TY - CHAP A1 - Chirkin, Artem A1 - König, Reinhard T1 - Concept of Interactive Machine Learning in Urban Design Problems : proceedings N2 - This work presents a concept of interactive machine learning in a human design process. An urban design problem is viewed as a multiple-criteria optimization problem. The outlined feature of an urban design problem is the dependence of a design goal on a context of the problem. We model the design goal as a randomized fitness measure that depends on the context. In terms of multiple-criteria decision analysis (MCDA), the defined measure corresponds to a subjective expected utility of a user. In the first stage of the proposed approach we let the algorithm explore a design space using clustering techniques. The second stage is an interactive design loop; the user makes a proposal, then the program optimizes it, gets the user’s feedback and returns back the control over the application interface. KW - MCDM KW - interactive machine learning KW - urban design KW - multiple-criteria optimization KW - Stadtgestaltung Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-26000 UR - http://dl.acm.org/citation.cfm?id=2898365 SP - 10 EP - 13 PB - ACM New York, NY, USA CY - San Jose, CA, USA ER - TY - JOUR A1 - Klein, Bernhard A1 - König, Reinhard T1 - Computational Urban Planning: Using the Value Lab as Control Center JF - FCL Magazine, Special Issue Simulation Platform N2 - Urban planning involves many aspects and various disciplines, demanding an asynchronous planning approach. The level of complexity rises with each aspect to be considered and makes it difficult to find universally satisfactory solutions. To improve this situation we propose a new approach, which complement traditional design methods with a computational urban plan- ning method that can fulfil formalizable design requirements automatically. Based on this approach we present a design space exploration framework for complex urban planning projects. For a better understanding of the idea of design space exploration, we introduce the concept of a digital scout which guides planners through the design space and assists them in their creative explorations. The scout can support planners during manual design by informing them about potential im- pacts or by suggesting different solutions that fulfill predefined quality requirements. The planner can change flexibly between a manually controlled and a completely automated design process. The developed system is presented using an exemplary urban planning scenario on two levels from the street layout to the placement of building volumes. Based on Self-Organizing Maps we implemented a method which makes it possible to visualize the multi-dimensional solution space in an easily analysable and comprehensible form. KW - Computational Urban Design KW - Stadtgestaltung Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-26011 SP - 38 EP - 45 ER - TY - JOUR A1 - Treyer, Lukas A1 - Klein, Bernhard A1 - König, Reinhard A1 - Meixner, Christine T1 - Lightweight Urban Computation Interchange (LUCI): A System to Couple Heterogenous Simulations and Views JF - Spatial Information Research N2 - In this paper we introduce LUCI, a Lightweight Urban Calculation Interchange system, designed to bring the advantages of calculation and content co-ordination system to small planning and design groups by the means of an open source middle-ware. The middle-ware focuses on problems typical to urban planning and therefore features a geo-data repository as well as a job runtime administration, to coordinate simulation models and its multiple views. The described system architecture is accompanied by two exemplary use cases, that have been used to test and further develop our concepts and implementations. KW - Middle-ware KW - Design-simulation-loop KW - Computational urban planning KW - Distributed computing KW - Multiple comparative views Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-26037 UR - http://link.springer.com/article/10.1007/s41324-016-0025-y SP - 1 EP - 12 ER - TY - CHAP A1 - König, Reinhard A1 - Schmitt, Gerhard ED - Szoboszlai, Mihály T1 - Backcasting and a new way of command in computational design : Proceedings T2 - CAADence in Architecture Conference N2 - It's not uncommon that analysis and simulation methods are used mainly to evaluate finished designs and to proof their quality. Whereas the potential of such methods is to lead or control a design process from the beginning on. Therefore, we introduce a design method that move away from a “what-if” forecasting philosophy and increase the focus on backcasting approaches. We use the power of computation by combining sophisticated methods to generate design with analysis methods to close the gap between analysis and synthesis of designs. For the development of a future-oriented computational design support we need to be aware of the human designer’s role. A productive combination of the excellence of human cognition with the power of modern computing technology is needed. We call this approach “cognitive design computing”. The computational part aim to mimic the way a designer’s brain works by combining state-of-the-art optimization and machine learning approaches with available simulation methods. The cognition part respects the complex nature of design problems by the provision of models for human-computation interaction. This means that a design problem is distributed between computer and designer. In the context of the conference slogan “back to command”, we ask how we may imagine the command over a cognitive design computing system. We expect that designers will need to let go control of some parts of the design process to machines, but in exchange they will get a new powerful command on complex computing processes. This means that designers have to explore the potentials of their role as commanders of partially automated design processes. In this contribution we describe an approach for the development of a future cognitive design computing system with the focus on urban design issues. The aim of this system is to enable an urban planner to treat a planning problem as a backcasting problem by defining what performance a design solution should achieve and to automatically query or generate a set of best possible solutions. This kind of computational planning process offers proof that the designer meets the original explicitly defined design requirements. A key way in which digital tools can support designers is by generating design proposals. Evolutionary multi-criteria optimization methods allow us to explore a multi-dimensional design space and provide a basis for the designer to evaluate contradicting requirements: a task urban planners are faced with frequently. We also reflect why designers will give more and more control to machines. Therefore, we investigate first approaches learn how designers use computational design support systems in combination with manual design strategies to deal with urban design problems by employing machine learning methods. By observing how designers work, it is possible to derive more complex artificial solution strategies that can help computers make better suggestions in the future. KW - Cognitive design computing KW - machine learning KW - backcasting KW - design synthesis KW - evolutionary optimization KW - CAD Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-25996 SP - 15 EP - 25 CY - Budapest ER - TY - JOUR A1 - Xin, Li A1 - Hijazi, Ihab Hamzi A1 - König, Reinhard A1 - Lv, Zhihan A1 - Zhong, Chen A1 - Schmitt, Gerhard T1 - Assessing Essential Qualities of Urban Space with Emotional and Visual Data Based on GIS Technique JF - ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION N2 - Finding a method to evaluate people’s emotional responses to urban spaces in a valid and objective way is fundamentally important for urban design practices and related policy making. Analysis of the essential qualities of urban space could be made both more effective and more accurate using innovative information techniques that have become available in the era of big data. This study introduces an integrated method based on geographical information systems (GIS) and an emotion-tracking technique to quantify the relationship between people’s emotional responses and urban space. This method can evaluate the degree to which people’s emotional responses are influenced by multiple urban characteristics such as building shapes and textures, isovist parameters, visual entropy, and visual fractals. The results indicate that urban spaces may influence people’s emotional responses through both spatial sequence arrangements and shifting scenario sequences. Emotional data were collected with body sensors and GPS devices. Spatial clustering was detected to target effective sampling locations; then, isovists were generated to extract building textures. Logistic regression and a receiver operating characteristic analysis were used to determine the key isovist parameters and the probabilities that they influenced people’s emotion. Finally, based on the results, we make some suggestions for design professionals in the field of urban space optimization. KW - Stadt KW - Gefühl KW - Geoinformationssystem KW - urban form; Geographical Information System;walking experience; isovists; logistic regression Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20170401-30995 ER - TY - CHAP A1 - König, Reinhard A1 - Varoudis, Tasos T1 - Spatial Optimizations: Merging depthmapX , spatial graph networks and evolutionary design in Grasshopper T2 - Proceedings of ecaade 34: Complexity & Simplicity N2 - In the Space Syntax community, the standard tool for computing all kinds of spatial graph network measures is depthmapX (Turner, 2004; Varoudis, 2012). The process of evaluating many design variants of networks is relatively complicated, since they need to be drawn in a separated CAD system, exported and imported in depthmapX via dxf file format. This procedure disables a continuous integration into a design process. Furthermore, the standalone character of depthmapX makes it impossible to use its network centrality calculation for optimization processes. To overcome this limitations, we present in this paper the first steps of experimenting with a Grasshopper component (reference omitted until final version) that can access the functions of depthmapX and integrate them into Grasshopper/Rhino3D. Here the component is implemented in a way that it can be used directly for an evolutionary algorithm (EA) implemented in a Python scripting component in Grasshopper KW - depthmapx KW - python KW - optimization KW - space syntax KW - grasshopper Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-26040 SP - 1 EP - 6 CY - Oulu, Finland ER - TY - JOUR A1 - Hijazi, Ihab Hamzi A1 - König, Reinhard A1 - Schneider, Sven A1 - Li, Xin A1 - Bielik, Martin A1 - Schmitt, Gerhard A1 - Donath, Dirk T1 - Geostatistical Analysis for the Study of Relationships between the Emotional Responses of Urban Walkers to Urban Spaces JF - International Journal of E-Planning Research N2 - The described study aims to find correlations between urban spatial configurations and human emotions. To this end, the authors measured people’s emotions while they walk along a path in an urban area using an instrument that measures skin conductance and skin temperature. The corresponding locations of the test persons were measured recorded by using a GPS-tracker (n=13). The results are interpreted and categorized as measures for positive and negative emotional arousal. To evaluate the technical and methodological process. The test results offer initial evidence that certain spaces or spatial sequences do cause positive or negative emotional arousal while others are relatively neutral. To achieve the goal of the study, the outcome was used as a basis for the study of testing correlations between people’s emotional responses and urban spatial configurations represented by Isovist properties of the urban form. By using their model the authors can explain negative emotional arousal for certain places, but they couldn’t find a model to predict emotional responses for individual spatial configurations. KW - Emotion KW - Isovist KW - Geo-Statistical Analysis KW - GIS KW - Geografie KW - Architektur Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20160622-26025 N1 - Erschienen in: International Journal of E-Planning Research ; Volume 5, Issue 1 (2016) SP - 1 EP - 19 ER -