Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
1031 results
Search Results
Now showing 1 - 10 of 1031
Conference Object A General Predictive Model to Evaluate Daylight Levels of Residential Buildings in the Mediterranean (Next Med) Region(Education and Research in Computer Aided Architectural Design in Europe, 2025) Ekici, B.Conceptual design is one of the most critical phases, as design decisions affect the buildings’ performance throughout their life cycle. Researchers consider various computational methods to achieve effective design proposals. Nevertheless, optimization algorithms are necessary to cope with the complexity and increase the efficiency of design alternatives in various aspects. In sustainable building design, these decisions require computationally expensive processes due to the simulation tasks. Besides, making sustainable design decisions is even more challenging in a Mediterranean climate due to changing conditions throughout the year. Therefore, recent studies frequently consider combining predictive models with optimization algorithms to decrease the burden of expensive simulation time. Relevant works present promising outcomes, yet they are limited to predicting the building performance of specific cases; thus, the proposed predictive models are limited to different design problems. This paper investigates the development of a general machine learning (ML) model to overcome this issue. With this motivation, a parametric test box consisting of twenty parameters related to weather data of twelve Mediterranean (Next Med) countries, space dimensions, vertical/horizontal louvers, and material type is developed using Grasshopper 3d. Moreover, a parametric urban model, which considers eight parameters related to the density of the surrounding buildings, is also created to generate numerous environments. The LadyBug tools simulate the daylight autonomy to generate 12,000 samples. Five different ML models involving artificial neural networks (ANN) are built in Python. Statistical results showed that train and test scores achieved promising outcomes in all ML models. However, when predicting user-defined scenarios not involved in the generated dataset, only ANNs perform generalizable, accurate predictions. The paper discusses the ability of ANN models to accurately predict different design scenarios and locations, and the trustworthiness of the training and test scores based only on collected data. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Conference Object Metacognitive, Cognitive, and Creative Dynamics in the Artificial Intelligence-Aided Design Process(Education and Research in Computer Aided Architectural Design in Europe, 2025) Yazici, G.; Doǧan, F.This study examines the effects of artificial intelligence-aided design processes (AIADP) on cognitive load, creativity, and metacognitive awareness. Within the scope of the study, a one-day face-to-face workshop was organised with twenty-eight architects, including architecture students studying at undergraduate and graduate levels, and the data based on the participants' experiences were analysed using qualitative research methods. The results of the sentiment-based content analysis show that integrating AI tools into the design process reduces cognitive load, supports creative thinking processes, facilitates rapid prototyping and feedback mechanisms, and increases metacognitive awareness. The findings reveal that AI-aided design tools can potentially improve designers' cognitive and creative capacities. The study addresses the effects of AIADP in educational and professional contexts from a local perspective, providing a new perspective on the literature on the integration of AI into design processes. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Conference Object Differential and Linear Analyses of Dizy Through MILP Modeling(Springer Science and Business Media Deutschland GmbH, 2026) İlter, M.B.; Koçak, O.; Kara, O.; Sulak, F.In this work, we present the first independent security analysis of DIZY, a recently proposed ultra-lightweight stream cipher with two variants: DIZY-80 and DIZY-128. Our analysis focuses on DIZY’s resistance to linear and differential cryptanalysis. We employ a formal technique known as Mixed Integer Linear Programming (MILP), which enables us to model the internal structure of DIZY and search for characteristics that describe how XOR differences or linear masks propagate through the cipher. Specifically, we construct such characteristics to evaluate how many S-boxes become “active” during keystream generation, as this number directly affects the cipher’s resistance to these attacks. Contrary to the designers’ claim that any linear or differential characteristic over 8 rounds must involve at least 20 active S-boxes in DIZY-80 and 22 in DIZY-128, we identify characteristics with only 18 differentially or linearly active S-boxes and 20 linearly active S-boxes, respectively. We mount two distinguishing attacks on each cipher. Our 3-round linear distinguishing attack requires 223 bits of keystream, while the 4-round version requires 235 bits for DIZY-128 and DIZY-80, respectively. Our 2-round differential resynchronization attacks succeed using only the first four bytes of keystream data from approximately 230 and 226 different initializations with chosen initialization vectors (IVs) for DIZY-128 and DIZY-80, respectively. While these attacks do not compromise the full 15-round version of the cipher, they provide valuable insights into the design of DIZY and contribute to a deeper understanding of the security requirements of its diffusion layer. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.Conference Object Material Optimisation for Future Double Skin Façade System Design(Institute of Physics, 2025) Unluturk, M.S.; Kazanasmaz, Z.T.; Ekici, B.; Göksal Özbalta, T.G.Façades have a significant impact on energy consumption in interiors. Designers aimed to reduce energy consumption by developing different façade systems. Double Skin Façade (DSF) aims to increase thermal and ventilation performance in the interior. The depth of the cavity gap between the two façade layers with air inside may adversely affect indoor daylight performance. In addition, studies in the literature indicate that this façade system shows optimum performance in cold climates. With the right design decisions, the DSF system can provide optimum performance in hot climates. In building designs with DSF systems in these climate zones, daylight and energy simulations can make the right design decisions. However, the climate crisis (CC) is increasing air temperatures and sunshine hours in hot and arid climate zones. Simulations are based on current climate data, and the recommendations obtained may not show optimum performance in the future. The study aims to propose an educational building model with a DSF system that will provide optimum visual comfort for 50 years in the Mediterranean climate type (CSA). Meteonorm has created weather scenarios for Izmir for 2050 and 2080. Opossum and Galapagos carried out the optimisation process using this data. The study proposes models that will perform optimally in Izmir for 50 years. © Published under licence by IOP Publishing Ltd.Conference Object Design of Adaptive Shading Device with Rigid Origami Technique: Improving Outdoor Thermal Comfort on Pathways of University Campus(Institute of Physics, 2025) Dağlier, Y.; Ekici, B.; Korkmaz, K.Since urbanization emerged with consequences for the built environment, shadows have played a key role in outdoor comfort. In hot climates, shadow has become a vital element in public spaces as it significantly affects social interaction on various occasions, such as university campus areas. The current state of the art shows that the role of shadings in outdoor environments is crucial to increasing pedestrian comfort and supporting overall well-being. While trees and canopies are commonly used for shading, their applicability is sometimes limited in pedestrian pathways. For example, the Izmir Institute of Technology (IZTECH) campus copes with outdoor discomfort during the extremely hot summer days. Due to the changing environmental conditions, static shading devices offer effective shadows only at specific times. This creates a necessity to design shading devices that can rotate and fold to mitigate temperatures more effectively and increase outdoor thermal comfort. A parametric shading model was developed using Grasshopper and Kangaroo Physics®, and its effectiveness was analyzed using Building Performance Simulation (BPS) tools. The research integrates heuristic optimization techniques to enhance shading performance, including Galapagos (Genetic Algorithm) and Opossum (RBF-opt and CMA-ES). Results indicate that the proposed kinetic shading devices reduced the universal thermal climate index (UTCI) by approximately 20% during peak sunlight hours. These findings suggest that adaptive shading strategies efficiently improve outdoor thermal comfort in urban public spaces. © 2025 Published under licence by IOP Publishing Ltd.Conference Object Energy-Efficient Urban Design Proposal in Urban Heat Island Formation: The Case of CSA Climate(Institute of Physics, 2025) Unluturk, I.U.; Yavuz, E.; Unluturk, M.S.; Akgun, B.Nowadays, unplanned construction resulting from urban growth and population increase reduces the resilience of cities and their historical texture and increases the need for buildings for housing in cities. This situation, which increases the density/height of city buildings, increases the surface temperature and reduces the green tissue, causes urban heat island. In this study, the Dumlupinar neighbourhood of Balıkesir, which attracts attention with its historical texture and where new buildings are designed in certain parts today, will be discussed. First, the areas with traditional and new buildings in the region are modelled parametrically in the Rhino/Grasshopper interface, obtained and compared through Dragonfly software and an urban prototype is created. However, in the computational design algorithms to be performed, not only today's weather scenario but also the weather scenario of 2050 was used. Models were created to minimise the urban heat island in 2050 climate conditions. This urban prototype is a proposal for sustainable cities to be built in cities in CSA climate types (Mediterranean climate). This proposal will guide municipalities in designing energy-efficient and carbon-neutral cities using the urban model of the urban heat island effect. © 2025 Institute of Physics Publishing. All rights reserved.Conference Object Assessment of Drought in Izmir District Using Standardized Precipitation Index(Springer Nature, 2025) Mersin, D.; Gulmez, A.; Safari, M.J.S.; Vaheddoost, B.; Tayfur, G.One of the main issues with agro-food and socio-economical security in the world is droughts. Regardless of cause or effect, the ever-changing climate is placing increasing strain on water resources pushing supply to its limits. Izmir, a growing city in Turkey, is endowed with variety of water resources, such as lakes, rivers, seashores, and groundwater reserves. Therefore, it is crucial for the planning and development of the area to examine past and foreseeable drought occurrences and their possible impact on water resources. In this regard, the study’s goal is to assess historical droughts in Izmir District. Data from three meteorological stations in Küçük Menderes basin, collected between 1973 and 2020, are utilized in this study. To establish the validity of the posterior drought analysis, the consistency and trend in the time series are first examined using the double mass curve, run test, and linear trend analysis. The next step is to assess the historical deficit related to meteorological, agricultural, and hydrological droughts using the SPI and moving mean (MA) operator. The temporal analysis of SPI reveals distinct drought patterns across the stations, with multiple moderate to extreme droughts occurring particularly between 1998 and 2010, highlighting significant spatial and temporal variability in drought severity and frequency. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.Conference Object An Experimental Study to Investigate the Efficiency of Floating Pontoons on the Wave Overtopping Reduction(International Society of Offshore and Polar Engineers, 2025) Ozbahceci, B.O.; Eroglu, N.There are many studies focused on the wave transmission performance of floating structures. However, the performance of floating structures to prevent coastal floods has not yet been investigated considering wave overtopping. This study aimed to experimentally assess the wave overtopping performance of a concrete floating pontoon in front of an existing vertical sea wall. The mean wave overtopping discharge, q, was compared for the cases with and without the floating pontoon model in front of the wall. Results showed that the baseline floating pontoon model reduced wave overtopping discharge by 30-90% compared to the case with the wall alone. Furthermore, the study revealed that an increase in freeboard or draft of the floating pontoon led to a greater reduction in wave overtopping. These findings suggest that the integration of a floating pontoon with optimized freeboard and draft could be an effective solution for reducing wave overtopping in coastal defense applications. © 2025 by the International Society of Offshore and Polar Engineers (ISOPE).Conference Object Developing Machine Learning Models to Predict Outdoor Thermal Comfort of Kinetic Shading Devices: An Approach for Global Optimization(Education and Research in Computer Aided Architectural Design in Europe, 2025) Dağlier, Y.; Ekici, B.; Korkmaz, K.Utilizing artificial intelligence (AI) methods in the design process supports the achievement of sustainable alternatives during the conceptual design. In various AI methods, optimization and machine learning (ML) algorithms are the most common methods to develop predictive models and discover favorable design alternatives with significantly reduced computational time. Recent works focused on limited datasets, as well as the evaluation of the developed prediction models based on collected data. During the optimization process of complex design problems, the number of design parameters becomes enormous; thus, search areas contain many design alternatives that might lead the search outside of the collected data. Therefore, evaluating the accuracy of prediction models only based on the collected samples may result in scenarios where the predicted outcome during the optimization process aligns with an unrealistic solution. This study investigates how accurately prediction models developed using different ML algorithms can perform in optimization processes. The proposed framework is used to cope with outdoor thermal performance, considering kinetic shading devices with rigid origami techniques. A parametric shading device model with kinematic principles and 10 design parameters is created in Grasshopper 3d. LadyBug is used to analyze the performance of the universal thermal climate index (UTCI). To minimize the UTCI, the radial basis function optimization (RBFOpt) algorithm in the Opossum plugin is used. To compare the optimization results with the prediction results, multiple linear regression, support vector machines, random forest, polynomial regression algorithms, and artificial neural networks (ANN) are developed to predict outdoor thermal comfort performance targets on each collected data set with 2000 samples. Results showed that ANN models can provide more accurate predictions during the optimization process. The paper aims to discuss the way ML algorithms are applied and evaluated for ML-based optimization domains in design problems. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Conference Object Combining Generative Adversarial Networks and Reinforcement Learning for Floor Plan Layout Generation(Education and Research in Computer Aided Architectural Design in Europe, 2025) Güldilek, M.; Ilal, M.E.; Ekici, B.Generative Adversarial Networks (GANs) are among artificial intelligence (AI) methods for generating architectural floor plan layouts to approximate spatial distribution with a reasonable degree of accuracy. However, when used exclusively, GAN-based tools may fail to capture architectural patterns and often produce unrealistic layouts. To address this limitation, researchers have proposed integrating Reinforcement Learning (RL) into GANs. While RL has been combined with generative algorithms in other fields, a systematic multi-scenario integration of GANs and RL remains underexplored in architecture. This paper introduces a new solution by combining RL and GANs to generate floor plan layouts tailored to user requirements. The research design involves three different integration strategies: (1a) mere generation, where RL refines GAN outputs by eliminating inconsistencies and errors; (1b) objective optimization, where RL targets measurable attributes such as spatial size and morphological legibility; and (1c) refinement of non-quantifiable attributes, where RL incorporates user feedback to improve flexibility and perceived comfort. Additionally, the study employs House-GAN++ as the GAN model and the PPO algorithm as the RL framework. Three case studies are presented to evaluate performance. Results demonstrate that integrating RL with GANs yields floor plan layouts more responsive to user needs than those produced by GANs alone. Each scenario illustrates how RL optimizes GAN-generated outputs according to functional, measurable, and perceptual goals. The methodology acknowledges user expectations and translates them into realistic, adaptable plans. Key outcomes include more realistic layouts, designs with distinctive characteristics, and user-customized floor plans created through interaction. The proposed framework enables automatic floor plan generation that combines design, optimization, and user input at the conceptual stage. This integration enhances architectural design processes by balancing computational efficiency with user-oriented adaptability, thus broadening the potential of AI-assisted design. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.