2004
title	Intelligent Behavior Control of 3D Objects in Virtual Environments
source	CAADRIA 2004 [Proceedings of the 9th International Conference on Computer Aided Architectural Design Research in Asia / ISBN 89-7141-648-3] Seoul Korea 28-30 April 2004, pp. 845-856
doi	https://doi.org/10.52842/conf.caadria.2004.845
summary	Cyberspace is more malleable than a physical environment, so it can afford much wider range of responsiveness. By applying the concept of place-making, we are experimenting virtual environments which are responsive to their users’ context-specific needs. Since objects are essential components that anchor the users’ various activities, having interactive objects in a 3D virtual environment is a major design concern for developing a dynamic and experience-rich virtual environment. We propose a layered agent model for intelligent behavior control of 3D objects, based on constraint solving process.
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	110caadria2004
id	110caadria2004
authors	John S. Gero and Wei Peng
year	2004
title	A Situated Agent-Based Design Assistant
source	CAADRIA 2004 [Proceedings of the 9th International Conference on Computer Aided Architectural Design Research in Asia / ISBN 89-7141-648-3] Seoul Korea 28-30 April 2004, pp. 145-158
doi	https://doi.org/10.52842/conf.caadria.2004.145
summary	This paper introduces a situated agent-based design assistant. The agent is wrapped around an existing design tool in order to adapt that design tool to its use. Current design tools are unchanged by their use and as a consequence as the designer develops experience in using the tool, the tool remains the same. Such an agent is able to learn from its interactions with environments through its “experience”. This learning is based on situated representation mechanisms and a constructive memory system. The agent wrapper will be able to adapt the tool’s behaviours to its use and as a result improve the tool’s usability.
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	cf2011_p157
id	cf2011_p157
authors	Boton, Conrad; Kubicki Sylvain, Halin Gilles
year	2011
title	Understanding Pre-Construction Simulation Activities to Adapt Visualization in 4D CAD Collaborative Tools
source	Computer Aided Architectural Design Futures 2011 [Proceedings of the 14th International Conference on Computer Aided Architectural Design Futures / ISBN 9782874561429] Liege (Belgium) 4-8 July 2011, pp. 477-492.
summary	Increasing productivity and efficiency is an important issue in the AEC field. This area is mainly characterized by fragmentation, heterogeneous teams with low lifetimes and many uncertainties. 4D CAD is one of the greatest innovations in recent years. It consists in linking a 3D model of the building with the works planning in order to simulate the construction evolution over time. 4D CAD can fill several needs from design to project management through constructivity analysis and tasks planning (Tommelein 2003). The literature shows that several applications have been proposed to improve the 4D CAD use (Chau et al. 2004; Lu et al. 2007; Seok & al. 2009). In addition, studies have shown the real impact of 4D CAD use in construction projects (Staub-French & Khanzode 2007; Dawood & Sika 2007). More recently, Mahalingam et al. (2010) showed that the collaborative use of 4D CAD is particularly useful during the pre-construction phase for comparing the constructability of working methods, for visually identifying conflicts and clashes (overlaps), and as visual tool for practitioners to discuss and to plan project progress. So the advantage of the 4D CAD collaborative use is demonstrated. Moreover, several studies have been conducted both in the scientific community and in the industrial world to improve it (Zhou et al. 2009; Kang et al. 2007). But an important need that remains in collaborative 4D CAD use in construction projects is about the adaptation of visualization to the users business needs. Indeed, construction projects have very specific characteristics (fragmentation, variable team, different roles from one project to another). Moreover, in the AEC field several visualization techniques can represent the same concept and actors choose one or another of these techniques according to their specific needs related to the task they have to perform. For example, the tasks planning may be represented by a Gantt chart or by a PERT network and the building elements can be depicted with a 3D model or a 2D plan. The classical view (3D + Gantt) proposed to all practitioners in the available 4D tools seems therefore not suiting the needs of all. So, our research is based on the hypothesis that adapting the visualization to individual business needs could significantly improve the collaboration. This work relies on previous ones and aim to develop a method 1) to choose the best suited views for performed tasks and 2) to compose adapted multiple views for each actor, that we call ‚Äúbusiness views‚Äù. We propose a 4 steps-method to compose business views. The first step identifies the users‚Äô business needs, defining the individual practices performed by each actor, identifying his business tasks and his information needs. The second step identifies the visualization needs related to the identified business needs. For this purpose, the user‚Äôs interactions and visualization tasks are described. This enables choosing the most appropriate visualization techniques for each need (step 3). At this step, it is important to describe the visualization techniques and to be able to compare them. Therefore, we proposed a business view metamodel. The final step (step 4) selects the adapted views, defines the coordination mechanisms and the interaction principles in order to compose coordinated visualizations. A final step consists in a validation work to ensure that the composed views really match to the described business needs. This paper presents the latest version of the method and especially presents our latest works about its first and second steps. These include making more generic the business tasks description in order to be applicable within most of construction projects and enabling to make correspondence with visualization tasks.
keywords	Pre-construction, Simulation, 4D CAD, Collaboration, Computer Supported Cooperative Work, Human-Computer Interface, Information visualization, Business view, Model driven engineering
series	CAAD Futures
email
last changed	2012/02/11 19:21

_id	caadria2004_k-1
id	caadria2004_k-1
authors	Kalay, Yehuda E.
year	2004
title	CONTEXTUALIZATION AND EMBODIMENT IN CYBERSPACE
source	CAADRIA 2004 [Proceedings of the 9th International Conference on Computer Aided Architectural Design Research in Asia / ISBN 89-7141-648-3] Seoul Korea 28-30 April 2004, pp. 5-14
doi	https://doi.org/10.52842/conf.caadria.2004.005
summary	The introduction of VRML (Virtual Reality Markup Language) in 1994, and other similar web-enabled dynamic modeling software (such as SGI’s Open Inventor and WebSpace), have created a rush to develop on-line 3D virtual environments, with purposes ranging from art, to entertainment, to shopping, to culture and education. Some developers took their cues from the science fiction literature of Gibson (1984), Stephenson (1992), and others. Many were web-extensions to single-player video games. But most were created as a direct extension to our new-found ability to digitally model 3D spaces and to endow them with interactive control and pseudo-inhabitation. Surprisingly, this technologically-driven stampede paid little attention to the core principles of place-making and presence, derived from architecture and cognitive science, respectively: two principles that could and should inform the essence of the virtual place experience and help steer its development. Why are the principles of place-making and presence important for the development of virtual environments? Why not simply be content with our ability to create realistically-looking 3D worlds that we can visit remotely? What could we possibly learn about making these worlds better, had we understood the essence of place and presence? To answer these questions we cannot look at place-making (both physical and virtual) from a 3D space-making point of view alone, because places are not an end unto themselves. Rather, places must be considered a locus of contextualization and embodiment that ground human activities and give them meaning. In doing so, places acquire a meaning of their own, which facilitates, improves, and enriches many aspects of our lives. They provide us with a means to interpret the activities of others and to direct our own actions. Such meaning is comprised of the social and cultural conceptions and behaviors imprinted on the environment by the presence and activities of its inhabitants, who in turn, ‘read’ by them through their own corporeal embodiment of the same environment. This transactional relationship between the physical aspects of an environment, its social/cultural context, and our own embodiment of it, combine to create what is known as a sense of place: the psychological, physical, social, and cultural framework that helps us interpret the world around us, and directs our own behavior in it. In turn, it is our own (as well as others’) presence in that environment that gives it meaning, and shapes its social/cultural character. By understanding the essence of place-ness in general, and in cyberspace in particular, we can create virtual places that can better support Internet-based activities, and make them equal to, in some cases even better than their physical counterparts. One of the activities that stands to benefit most from understanding the concept of cyber-places is learning—an interpersonal activity that requires the co-presence of others (a teacher and/or fellow learners), who can point out the difference between what matters and what does not, and produce an emotional involvement that helps students learn. Thus, while many administrators and educators rush to develop webbased remote learning sites, to leverage the economic advantages of one-tomany learning modalities, these sites deprive learners of the contextualization and embodiment inherent in brick-and-mortar learning institutions, and which are needed to support the activity of learning. Can these qualities be achieved in virtual learning environments? If so, how? These are some of the questions this talk will try to answer by presenting a virtual place-making methodology and its experimental implementation, intended to create a sense of place through contextualization and embodiment in virtual learning environments.
series	CAADRIA
type	normal paper
last changed	2022/06/07 07:52

_id	2004_105
id	2004_105
authors	Petric, Jelena and Maver, Tom
year	2004
title	Computer Aided Design Appraisal - A Modest Experiment
source	Architecture in the Network Society [22nd eCAADe Conference Proceedings / ISBN 0-9541183-2-4] Copenhagen (Denmark) 15-18 September 2004, pp. 105-111
doi	https://doi.org/10.52842/conf.ecaade.2004.105
summary	The paper starts with a re-iteration of the concept of appraisal of digital prototypes during the early phases of the architectural design activity and with a summary of research and development from the early seventies to the current time; the use of appraisal by progressive practices is described in the context of the company Integrated Environmental Systems. The paper then focuses as an experiment which set out to determine how the information delivered by the computer based appraisal of virtual prototypes is ordered and used by professionals in the evaluation of design alternatives. The information provided to the professionals is detailed and their self-assessment of their management and utilsation of the data is reported, together with their critique of the experience. Conclusions are drawn and future research directions proposed.
keywords	Appraisal, Evaluation, Design Alternatives, Performance, Experiment
series	eCAADe
last changed	2022/06/07 08:00

_id	a0d4
id	a0d4
authors	Rosa Enrich, Andrea Carnicero, Gustavo Fornari & Pedro Orazzi
year	2004
title	ANALYSIS AND EVALUATION OF MATHEMATICAL LEARNING STRUCTURES
source	Proceedings of the Fourth International Conference of Mathematics & Design, Spetial Edition of the Journal of Mathematics & Design, Volume 4, No.1, pp. 13-21.
summary	Abstract: A series of practical tasks have been done under the general name of “Surfaces in invisible cities”. Each task was based on a story taken from the book The Invisible Cities by Italo Calvino. The research carried out allows to design a pedagogical project which makes evident , generates and connects several intentions, motivations and learning structures. It proposes the use of multi- level languages and readings. Therefore, each task takes more time than that of the proposed mathematical class. Its implementation generates a broader view than that seen at the time of design. From the detailed analysis of the results obtained, the following diverse pedagogical aspects of this work project arise: a. The use of several multiple intelligence: Howard Gardner (1985) found that a man has several distinct intelligence types among which Logical-Mathematical; Spatial; Linguistic -oriented; Musical; Intra-personal; Kinesthetic-Corporal; Interpersonal stand out. Only those types used in the task will be analyzed, making a brief description of each type. b. The architectonic-city planning aspects: architectonic-city planning interpretation of the space imagined after reading the text, with the purpose of identifying figures, shapes, volumes and colors which are expressed via an analogous space. They consist of visual, architectonic and territorial speculations without a rigorous spatial theory and it is pretended that they possess a technical precision at mathematical concept level. c. The mathematical contents: a study of the conical and square shapes present in the designs done and used in a creative manner in students’ compositions following the reading of the story chosen is carried out. An analysis of shapes is performed and mathematical problems are posed within the design context. Traditional sketching methods have been used in task solving and the possibilities offered by the virtual tools are analyzed. Emphasis has been put on the vertical and horizontal interchanges in the Chair, generating changes in knowledge transmission perspectives, thus allowing the sharing of contents, abilities and resources. The architectonic work imagined and created by the students will focus on these different working lines creating a harmonious and significant whole. The work is the result of multiple connections and creative proposals.
keywords	city, geometry, multiple intelligence
series	other
type	normal paper
email
last changed	2005/04/07 12:46

_id	caadria2018_016
id	caadria2018_016
authors	Zahedi, Ata and Petzold, Frank
year	2018
title	Utilization of Simulation Tools in Early Design Phases Through Adaptive Detailing Strategies
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 11-20
doi	https://doi.org/10.52842/conf.caadria.2018.2.011
summary	Decisions taken at early stages of building design have a significant effect on the planning steps for the entire lifetime of the project as well as the performance of the building throughout its lifecycle (MacLeamy 2004). Building Information Modelling (BIM) could bring forward and enhance the planning and decision-making processes by enabling the direct reuse of data hold by the model for diverse analysis and simulation tasks (Borrmann et al. 2015). The architect today besides a couple of simplified simulation tools almost exclusively uses his know-how for evaluating and comparing design variants in the early stages of design. This paper focuses on finding new ways to facilitate the use of analytical and simulation tools during the important early phases of conceptual building design, where the models are partially incomplete. The necessary enrichment and proper detailing of the design model could be achieved by means of dialogue-based interaction concepts with analytical and simulation tools through adaptive detailing strategies. This concept is explained using an example scenario for design process. A generic description of the aimed dialog-based interface to various simulation tools will also be discussed in this paper using an example scenario.
keywords	BIM; Early Design Stages; Adaptive Detailing ; Communication Protocols; Design Variants
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	2004_050
id	2004_050
authors	Chiu, Mao-Lin
year	2004
title	Curious Agents in Virtual Exhibitive Environments Simulative Human-Computer Interaction
source	Architecture in the Network Society [22nd eCAADe Conference Proceedings / ISBN 0-9541183-2-4] Copenhagen (Denmark) 15-18 September 2004, pp. 50-57
doi	https://doi.org/10.52842/conf.ecaade.2004.050
summary	The creation of virtual environments is becoming the alternative for spatial design, while what can be expanded from the real environment is often questioned. This paper proposes the agent interface based on curiosity to create human computer interaction in virtual exhibitive environments. From a social and behavioral point of view, this research explores the use of places as metaphors and simulative human-computer interactions in virtual environments by reactive agents and proactive curious agents based on situation detection. The process is demonstrated by a museum exhibition project. Both the physical and the virtual environment are built, and studied the human behaviors and experiences from their presence at both environments. Agent interfaces are adopted in the virtual environment to enhance people-to-people and people-to-place interactions. The development process, the observation, the interface agent, and discussion based on the findings are presented.
keywords	Virtual Environment; Digital Design; Agent; Curiosity; Interfaces
series	eCAADe
email
last changed	2022/06/07 07:56

_id	acadia04_150
id	acadia04_150
authors	Clarke, Cory
year	2004
title	The Siren's Call
source	Fabrication: Examining the Digital Practice of Architecture [Proceedings of the 23rd Annual Conference of the Association for Computer Aided Design in Architecture and the 2004 Conference of the AIA Technology in Architectural Practice Knowledge Community / ISBN 0-9696665-2-7] Cambridge (Ontario) 8-14 November, 2004, 150-161
doi	https://doi.org/10.52842/conf.acadia.2004.150
summary	This paper presents an account of our research and development of processes providing seamless transition from design to fabrication. The narrative of our design, development, and prototyping experi¬ments spans seven years, including our current project, the Trusset software/structural system. Trusset is a combined building system and agent-based software design tool. The building system is based on a differential space-truss designed for fabrication entirely with computer numerically controlled (CNC) linear cutting devices, such as laser cut¬ters or three-axis mills. The software component is a set of agent-based design tools for developing surfaces and envelopes formally suitable to be built using the space-truss structure. Developed in parallel, the soft¬ware and building components combine within the Trusset system to provide a seamless pipeline from design to fabrication and assembly. The story of the development of software components and structural system, leading to the Trusset, act as a means of discussing the larger issues framing the research: the potential pitfalls and benefits of design and fabrication integration via the computer.
keywords	Fabrication, Space-truss, Structure
series	ACADIA
email
last changed	2022/06/07 07:56

_id	ijac20032206
id	ijac20032206
authors	Cory Clarke; Phillip Anzalone
year	2004
title	Trusset: Parallel Development of Software and Construction Systems for Space-Truss Structures
source	International Journal of Architectural Computing vol. 2 - no. 2
summary	This paper documents our current progress on theparallel development of a building system andcorresponding agent-based software design tools;together the two produce a seamless pipeline fromdesign to fabrication and assembly. The building systemis a clad differential space-truss designed forfabrication entirely with computer numericallycontrolled (CNC) linear cutting devices such as CNClaser cutters or two-axis mills. The softwarecomponent is a set of agent-based design tools fordeveloping surfaces and envelopes formally suitable tobe built using our space-truss system.
series	journal
email
more	http://www.multi-science.co.uk/ijac.htm
last changed	2007/03/04 07:08

_id	ddss2004_ra-33
id	ddss2004_ra-33
authors	Diappi, L., P. Bolchim, and M. Buscema
year	2004
title	Improved Understanding of Urban Sprawl Using Neural Networks
source	Van Leeuwen, J.P. and H.J.P. Timmermans (eds.) Recent Advances in Design & Decision Support Systems in Architecture and Urban Planning, Dordrecht: Kluwer Academic Publishers, ISBN: 14020-2408-8, p. 33-49
summary	It is widely accepted that the spatial pattern of settlements is a crucial factor affecting quality of life and environmental sustainability, but few recent studies have attempted to examine the phenomenon of sprawl by modelling the process rather than adopting a descriptive approach. The issue was partly addressed by models of land use and transportation which were mainly developed in the UK and US in the 1970s and 1980s, but the major advances were made in the area of modelling transportation, while very little was achieved in the area of spatial and temporal land use. Models of land use and transportation are well-established tools, based on explicit, exogenouslyformulated rules within a theoretical framework. The new approaches of artificial intelligence, and in particular, systems involving parallel processing, (Neural Networks, Cellular Automata and Multi-Agent Systems) defined by the expression “Neurocomputing”, allow problems to be approached in the reverse, bottom-up, direction by discovering rules, relationships and scenarios from a database. In this article we examine the hypothesis that territorial micro-transformations occur according to a local logic, i.e. according to use, accessibility, the presence of services and conditions of centrality, periphericity or isolation of each territorial “cell” relative to its surroundings. The prediction capabilities of different architectures of supervised Neural networks are implemented to the south Metropolitan area of Milan at two different temporal thresholds and discussed. Starting from data on land use in 1980 and 1994 and by subdividing the area into square cells on an orthogonal grid, the model produces a spatial and functional map of urbanisation in 2008. An implementation of the SOM (Self Organizing Map) processing to the Data Base allows the typologies of transformation to be identified, i.e. the classes of area which are transformed in the same way and which give rise to territorial morphologies; this is an interesting by-product of the approach.
keywords	Neural Networks, Self-Organizing Maps, Land-Use Dynamics, Supervised Networks
series	DDSS
last changed	2004/07/03 22:13

_id	sigradi2004_404
id	sigradi2004_404
authors	Eduardo Lyon
year	2004
title	Artificial intelligence and emergence in architecture: A multi-agent based model for design processes
source	SIGraDi 2004 - [Proceedings of the 8th Iberoamerican Congress of Digital Graphics] Porte Alegre - Brasil 10-12 november 2004
summary	The purpose of this paper is to provide an alternative approach to traditional design process formulation and elaboration. In contrast to traditional models of design process fundamentally defined by the abstract manipulation of objects, this study recognizes that the resources available for rethinking architecture are to be found in a reformulation of its theory and practice. This reformulation should be based on non-linear design processes in which dynamic emergence and invention take the place of a linear design process fixed on a particular object evolution. Design is possible to be defined in two different and commonly confused ways; one as the process of designing or design activity and the second as the product of designing. In this study, we are concerned with design as a process to emphasize the misconceptions, derived from studying design products solely. Therefore, we propose a change from a design knowledge based on objects to a one focused on design as a network of processes.
series	SIGRADI
email
last changed	2016/03/10 09:51

_id	2004_148
id	2004_148
authors	Fatah gen. Schieck, A., Penn, A., Mottram, C., Strothmann, C., Ohlenburg, J., Broll, W. and Aish, F.
year	2004
title	Interactive Space Generation through Play - Exploring Form Creation and the Role of Simulation on the Design Table
source	Architecture in the Network Society [22nd eCAADe Conference Proceedings / ISBN 0-9541183-2-4] Copenhagen (Denmark) 15-18 September 2004, pp. 148-158
doi	https://doi.org/10.52842/conf.ecaade.2004.148
summary	In this paper we report on recent developments in ARTHUR: an approach to support complex design and planning decisions for architects together with the simulation of pedestrian movement and the integration of existing CAD tools on the design table. Following a brief introduction, past and current work that has taken a similar approach will be reviewed. Next we describe a scenario that integrates agent-based simulations of pedestrian movement with space creation, and then give an overview of the system before finally discussing findings related to recent user evaluation studies of the system. This paper suggests that the integration of simulated pedestrian movement on the design table, while going through a cycle of reflection-in-action, plays a vital role in exploring possible design solutions and encourages new and different ways of thinking about design problems.
keywords	Tangible User Interface, Pedestrian Simulation, Collaboration, Augmented Reality (AR), CAD Integration
series	eCAADe
last changed	2022/06/07 07:55

_id	ddss2004_d-111
id	ddss2004_d-111
authors	Kitazawa, K. and M. Batty
year	2004
title	Pedestrian Behaviour Modelling
source	Van Leeuwen, J.P. and H.J.P. Timmermans (eds.) Developments in Design & Decision Support Systems in Architecture and Urban Planning, Eindhoven: Eindhoven University of Technology, ISBN 90-6814-155-4, p. 111-126
summary	This paper introduces a study of pedestrian behaviour modelling which incorporates ideas about agent-based systems and the traffic models based on the utility-maximization theory. The aim of this study is to examine the applicable scope of one of the basic assumptions in existing spatial behaviour models; the route with shortest distance maximizes the utility of each pedestrian’s travel. Although shortest-path models have been widely used in the field of Traffic management to predict routing behaviour, there can be seen a lot of erratic behaviour in urban areas, shopping migration behaviour for instance, which can not be explained by them. Thus, it is important to identify other possible influential factors on their utility maximization process in order to develop more explicable models of pedestrian movements. In this study, we implemented a simulation model using the shortest-path model as one of evaluation criteria of Genetic Algorithms (GA) to computationally emulate retail movements of shoppers in a big shopping centre and to test the accuracy of the model by comparison between the routes estimated by the model and actual trajectories of shoppers. This simulation system will be used as a platform for further modelling.
keywords	Pedestrian Modelling, Retail Movement, Shortest-Path, Genetic Algorithms
series	DDSS
last changed	2004/07/03 22:13

_id	ddss2004_d-157
id	ddss2004_d-157
authors	Krafta, R.
year	2004
title	Space is the Machine, with a Ghost Inside
source	Van Leeuwen, J.P. and H.J.P. Timmermans (eds.) Developments in Design & Decision Support Systems in Architecture and Urban Planning, Eindhoven: Eindhoven University of Technology, ISBN 90-6814-155-4, p. 157-173
summary	The purpose of this paper is to report efforts towards the construction of a model for urban spatial dynamics simulation, based on multi-agents and space. The underlying idea is to have urban space producers and consumers operating in a two-layer, two-circuit model. The first layer holds urban space and its successive transformations; a second layer contains agents related to space; the first circuit simulates space production, and a second one simulates space consumption. Relationship between layers is represented as objective spatial features that agents are submitted to (the machine) and subjective meanings agents attach to each spatial feature (the ghost). While space works always in the same way, meanings vary according to each agent’s background and context. Relationships between circuits are represented by means of a market game in which producers try to maximize their profits by gambling with their risks, whereas consumers try to foresee the spatial distribution of local externalities that maximizes their utilities and investments. Urban Spatial Features are captured through centrality and land use patterns; every single agent’s action leads to changes in both patterns. Producers’ profit is a function of built form location. Consumers’ local externalities are concerned basically with present and future services. The model iteration is twofold: first it generates and allocates a number of built forms within a previously determined spatial system (a cellular matrix, for example), and second it allocates users to built forms. Population of users have its social profile and growth rate externally determined. Built form allocation is decided on the basis of a combination of profitXrisk perspectives. Users’ locational choice is supported by accessibility to services and present/future neighbourhood profile. Built form allocation works as parameter for users’ locational assessment, whereas users’ choices are used as parameters for developers. The model tends to adjust itself, in terms of quantities and types of built forms to be erected, although through a market lag of some iterations. Allocations are always made through weighted draws, so that mutations (non deterministic allocations) do occur.
keywords	Urban Morphology, Urban Growth, Simulation
series	DDSS
last changed	2004/07/03 22:13

For more results click below: