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 741

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

_id	349e
authors	Durmisevic, Sanja
year	2002
title	Perception Aspects in Underground Spaces using Intelligent Knowledge Modeling
source	Delft University of Technology
summary	The intensification, combination and transformation are main strategies for future spatial development of the Netherlands, which are stated in the Fifth Bill regarding Spatial Planning. These strategies indicate that in the future, space should be utilized in a more compact and more efficient way requiring, at the same time, re-evaluation of the existing built environment and finding ways to improve it. In this context, the concept of multiple space usage is accentuated, which would focus on intensive 4-dimensional spatial exploration. The underground space is acknowledged as an important part of multiple space usage. In the document 'Spatial Exploration 2000', the underground space is recognized by policy makers as an important new 'frontier' that could provide significant contribution to future spatial requirements.In a relatively short period, the underground space became an important research area. Although among specialists there is appreciation of what underground space could provide for densely populated urban areas, there are still reserved feelings by the public, which mostly relate to the poor quality of these spaces. Many realized underground projects, namely subways, resulted in poor user satisfaction. Today, there is still a significant knowledge gap related to perception of underground space. There is also a lack of detailed documentation on actual applications of the theories, followed by research results and applied techniques. This is the case in different areas of architectural design, but for underground spaces perhaps most evident due to their infancv role in general architectural practice. In order to create better designs, diverse aspects, which are very often of qualitative nature, should be considered in perspective with the final goal to improve quality and image of underground space. In the architectural design process, one has to establish certain relations among design information in advance, to make design backed by sound rationale. The main difficulty at this point is that such relationships may not be determined due to various reasons. One example may be the vagueness of the architectural design data due to linguistic qualities in them. Another, may be vaguely defined design qualities. In this work, the problem was not only the initial fuzziness of the information but also the desired relevancy determination among all pieces of information given. Presently, to determine the existence of such relevancy is more or less a matter of architectural subjective judgement rather than systematic, non-subjective decision-making based on an existing design. This implies that the invocation of certain tools dealing with fuzzy information is essential for enhanced design decisions. Efficient methods and tools to deal with qualitative, soft data are scarce, especially in the architectural domain. Traditionally well established methods, such as statistical analysis, have been used mainly for data analysis focused on similar types to the present research. These methods mainly fall into a category of pattern recognition. Statistical regression methods are the most common approaches towards this goal. One essential drawback of this method is the inability of dealing efficiently with non-linear data. With statistical analysis, the linear relationships are established by regression analysis where dealing with non-linearity is mostly evaded. Concerning the presence of multi-dimensional data sets, it is evident that the assumption of linear relationships among all pieces of information would be a gross approximation, which one has no basis to assume. A starting point in this research was that there maybe both linearity and non-linearity present in the data and therefore the appropriate methods should be used in order to deal with that non-linearity. Therefore, some other commensurate methods were adopted for knowledge modeling. In that respect, soft computing techniques proved to match the quality of the multi-dimensional data-set subject to analysis, which is deemed to be 'soft'. There is yet another reason why soft-computing techniques were applied, which is related to the automation of knowledge modeling. In this respect, traditional models such as Decision Support Systems and Expert Systems have drawbacks. One important drawback is that the development of these systems is a time-consuming process. The programming part, in which various deliberations are required to form a consistent if-then rule knowledge based system, is also a time-consuming activity. For these reasons, the methods and tools from other disciplines, which also deal with soft data, should be integrated into architectural design. With fuzzy logic, the imprecision of data can be dealt with in a similar way to how humans do it. Artificial neural networks are deemed to some extent to model the human brain, and simulate its functions in the form of parallel information processing. They are considered important components of Artificial Intelligence (Al). With neural networks, it is possible to learn from examples, or more precisely to learn from input-output data samples. The combination of the neural and fuzzy approach proved to be a powerful combination for dealing with qualitative data. The problem of automated knowledge modeling is efficiently solved by employment of machine learning techniques. Here, the expertise of prof. dr. Ozer Ciftcioglu in the field of soft computing was crucial for tool development. By combining knowledge from two different disciplines a unique tool could be developed that would enable intelligent modeling of soft data needed for support of the building design process. In this respect, this research is a starting point in that direction. It is multidisciplinary and on the cutting edge between the field of Architecture and the field of Artificial Intelligence. From the architectural viewpoint, the perception of space is considered through relationship between a human being and a built environment. Techniques from the field of Artificial Intelligence are employed to model that relationship. Such an efficient combination of two disciplines makes it possible to extend our knowledge boundaries in the field of architecture and improve design quality. With additional techniques, meta know/edge, or in other words "knowledge about knowledge", can be created. Such techniques involve sensitivity analysis, which determines the amount of dependency of the output of a model (comfort and public safety) on the information fed into the model (input). Another technique is functional relationship modeling between aspects, which is derivation of dependency of a design parameter as a function of user's perceptions. With this technique, it is possible to determine functional relationships between dependent and independent variables. This thesis is a contribution to better understanding of users' perception of underground space, through the prism of public safety and comfort, which was achieved by means of intelligent knowledge modeling. In this respect, this thesis demonstrated an application of ICT (Information and Communication Technology) as a partner in the building design process by employing advanced modeling techniques. The method explained throughout this work is very generic and is possible to apply to not only different areas of architectural design, but also to other domains that involve qualitative data.
keywords	Underground Space; Perception; Soft Computing
series	thesis:PhD
email
last changed	2003/02/12 22:37

_id	42dd
authors	Kobayashi, Yoshihiro and Terzidis, Kostas
year	2000
title	Extracting the Geometry of Buildings from Satellite Images using Fuzzy Multiple Layer Perceptrons
source	SIGraDi’2000 - Construindo (n)o espacio digital (constructing the digital Space) [4th SIGRADI Conference Proceedings / ISBN 85-88027-02-X] Rio de Janeiro (Brazil) 25-28 september 2000, pp. 236-239
summary	This paper presents Computer Aided Architectural Design (CAAD) system utilizing the technologies of artificial intelligence (AI) and image processing. The goal is to create a CAAD system that detects buildings from satellite images and produces computer city models allowing the system’s users to manipulate the models utilizing machine learning technology. The flexibility and usability of the system was evaluated with case studies. Soft computing technologies including neural networks and fuzzy systems are mainly applied and tested as the system’s methodology.
series	SIGRADI
email
last changed	2016/03/10 09:54

_id	d8df
authors	Naticchia, Berardo
year	1999
title	Physical Knowledge in Patterns: Bayesian Network Models for Preliminary Design
doi	https://doi.org/10.52842/conf.ecaade.1999.611
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 611-619
summary	Computer applications in design have pursued two main development directions: analytical modelling and information technology. The former line has produced a large number of tools for reality simulation (i.e. finite element models), the latter is producing an equally large amount of advances in conceptual design support (i.e. artificial intelligence tools). Nevertheless we can trace rare interactions between computation models related to those different approaches. This lack of integration is the main reason of the difficulty of CAAD application to the preliminary stage of design, where logical and quantitative reasoning are closely related in a process that we often call 'qualitative evaluation'. This paper briefly surveys the current development of qualitative physical models applied in design and propose a general approach for modelling physical behaviour by means of Bayesian network we are employing to develop a tutoring and coaching system for natural ventilation preliminary design of halls, called VENTPad. This tool explores the possibility of modelling the causal mechanism that operate in real systems in order to allow a number of integrated logical and quantitative inference about the fluid-dynamic behaviour of an hall. This application could be an interesting connection tool between logical and analytical procedures in preliminary design aiding, able to help students or unskilled architects, both to guide them through the analysis process of numerical data (i.e. obtained with sophisticate Computational Fluid Dynamics software) or experimental data (i.e. obtained with laboratory test models) and to suggest improvements to the design.
keywords	Qualitative Physical Modelling, Preliminary Design, Bayesian Networks
series	eCAADe
email
last changed	2022/06/07 07:59

_id	15e4
authors	Sariyildiz, S., Stouffs, R. and Tunçer, B.
year	2000
title	Vision on ICT Developments for the Building Sector
doi	https://doi.org/10.52842/conf.acadia.2000.011
source	Eternity, Infinity and Virtuality in Architecture [Proceedings of the 22nd Annual Conference of the Association for Computer-Aided Design in Architecture / 1-880250-09-8] Washington D.C. 19-22 October 2000, pp. 11-18
summary	The building sector is entering a new era. Developments in information and communication technology have an impact throughout the entire life cycle of a building, not only from a process and technical point of view but also from a creative design point of view. As a result of developments of advanced modeling software for architectural design, the gap between what the architect can envision and what the building technician or product architect can materialize is enlarging. Internet technology has already started to provide a closer link between the participants in the building process, their activities, knowledge, and information. Concurrent and collaborative engineering will be the future of building practice in respect to efficiency and quality improvement of this sector. The nature of the building process is complex, not only from a communication point of view, but also from the information of the number of participants, the spatial organization and the infrastructure etc. In the near future, soft computing techniques such as artificial neural networks, fuzzy logic, and genetic algorithms will make contributions to the problem solving aspects of the complex design process. This paper provides an overview of these and other future developments of information and communication technology (ICT) within the building sector.
series	ACADIA
email
last changed	2022/06/07 07:57

_id	ga0026
id	ga0026
authors	Ransen, Owen F.
year	2000
title	Possible Futures in Computer Art Generation
source	International Conference on Generative Art
summary	Years of trying to create an "Image Idea Generator" program have convinced me that the perfect solution would be to have an artificial artistic person, a design slave. This paper describes how I came to that conclusion, realistic alternatives, and briefly, how it could possibly happen. 1. The history of Repligator and Gliftic 1.1 Repligator In 1996 I had the idea of creating an “image idea generator”. I wanted something which would create images out of nothing, but guided by the user. The biggest conceptual problem I had was “out of nothing”. What does that mean? So I put aside that problem and forced the user to give the program a starting image. This program eventually turned into Repligator, commercially described as an “easy to use graphical effects program”, but actually, to my mind, an Image Idea Generator. The first release came out in October 1997. In December 1998 I described Repligator V4 [1] and how I thought it could be developed away from simply being an effects program. In July 1999 Repligator V4 won the Shareware Industry Awards Foundation prize for "Best Graphics Program of 1999". Prize winners are never told why they won, but I am sure that it was because of two things: 1) Easy of use 2) Ease of experimentation "Ease of experimentation" means that Repligator does in fact come up with new graphics ideas. Once you have input your original image you can generate new versions of that image simply by pushing a single key. Repligator is currently at version 6, but, apart from adding many new effects and a few new features, is basically the same program as version 4. Following on from the ideas in [1] I started to develop Gliftic, which is closer to my original thoughts of an image idea generator which "starts from nothing". The Gliftic model of images was that they are composed of three components: 1. Layout or form, for example the outline of a mandala is a form. 2. Color scheme, for example colors selected from autumn leaves from an oak tree. 3. Interpretation, for example Van Gogh would paint a mandala with oak tree colors in a different way to Andy Warhol. There is a Van Gogh interpretation and an Andy Warhol interpretation. Further I wanted to be able to genetically breed images, for example crossing two layouts to produce a child layout. And the same with interpretations and color schemes. If I could achieve this then the program would be very powerful. 1.2 Getting to Gliftic Programming has an amazing way of crystalising ideas. If you want to put an idea into practice via a computer program you really have to understand the idea not only globally, but just as importantly, in detail. You have to make hard design decisions, there can be no vagueness, and so implementing what I had decribed above turned out to be a considerable challenge. I soon found out that the hardest thing to do would be the breeding of forms. What are the "genes" of a form? What are the genes of a circle, say, and how do they compare to the genes of the outline of the UK? I wanted the genotype representation (inside the computer program's data) to be directly linked to the phenotype representation (on the computer screen). This seemed to be the best way of making sure that bred-forms would bare some visual relationship to their parents. I also wanted symmetry to be preserved. For example if two symmetrical objects were bred then their children should be symmetrical. I decided to represent shapes as simply closed polygonal shapes, and the "genes" of these shapes were simply the list of points defining the polygon. Thus a circle would have to be represented by a regular polygon of, say, 100 sides. The outline of the UK could easily be represented as a list of points every 10 Kilometers along the coast line. Now for the important question: what do you get when you cross a circle with the outline of the UK? I tried various ways of combining the "genes" (i.e. coordinates) of the shapes, but none of them really ended up producing interesting shapes. And of the methods I used, many of them, applied over several "generations" simply resulted in amorphous blobs, with no distinct family characteristics. Or rather maybe I should say that no single method of breeding shapes gave decent results for all types of images. Figure 1 shows an example of breeding a mandala with 6 regular polygons: Figure 1 Mandala bred with array of regular polygons I did not try out all my ideas, and maybe in the future I will return to the problem, but it was clear to me that it is a non-trivial problem. And if the breeding of shapes is a non-trivial problem, then what about the breeding of interpretations? I abandoned the genetic (breeding) model of generating designs but retained the idea of the three components (form, color scheme, interpretation). 1.3 Gliftic today Gliftic Version 1.0 was released in May 2000. It allows the user to change a form, a color scheme and an interpretation. The user can experiment with combining different components together and can thus home in on an personally pleasing image. Just as in Repligator, pushing the F7 key make the program choose all the options. Unlike Repligator however the user can also easily experiment with the form (only) by pushing F4, the color scheme (only) by pushing F5 and the interpretation (only) by pushing F6. Figures 2, 3 and 4 show some example images created by Gliftic. Figure 2 Mandala interpreted with arabesques Figure 3 Trellis interpreted with "graphic ivy" Figure 4 Regular dots interpreted as "sparks" 1.4 Forms in Gliftic V1 Forms are simply collections of graphics primitives (points, lines, ellipses and polygons). The program generates these collections according to the user's instructions. Currently the forms are: Mandala, Regular Polygon, Random Dots, Random Sticks, Random Shapes, Grid Of Polygons, Trellis, Flying Leap, Sticks And Waves, Spoked Wheel, Biological Growth, Chequer Squares, Regular Dots, Single Line, Paisley, Random Circles, Chevrons. 1.5 Color Schemes in Gliftic V1 When combining a form with an interpretation (described later) the program needs to know what colors it can use. The range of colors is called a color scheme. Gliftic has three color scheme types: 1. Random colors: Colors for the various parts of the image are chosen purely at random. 2. Hue Saturation Value (HSV) colors: The user can choose the main hue (e.g. red or yellow), the saturation (purity) of the color scheme and the value (brightness/darkness) . The user also has to choose how much variation is allowed in the color scheme. A wide variation allows the various colors of the final image to depart a long way from the HSV settings. A smaller variation results in the final image using almost a single color. 3. Colors chosen from an image: The user can choose an image (for example a JPG file of a famous painting, or a digital photograph he took while on holiday in Greece) and Gliftic will select colors from that image. Only colors from the selected image will appear in the output image. 1.6 Interpretations in Gliftic V1 Interpretation in Gliftic is best decribed with a few examples. A pure geometric line could be interpreted as: 1) the branch of a tree 2) a long thin arabesque 3) a sequence of disks 4) a chain, 5) a row of diamonds. An pure geometric ellipse could be interpreted as 1) a lake, 2) a planet, 3) an eye. Gliftic V1 has the following interpretations: Standard, Circles, Flying Leap, Graphic Ivy, Diamond Bar, Sparkz, Ess Disk, Ribbons, George Haite, Arabesque, ZigZag. 1.7 Applications of Gliftic Currently Gliftic is mostly used for creating WEB graphics, often backgrounds as it has an option to enable "tiling" of the generated images. There is also a possibility that it will be used in the custom textile business sometime within the next year or two. The real application of Gliftic is that of generating new graphics ideas, and I suspect that, like Repligator, many users will only understand this later. 2. The future of Gliftic, 3 possibilties Completing Gliftic V1 gave me the experience to understand what problems and opportunities there will be in future development of the program. Here I divide my many ideas into three oversimplified possibilities, and the real result may be a mix of two or all three of them. 2.1 Continue the current development "linearly" Gliftic could grow simply by the addition of more forms and interpretations. In fact I am sure that initially it will grow like this. However this limits the possibilities to what is inside the program itself. These limits can be mitigated by allowing the user to add forms (as vector files). The user can already add color schemes (as images). The biggest problem with leaving the program in its current state is that there is no easy way to add interpretations. 2.2 Allow the artist to program Gliftic It would be interesting to add a language to Gliftic which allows the user to program his own form generators and interpreters. In this way Gliftic becomes a "platform" for the development of dynamic graphics styles by the artist. The advantage of not having to deal with the complexities of Windows programming could attract the more adventurous artists and designers. The choice of programming language of course needs to take into account the fact that the "programmer" is probably not be an expert computer scientist. I have seen how LISP (an not exactly easy artificial intelligence language) has become very popular among non programming users of AutoCAD. If, to complete a job which you do manually and repeatedly, you can write a LISP macro of only 5 lines, then you may be tempted to learn enough LISP to write those 5 lines. Imagine also the ability to publish (and/or sell) "style generators". An artist could develop a particular interpretation function, it creates images of a given character which others find appealing. The interpretation (which runs inside Gliftic as a routine) could be offered to interior designers (for example) to unify carpets, wallpaper, furniture coverings for single projects. As Adrian Ward [3] says on his WEB site: "Programming is no less an artform than painting is a technical process." Learning a computer language to create a single image is overkill and impractical. Learning a computer language to create your own artistic style which generates an infinite series of images in that style may well be attractive. 2.3 Add an artificial conciousness to Gliftic This is a wild science fiction idea which comes into my head regularly. Gliftic manages to surprise the users with the images it makes, but, currently, is limited by what gets programmed into it or by pure chance. How about adding a real artifical conciousness to the program? Creating an intelligent artificial designer? According to Igor Aleksander [1] conciousness is required for programs (computers) to really become usefully intelligent. Aleksander thinks that "the line has been drawn under the philosophical discussion of conciousness, and the way is open to sound scientific investigation". Without going into the details, and with great over-simplification, there are roughly two sorts of artificial intelligence: 1) Programmed intelligence, where, to all intents and purposes, the programmer is the "intelligence". The program may perform well (but often, in practice, doesn't) and any learning which is done is simply statistical and pre-programmed. There is no way that this type of program could become concious. 2) Neural network intelligence, where the programs are based roughly on a simple model of the brain, and the network learns how to do specific tasks. It is this sort of program which, according to Aleksander, could, in the future, become concious, and thus usefully intelligent. What could the advantages of an artificial artist be? 1) There would be no need for programming. Presumbably the human artist would dialog with the artificial artist, directing its development. 2) The artificial artist could be used as an apprentice, doing the "drudge" work of art, which needs intelligence, but is, anyway, monotonous for the human artist. 3) The human artist imagines "concepts", the artificial artist makes them concrete. 4) An concious artificial artist may come up with ideas of its own. Is this science fiction? Arthur C. Clarke's 1st Law: "If a famous scientist says that something can be done, then he is in all probability correct. If a famous scientist says that something cannot be done, then he is in all probability wrong". Arthur C Clarke's 2nd Law: "Only by trying to go beyond the current limits can you find out what the real limits are." One of Bertrand Russell's 10 commandments: "Do not fear to be eccentric in opinion, for every opinion now accepted was once eccentric" 3. References 1. "From Ramon Llull to Image Idea Generation". Ransen, Owen. Proceedings of the 1998 Milan First International Conference on Generative Art. 2. "How To Build A Mind" Aleksander, Igor. Wiedenfeld and Nicolson, 1999 3. "How I Drew One of My Pictures: or, The Authorship of Generative Art" by Adrian Ward and Geof Cox. Proceedings of the 1999 Milan 2nd International Conference on Generative Art.
series	other
email
more	http://www.generativeart.com/
last changed	2003/08/07 17:25

_id	ga0016
id	ga0016
authors	Thum, Robert and Derix, Christian
year	2000
title	Artificial Neural Network Spaces
source	International Conference on Generative Art
summary	In the processes of continues functional differentiation the contemporary society increasingly displays the characteristics of complex, distributed systems. In this condition architecture can no longer rely on top-down reductionist methodologies in ignoring the constituting importance of contextual parameters. The present paper describes how Artificial Neural Networks can be employed to design with-in the underlying logic of our society -the logic of distributed systems. In computer simulations the paper explores the capability of ANN to Self-organization: Neural Networks Architectures absorb and adapt vast amount of urban data in order to adjust their organization to exterior changes through interior structural reconfiguration, thus producing adaptive spatial formations.
series	other
type	normal paper
email
more	http://www.generativeart.com/
last changed	2012/09/25 07:42

_id	7847
authors	Kartam, Nabil and Flood, Ian
year	2000
title	Construction simulation using parallel computing environments
source	Automation in Construction 10 (1) (2000) pp. 69-78
summary	The paper describes and compares alternative approaches to implementing construction simulation models within a multiprocessor computing environment. Both parallel-algorithmic and neural network based methods of simulating construction processes are considered, and compared with the conventional serial-algorithmic approach. The lines along which a simulation algorithm can be divided into tasks for parallel execution on a multiprocessor are first discussed, and the merits of each approach are identified. This is followed by a brief discourse on neural networks, their application to construction simulation, and the way in which such an implementation can be implemented within a multiprocessing environment. The merits and demerits of all approaches are discussed with particular reference to a model of an excavation system. A case study comparing the speed at which each implementation can process a simulation shows the neural approach to operate approximately two orders of magnitude faster than the alternatives. The paper concludes with an indication of future research to be conducted in this field.
series	journal paper
more	http://www.elsevier.com/locate/autcon
last changed	2003/05/15 21:22

_id	aef9
id	aef9
authors	Brown, A., Knight, M. and Berridge, P. (Eds.)
year	1999
title	Architectural Computing from Turing to 2000 [Conference Proceedings]
doi	https://doi.org/10.52842/conf.ecaade.1999
source	eCAADe Conference Proceedings / ISBN 0-9523687-5-7 / Liverpool (UK) 15-17 September 1999, 773 p.
summary	The core theme of this book is the idea of looking forward to where research and development in Computer Aided Architectural Design might be heading. The contention is that we can do so most effectively by using the developments that have taken place over the past three or four decades in Computing and Architectural Computing as our reference point; the past informing the future. The genesis of this theme is the fact that a new millennium is about to arrive. If we are ruthlessly objective the year 2000 holds no more significance than any other year; perhaps we should, instead, be preparing for the year 2048 (2k). In fact, whatever the justification, it is now timely to review where we stand in terms of the development of Architectural Computing. This book aims to do that. It is salutary to look back at what writers and researchers have said in the past about where they thought that the developments in computing were taking us. One of the common themes picked up in the sections of this book is the developments that have been spawned by the global linkup that the worldwide web offers us. In the past decade the scale and application of this new medium of communication has grown at a remarkable rate. There are few technological developments that have become so ubiquitous, so quickly. As a consequence there are particular sections in this book on Communication and the Virtual Design Studio which reflect the prominence of this new area, but examples of its application are scattered throughout the book. In 'Computer-Aided Architectural Design' (1977), Bill Mitchell did suggest that computer network accessibility from expensive centralised locations to affordable common, decentralised computing facilities would become more commonplace. But most pundits have been taken by surprise by just how powerful the explosive cocktail of networks, email and hypertext has proven to be. Each of the ingredients is interesting in its own right but together they have presented us with genuinely new ways of working. Perhaps, with foresight we can see what the next new explosive cocktail might be.
series	eCAADe
email
more	http://www.ecaade.org
last changed	2022/06/07 07:49

_id	958e
authors	Coppola, Carlo and Ceso, Alessandro
year	2000
title	Computer Aided Design and Artificial Intelligence in Urban and Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2000.301
source	Promise and Reality: State of the Art versus State of Practice in Computing for the Design and Planning Process [18th eCAADe Conference Proceedings / ISBN 0-9523687-6-5] Weimar (Germany) 22-24 June 2000, pp. 301-307
summary	In general, computer-aided design is still limited to a rather elementary use of the medium, as it is mainly used for the representation/simulation of a design idea w an electronic drawing-table. hich is not computer-generated. The procedures used to date have been basically been those of an electronic drawing-table. At the first stage of development the objective was to find a different and better means of communication, to give form to an idea so as to show its quality. The procedures used were 2D design and 3D simulation models, usually used when the design was already defined. The second stage is when solid 3D modelling is used to define the formal design at the conception stage, using virtual models instead of study models in wood, plastic, etc. At the same time in other connected fields the objective is to evaluate the feasibility of the formal idea by means of structural and technological analysis. The third stage, in my opinion, should aim to develop procedures capable of contributing to both the generation of the formal idea and the simultaneous study of technical feasibility by means of a decision-making support system aided by an Artificial Intelligence procedure which will lead to what I would describe as the definition of the design in its totality. The approach to architectural and urban design has been strongly influenced by the first two stages, though these have developed independently and with very specific objectives. It is my belief that architectural design is now increasingly the result of a structured and complex process, not a simple act of pure artistic invention. Consequently, I feel that the way forward is a procedure able to virtually represent all the features of the object designed, not only in its definitive configuration but also and more importantly in the interactions which determine the design process as it develops. Thus A.I. becomes the means of synthesis for models which are hierarchically subordinated which together determine the design object in its developmental process, supporting decision-making by applying processing criteria which generative modelling has already identified. This trend is currently being experimented, giving rise to interesting results from process design in the field of industrial production.
series	eCAADe
email
more	http://www.uni-weimar.de/ecaade/
last changed	2022/06/07 07:56

_id	ga0015
id	ga0015
authors	Daru, R., Vreedenburgh, E. and Scha, R.
year	2000
title	Architectural Innovation as an evolutionary process
source	International Conference on Generative Art
summary	Traditionally in art and architectural history, innovation is treated as a history of ideas of individuals (pioneers), movements and schools. The monograph is in that context one of the most used forms of scientific exercise. History of architecture is then mostly seen as a succession of dominant architectural paradigms imposed by great architectural creators fighting at the beginning against mainstream establishment until they themselves come to be recognised. However, there have been attempts to place architectural innovation and creativity in an evolutionary perspective. Charles Jencks for example, has described the evolution of architectural and art movements according to a diagram inspired by ecological models. Philip Steadman, in his book "The Evolution of Designs. Biological analogy in architecture and the applied arts" (1979), sketches the history of various biological analogies and their impact on architectural theory: the organic, classificatory, anatomical, ecological and Darwinian or evolutionary analogies. This last analogy "explains the design of useful objects and buildings, particularly in primitive society and in the craft tradition, in terms of a sequence of repeated copyings (corresponding to inheritance), with small changes made at each stage ('variations'), which are then subjected to a testing process when the object is put into use ('selection')." However, Steadman has confined his study to a literature survey as the basis of a history of ideas. Since this pioneering work, new developments like Dawkins' concept of memes allow further steps in the field of cultural evolution of architectural innovation. The application of the concept of memes to architectural design has been put forward in a preceding "Generative Art" conference (Daru, 1999), showing its application in a pilot study on the analysis of projects of and by architectural students. This first empirical study is now followed by a study of 'real life' architectural practice. The case taken has a double implication for the evolutionary analogy. It takes a specific architectural innovative concept as a 'meme' and develops the analysis of the trajectory of this meme in the individual context of the designer and at large. At the same time, the architect involved (Eric Vreedenburgh, Archipel Ontwerpers) is knowledgeable about the theory of memetic evolution and is applying a computer tool (called 'Artificial') together with Remko Scha, the authoring computer scientist of the program who collaborates frequently with artists and architects. This case study (the penthouse in Dutch town planning and the application of 'Artificial') shall be discussed in the paper as presented. The theoretical and methodological problems of various models of diffusion of memes shall be discussed and a preliminary model shall be presented as a framework to account for not only Darwinian but also Lamarckian processes, and for individual as well as collective transmission, consumption and creative transformation of memes.
keywords	evolutionary design, architectural innovation, memetic diffusion, CAAD, penthouses, Dutch design, creativity, Darwinian and Lamarckian processes
series	other
more	http://www.generativeart.com/
last changed	2003/08/07 17:25

_id	5007
authors	Elezkurtaj, Tomor and Franck, Georg
year	1999
title	Genetic Algorithms in Support of Creative Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.1999.645
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 645-651
summary	The functions supported by commercial CAAD software are drawing, construction and presentation. Up to now few programs supporting the creative part of architectural problem solving have become available. The grand hopes of symbolic AI to program creative architectural design have been disappointing. In the meantime, methods called referred to as New AI have become available. Such methods includegenetic algorithms (GA). But GA, though successfully applied in other fields of engineering, still waits to be applied broadly in architectural design. A main problem lies in defining function in architecture. It is much harder to define the function of a building than that of a machine. Without specifying the function of the artifact, the fitness function of the design variants participating in the survival game of artificial evolution remains undetermined. It is impossible to fully specify the fitness function of architecture. The approach presented is one of circumventing a full specification through dividing labor between the GA software and its user. The fitness function of architectural ground plans is typically defined in terms only of the proportions of the room to be accommodated and certain topological relations between them. The rest is left to the human designer who interactively intervenes in the evolution game as displayed on the screen.
keywords	Genetic Algorithms, Creative Architectural Design
series	eCAADe
email
last changed	2022/06/07 07:55

_id	f91f
authors	Elezkurtaj, Tomor and Franck, Georg
year	2000
title	Geometry and Topology. A User-Interface to Artificial Evolution in Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2000.309
source	Promise and Reality: State of the Art versus State of Practice in Computing for the Design and Planning Process [18th eCAADe Conference Proceedings / ISBN 0-9523687-6-5] Weimar (Germany) 22-24 June 2000, pp. 309-312
summary	The paper presents a system that supports architectural floor plan design interactively. The method of problem solving implemented is a combination of an evolutionary strategy (ES) and a genetic algorithm (GA). The problem to be solved consists of fitting a number of rooms (n) into an outline by observing functional requirements. The rooms themselves are specified concerning size, function and preferred proportion. The functional requirements entering the fitness functions are expressed in terms of the proportions of the rooms and the neighbourhood relations between them. The system is designed to deal with one of the core problems of computer supported creativity in architecture. For architecture, form not only, but also function is relevant. Without specifying the function that a piece of architecture is supposed to fulfil, it is hard to support its design by computerised methods of problem solving and optimisation. In architecture, however, function relates to comfort, easiness of use, and aesthetics as well. Since it is extraordinary hard, if not impossible, to operationalise aesthetics, computer aided support of creative architectural design is still in its infancy.
keywords	New AI, Genetic Algorithms, Artificial Evolution, creative Architectural Design, Interactive Design, Topology
series	eCAADe
email
more	http://www.uni-weimar.de/ecaade/
last changed	2022/06/07 07:55

_id	1f21
authors	Geebelen, Benjamin and Neuckermans, Herman
year	2000
title	IDEA-l. Bringing Natural Lighting to the Early Design Stages
doi	https://doi.org/10.52842/conf.ecaade.2000.193
source	Promise and Reality: State of the Art versus State of Practice in Computing for the Design and Planning Process [18th eCAADe Conference Proceedings / ISBN 0-9523687-6-5] Weimar (Germany) 22-24 June 2000, pp. 193-196
summary	This paper discusses the use of computers as design tools for natural lighting in the early stages of the architectural design process. It focuses on IDEA-l, a new natural-lighting design tool, currently under development, that is meant to offer the architect/designer a digital equivalent for scale models, artificial sky simulators and heliodons.
series	eCAADe
email
more	http://www.uni-weimar.de/ecaade/
last changed	2022/06/07 07:51

_id	1076
authors	Gero, John S. and Saunders, Robert
year	2000
title	Constructed Representations and Their Functions in Computational Models of Designing
doi	https://doi.org/10.52842/conf.caadria.2000.215
source	CAADRIA 2000 [Proceedings of the Fifth Conference on Computer Aided Architectural Design Research in Asia / ISBN 981-04-2491-4] Singapore 18-19 May 2000, pp. 215-224
summary	This paper re-examines the conclusions made by Schön and Wiggins in 1992 that computers were unable to reproduce processes crucial to designing. We propose that recent developments in artificial intelligence and design computing put us in a position where we can begin to computationally model designing as conceived by Schön and Wiggins. We present a computational model of designing using situated processes that construct representations. We show how constructed representations support computational processes that model the different kinds of seeing reported in designing. We also present recently developed computational processes that can identify unexpected consequences of design actions using adaptive novelty detection.
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ga0028
id	ga0028
authors	Kabala, J., Conrado, C. and Overveld, K. van
year	2000
title	Communicative Profiles - Generative Art Applied in Information Access Interfaces
source	International Conference on Generative Art
summary	The path of ubiquitous computing and the domain of ambient intelligence are expected to stimulate emergence of new interaction paradigms. There is a need to develop adequate means of natural communication with an intelligent information system. This, presumably, requires a more integrated development of form and function of the interface. The interface design concept proposed in this paper is based on an evolutionary mechanism and it aims at development of an interactive and adaptive animation system. It is proposed that through a coherent process of adaptation of a system functionality and its appropriate visualization, a personalized and more natural experience of interaction might be achieved.
keywords	natural interaction, ambient intelligence, artificial evolution, interactive animation system, personalization, user experience
series	other
email
more	http://www.generativeart.com/
last changed	2003/08/07 17:25

_id	c991
authors	Moorhouse, Jon and Brown,Gary
year	1999
title	Autonomous Spatial Redistribution for Cities
doi	https://doi.org/10.52842/conf.ecaade.1999.678
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 678-684
summary	The paper investigates an automated methodology for the appropriate redistribution of usable space in distressed areas of inner cities. This is achieved by categorising activity space and making these spaces morphologically mobile in relation to the topography within a representative artificial space. The educational module has been influenced by theories from the natural environment, which possess patterns that have inherent evolutionary programmes in which the constituents are recyclable, Information is strategically related to the environment to produce forms of growth and behaviour. Artificial landscape patterns fail to evolve, the inhabited landscape needs a means of starting from simplicity and building into the most complex of systems that are capable of re-permutation over time. The paper then describes the latest methodological development in terms of a shift from the use of the computer as a tool for data manipulation to embracing the computer as a design partner. The use of GDL in particular is investigated as a facilitator for such generation within a global, vectorial environment.
keywords	Animated, Urban, Programme, Education, Visual Database
series	eCAADe
email
last changed	2022/06/07 07:58

_id	6072
authors	Orzechowski, M.A., Timmermans, H.J.P. and De Vries, B.
year	2000
title	Measuring user satisfaction for design variations through virtual reality
source	Timmermans, H.J.P. & Vries, B. de (eds.) Design & Decision Support Systems in Architecture - Proceedings of the 5th International Conference, August 22-25 2000, Nijkerk, pp. 278-288
summary	Virtual Reality (VR), and Artificial Intelligence (AI) technology have become increasingly more common in all disciplines of modern life. These new technologies range from simple software assistants to sophisticated modeling of human behavior. In this research project, we are creating an AI agent environment that helps architects to identify user preferences through a Virtual Reality Interface. At the current stage of development, the research project has resulted in a VR application - MuseV2 that allows users to instantly modify an architectural design. The distinctive feature of this application is that a space is considered as a base for all user modifications and as a connection between all design elements. In this paper we provide some technical information about MuseV2. Presentation of a design through VR allows AI agents to observe user-induced modifications and to gather preference information. In addition to allowing for an individualized design, this information generalized across a sample of users should provide the basis for developing basic designs for particular market segments and predict the market potential of those designs. The system that we envision should not become an automated design tool, but an adviser and viewer for users, who have limited knowledge or no knowledge at all about CAD systems, and architectural design. This tool should help investors to assess preferences for new community housing in order to meet the needs of future inhabitants.
series	other
email
last changed	2003/04/23 15:50

_id	a4e9
authors	Petrovic, Igor and Svetel, Igor
year	1999
title	From Number Cruncher to Digital Being: The Changing Role of Computer in CAAD
doi	https://doi.org/10.52842/conf.ecaade.1999.033
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 33-39
summary	The paper reflects on a thirteen-year period of CAAD research and development by a small group of researchers and practitioners. Starting with simple algorithmic drafting programmes, the work transcended to expert systems and distributed artificial intelligence, using computers as tools. The research cycle is about to begin afresh; computers in the next century shall not be detached entities but the extensions of man. The computer shall be the medium that will enable a designer to be what he/she really is. This future has already begun.
keywords	History of CAAD, CAAD Design Paradigms, CAADfuture
series	eCAADe
email
last changed	2022/06/07 08:00

_id	9c96
authors	Szalapaj, Peter and Chang, David C.
year	1999
title	Computer Architectural Representation - Applying the VOIDs Framework to a Bridge Design Scheme
doi	https://doi.org/10.52842/conf.ecaade.1999.387
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 387-394
summary	A virtual environment presents sensory information and visual feedback to the user in order to give convincing illusion of an artificial world. In the architectural profession, the spatio-temporal metaphor in itself constitutes significant information retrieval, because we understand architecture by seeing it. This paper attempts to understand, and then to analyse the characteristics of representation of architectural models in virtual environments. We will examine the use and creativity of current computer generated architectural presentation in virtual environments. Our observations will be applied to the modelling of a bridge in Castlefield, Manchester, and evaluated by a group of students within the School of Architecture at Sheffield University. The conclusion of this paper will be the presentation of a conceptual structure for representing architectural models in virtual environments. This paper also explores the tension between the correspondence and constructivist views of representation. The correspondence view of representation relies on the idea that a representation corresponds to what is out there in the world. The constructivist view of representation advocates that any actual interpretation would depend on the context of their social and cultural backgrounds. However, the authors believe there should be a combination of these two views for architectural representation in virtual environments, and a framework developed by the authors - VOIDs will be presented.
keywords	Virtual Environment, Architectural Representation, VOIDs, Correspondence, Constructivist
series	eCAADe
email
last changed	2022/06/07 07:56

_id	d59a
authors	Zarnowiecka, Jadwiga C.
year	1999
title	AI and Regional Architecture
doi	https://doi.org/10.52842/conf.ecaade.1999.584
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 584-588
summary	In 1976 Richard Foqué established periods in the development of methods of designing. The first stage (the 50's and early 60's) - automatization of the designing process - properly identified language of description that is understood by a machine is vital. Christopher Alexander publishes 'Pattern Language'. The second stage (late 60's) - the use of the Arts - research techniques as interview, questionnaire, active observation; ergonomic aspects are also taken into consideration. The third stage (starts at the turn of the 60's and 70's) - co-participation of all of the parties involved in the designing process, and especially the user. The designing process becomes more complex but at the same time more intelligible to a non-professional - Alexander's 'Pattern Language' returns. It's been over 20 years now since the publication of this work. In the mid 70's prototypes of integrate building description are created. We are dealing now with the next stage of the designing methods development. Unquestionable progress of computer optimalization of technical and economical solutions has taken place. It's being forecasted that the next stage would be using computer as a simulator of the designing process. This stage may be combined with the development of AI. (Already in 1950 Alan Turing had formulated the theoretical grounds of Artificial Intelligence.) Can the development of the AI have the influence on the creation of present time regional architecture? Hereby I risk a conclusion that the development of AI can contribute to the creation of modern regional architecture.
keywords	Design Process, Artificial Intelligence, Regional Architecture
series	eCAADe
email
last changed	2022/06/07 07:57

For more results click below: