A Model for Decision Support in Energy Efficient Redesign Process

PHD Research

Ahu Sokmenoglu




PhD started in: 1 January 2008


Latest graduate degree MArch, Istanbul Technical University


undergraduate degree  Architect


Promoter(s): Prof. Dr. ir. Sevil Sariyildiz


Co-promoter: Prof. Dr. Gulen Cagdas (Istanbul Technical University)


Daily Supervisor(s): Rudi Stouffs



Main Question:

What kind of patterns and relationships can be extracted from existing pointillist (Doel, 1999) urban analysis maps of Beyoglu by the application of Knowledge Discovery and Data Mining methodologies and how this type of knowledge can assist architects and urban planners at design, policy and strategy levels?




-a methodological framework for the application of Knowledge Discovery methodologies in urban feature analysis

-a micro-scale GIS database for Beyoglu Preservation area









Keywords: Urban Data Analysis, Data Mining, Knowledge Discovery in Databases, Micro-scale GIS database, Beyoglu



Area of Research: Computation & Performance



Chair of Design Informatics, Dept. of Architectural Engineering + Technology, Faculty of Architecture





































Research Summary:

In the early 21st century, information of the city and its users comes to light with a set of new-sophisticated tools (fuzzy sets, neural networks, genetic algorithm, evolutionary computation, data-mining methods) for dealing complexity of natural and artificial systems. This is very fascinating and promising for the future of cities in two terms; to provide solutions to the major problems of cities and to understand more the complexity of the cities. Hence, exploring new techniques and methodologies of data analysis to implement in urban analysis is the major motivating aspect behind this research. Within this perspective, the main goal of this research is to develop a conceptual and methodological framework to uncover hidden patterns and relationships among urban features within an urban context by analyzing multi-dimensional, micro-scale urban data. To achieve this aim a particular urban context is chosen as a test area, a micro-scale GIS database is constructed and a particular method of analysis is applied. This research applies Data Mining as a methodology of Knowledge Discovery in urban feature analysis with a particular interest in exploring the patterns and relationships of micro-scale data in Beyoglu (a historical district of Istanbul). The major data source is the conventional cartographic representations of Beyoglu obtained in the form of various classification maps from Istanbul Metropolitan Municipality.



Research Methodology:

Research methodology that is developed for the realization of this research has four main steps; exploratory phase, involving exploration of the literature on urban conceptualizations and theories, various tools, techniques and methods applied in urban analysis and practice side by side with recent developments in computation and information science; phase of research formulation, in which the knowledge gathered in previous phase is used for developing a specific conceptual framework for cities and a specific methodological framework for urban analysis; the implementation phase consists of the construction of a micro-scale GIS database and three different applications of Knowledge Discovery methods (Data Mining techniques) in urban analysis based on this database and the critical reflection phase where a critical review of the conceptual and methodological approach is done based on the findings of the implementation phase; and the research ends with a set of future projections.



Key Publications:

- Sokmenoglu, A., Sonmez, N. O., 2013, Exploring Reciprocal Relationships of Land-use Patterns in Cihangir, eCAADe 2013: Computation and Performance, TU Delft, September, 18-20 2013, Delft

- Sokmenoglu, A., Çagdas, G., Sarıyıldız, S., 2012 “Exploring Relationships of an Urban System: Beyoglu”, International Planning History Society Conference 2012, Sao Paulo, Brasil, 15-18th July

- Sokmenoglu, A., Çagdas, G., Sarıyıldız, S., 2011, “A Multi-Dimensional Exploration of Urban Attributes by Data Mining”, Proceedings of the CAAD Futures 2011: Designing Together, ULg, P.Leclercq, A. Heylighen and G. Martin (eds.), 2011, Liege, Belgium, p. 333-349

- Sokmenoglu, A., Çagdas, G., Sarıyıldız, S., 2011, “Application of Data Mining In Micro-scale Urban Feature Analysis”, Proceedings of the 11th International Conference on GeoComputation, University College London, UK 20th – 22nd July 2011, p. 154-160

- Sokmenoglu, A., Çagdas, G., Sarıyıldız, S., 2010, “Exploring the Patterns and Relationships of Urban Attributes by Data Mining”, eCAADe 2010: Future Cities, ETH Zurich, Zurich, September 15-18, 2010, p. 873-881.





Telnr +3127892136


Room 01+.West.040


Faculty of Architecture and the

Built Environment


Building 8


Julianalaan 134


2628 BL Delft