Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
6 results
Search Results
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 Optimized Cooperative Routing for Autonomous Vehicles(Institute of Electrical and Electronics Engineers Inc., 2025) Saydam, B.; Ayav, T.Current traffic control systems - comprising traffic lights, signs, and right-of-way rules - are often inadequate, leading to accidents, excessive fuel consumption, and unnecessary delays. Three key scenarios contribute to these inefficiencies. First, drivers may run red lights due to a lack of traffic signal timing information, leading to indecision when encountering a yellow light, a major cause of accidents. Second, abrupt speed changes in response to traffic signals force drivers to brake suddenly, increasing fuel consumption and travel time. For instance, a driver may accelerate at a green light only to encounter a red light shortly after, resulting in inefficient fuel use. Lastly, vehicles often remain stopped at red lights despite no cross-traffic, leading to wasted fuel and time.This study simulates these scenarios using the Eclipse SUMO tool, with results aligning with expected inefficiencies. The problem is mathematically modeled using Pyomo, and a centralized optimization approach is applied to enhance traffic synchronization and efficiency. By dynamically calculating vehicle velocities based on real-time traffic data, the study proposes an optimized, traffic light-free system. The results demonstrate improved fuel efficiency, reduced accidents, and minimized delays, highlighting the potential of centralized optimization in modern traffic management. © 2025 Elsevier B.V., All rights reserved.Article Citation - WoS: 3Citation - Scopus: 3Shelf-Life Extension of Traditional Licorice Root “sherbet” With a Novel Pulsed Electric Field Processing(Frontiers Media S.A., 2023) Akdemir Evrendilek, Gulsun; Demir, Irem; Uzuner, SibelPulsed electric field (PEF) processing of licorice root "sherbet" (LRS) by various electric field strengths (7.00, 15.50, and 24.10 kV/cm), treatment times (108, 432, and 756 mu sec), and processing temperatures (6, 18, and 30 degrees C) according to the Box-Behnken design were performed. The samples were analyzed for pH, titratable acidity, conductivity, turbidity, total reducing sugar, color (L*, a*, and b*), hue, chroma, total color difference, color intensity, color tone (yellow, red, and blue color tones), total antioxidant capacity, total phenolic substance content, and sensory properties. Results revealed that PEF processing did not adversely affect most of the physical, chemical, and sensory properties of LRS, with a maximum of 2.48, 4.04, 1.78, and 1.20 log reductions on the initial total mesophilic aerobic bacteria, total mold and yeast, Bacillus circulans, and Candida tropicalis. The response variable modeled for the PEF was found to be conductivity, with the optimum processing conditions of 6.90 kV/cm, 756.00 mu s, and 7.48 degrees C. After that, the samples were stored at 4 degrees C and 22 degrees C for shelf-life studies. Control samples at 4 degrees C and 22 degrees C were spoiled on the fifth and second days, whereas PEF-treated samples stored at 4 degrees C began to deteriorate after the 40th day and the samples stored at 22 degrees C after the 30th day, respectively. It was revealed that PEF is a suitable process to extend the shelf-life of licorice "sherbet" with preservation of physicochemical and sensory properties.Article Citation - Scopus: 8Optimal Design of the Type Iii Hydrogen Storage Tank for Different Carbon/Epoxy Materials by Modified Differential Evolution Method(MIM RESEARCH GROUP, 2019) Ayakdaş,O.; Aydın,L.; Savran,M.; Küçükdoğan,N.; Öztürk,S.In this study, the main objective is to minimize the failure index of a cylindrical laminated composite hydrogen storage tank under internal pressure. The first step is to obtain the distribution of stress components based on Classical Laminated Plate Theory (CLPT). The second is to evaluate the burst pressure of the tank according to three different first ply failure criteria and then to compare the results with the experimental and numerical ones from literature. In the final part of the study, the best possible combination of winding angles, stacking sequences and thicknesses of laminates satisfying minimum possible stress concentration will be obtained for different Carbon/Epoxy materials by Differential Evolution Method. The stress components and, the burst pressures reached according to Hashin-Rotem, Maximum Stress, and Tsai-Wu first-ply failure criteria, have been complied with experimental and numerical results in the literature for Type III pressure vessels. Manufacturable Type-III tank designs have been proposed satisfying the 35 MPa burst pressure for different Carbon/Epoxy materials. © 2019 MIM Research Group. All rights reserved.Book Part Citation - Scopus: 1A New Stable Solar System for Electricity, Cooling, Heating, and Potable Water Production in Sunny Coastal Areas(Springer, 2023) Khani, Leyla; Mohammadpourfard, MousaNowadays, more attention is paid to provide clean energy products with low environmental pollution in a decentralized way. Many coastal rural areas suffer from freshwater and electricity scarcity, especially in hot weather condition. Meanwhile, these regions have a great access to intense solar radiation and seawater. Hence, it seems logical to use the available solar energy in those places to provide to necessities like power, heating, and cooling. A new solar cooling, power, heating, and freshwater production system is designed, evaluated, and optimized in this research. The proposed system is composed of several subsystems to generate each product with high efficiency and reliability. Solar energy is unavailable at night, so molten salt energy storage is used to establish the steady operation of the system. Then, the system is evaluated from thermodynamic and exergoeconomic viewpoints, and a parametric study is accomplished to study the effect on the system performance of key variables. In the end, the system is optimized to determine its best operating condition for different cases. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Conference Object Citation - Scopus: 1Effects of Processing on the Properties and Permeability of Pure Gases Through Sol-Gel Silica Membranes(Trans Tech Publications, 2004) Topuz, Berna; Çiftçioğlu, Muhsin; Özkan, FehimeN2, O2 and CO2 pure gas permeation through sol-gel derived silica membranes were determined and the effects of processing parameters on the microstructure of the membrane was investigated. Silica sols were prepared in an alcoholic solution by hydrolysis and condensation of TEOS as a function of acid content. The thickness of the silica membranes was determined to be about 2μm and significant infiltration into the support was observed from the SEM pictures. The supported membranes were heat treated in the 50-400°C. The N2 permeabilities of silica membranes varied in the 2.2*10-10-2.7*10-8 mol/m2.s.Pa range for single layer membranes dipped for 10s. in the sol. The CO2 permeability of these membranes varied in the 1.2*10-9-6.95 *10-8 mol/m2.s.Pa range. The sols became viscous and gelled at 50°C in 16 hours. The O2 permeability increased with aging time. The optimum dipping time during processing was determined to be 10 seconds. The increase in the acid content of the sols were observed to increase permeabilities of the membranes significantly.