WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394
Browse
6 results
Search Results
Article Forecasting the Consumer Price Index in Türkiye Using Machine Learning Models: A Comparative Analysis(Gazi Univ, 2025-09-01) Söylemez, İsmet; Ünlü, Ramazan; Nalici, Mehmet ErenThis study utilizes machine learning models to forecast Türkiye's Consumer Price Index (CPI), thereby addressing a critical gap in inflation prediction methodologies. The central research problem involves the forecasting of CPI in a volatile economic environment, which is essential for informed policymaking. The primary objective of this study is to evaluate the performance of three machine learning models, such as Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM), in forecasting CPI over periods ranging from one to six months, utilizing data from 2012 to 2024. The study's unique contribution lies in the application of the \"SelectKBest\" method, which identifies the most relevant indices, thereby enhancing the efficiency of the models. An ensemble method, Averaging Voting, is also employed to combine the strengths of these models, producing more accurate and robust predictions. The findings indicate that while the RF model consistently generates the most accurate forecasts across all shifts, the SVM model demonstrates a particular strength in the domain of short-term predictions. The ensemble model demonstrates a substantial performance improvement, with a R2 value of 0.962 for one-month ahead of estimates and 0.956 for five-month forecasts. This combined approach has been shown to outperform individual models, offering a more reliable framework for CPI forecasting. The findings offer valuable insights for economic policymakers, enabling more precise and stable inflation predictions in Türkiye.Article Microstrip Stub Filter Design with Enhanced Performance Inspired by SIW Structures Operating at 1.93 GHz GSMBand(Gazi Univ, 2026-03-29) Tosun, Huseyin; Yentur, Abdulkadir; Kilic, Veli TayfunThis paper reports a microstrip stub filter design operating at 1.93 GHz GSM band with enhanced performance inspired by SIW structures. In the designed filter additional vias are placed around the microstrip lines to enhance the encasing of the electromagnetic fields while propagating through the filter to develop the filter performance. The filter was examined with electromagnetic simulations for various numbers of vias and different via to microstrip line distances. Results show that the maximum transmission coefficient (S21 parameter) magnitude value reached in the pass band of the filter increases with the number of the vias and as the vias get closer to the lines. On the other hand, when the via number increases and the space between them and the lines narrows, the frequency at which the maximum S21 value is attained shifts to lower frequencies. The designed filters were manufactured, too. Results obtained in the measurements agree well with the simulation results. Additionally, a receiver system operating at 1.93 GHz band was constructed. System experiments were carried out with the constructed prototype for the manufactured filters. Results show that a greater signal level in the filter pass band is achieved and unwanted signals outside the filter pass band are suppressed more in the system where the filter with vias is used instead of the filter without any additional via. The findings indicate that the designed filters inspired by SIW structures are promising for applications requiring high signal quality.Article Fluctuations in the European Housing Market: Forecasting the House Price Index Change with Time-Series Models(Gazi Univ, 2026-03-15) Soylemez, Ismet; Nalici, Mehmet Eren; Unlu, RamazanThis study presents a comparative analysis of a time series models for forecasting changes in the Housing Price Index (HPI) in 27 European countries. Accurate HPI forecasting is essential for the development of effective policies and investment strategies. The study uses quarterly data from Q4 2013 to Q3 2024. Methodologically, the stationarity of the data is tested using the Dickey-Fuller test and differencing is applied to non-stationary series. The ARIMA, Holt Linear Trend, Additive Damped Trend and Exponential Smoothing models are evaluated based on the lowest mean squared error (MSE) value for each country. The findings confirmed the heterogeneous structure of the European housing market, showing that no single model is suitable for all countries. The ARIMA model provided the most accurate results for nine countries, while the Holt Linear Trend and Additive Damped Trend models performed best in seven countries each. Forecasts for the period 2025-2026 are generated based on these results. This study highlights the importance of adopting country-specific and adaptable forecasting approaches to accommodate the varying dynamics of European housing markets.Article Citation - WoS: 7Conceptual Research of Movement in Kinetic Architecture(Gazi Univ, 2018) Ilerisoy, Zeynep Yesim; Pekdemir Basegmez, MerveIn this study, the place of movement concept in architectural design is investigated; the possibilities provided to the user by evaluating the varying potentials in architectural design have been discussed as a hypothesis. In this direction, movement concept in kinetic structures applied from the 20th century to today are examined. The paper depends on a qualitative methodology, which is a non-numerical method that depends on constructed cases in order to support research hypothesis. Relations, differences and conceptual partnerships between cases have been revealed by investigating the application points of movement and user participation in the design of these structures that is fast-spreading particularly. From the studied examples, it is determined that the surface movement is preferred, when the movement point is taken into consideration the facades are primarily used, and the most common movement type is the sliding movement. Afterwards, it has been revealed that the different physical properties of the movement and the possibilities that are provided change independently of each other. Even in many cases the movement is preferred due to multiple purposes. The most common purpose is adapting to environmental conditions. As a result, this study, which aims to strengthen the perception of architects, will set an example for the development of kinetic architecture.Article Citation - WoS: 10Self-Healing Performance of Biogranule Containing Microbial Self-Healing Concrete Under Intermittent Wet/Dry Cycles(Gazi Univ, 2021) Ersan, Yusuf CagatayDevelopment of self-sensing and self-healing concrete is essential to minimize the labour-intensive monitoring and repair activities conducted for the maintenance of concrete structures. A type of self-healing concrete can be achieved by using microbial agents that induce calcium carbonate precipitation inside a concrete crack. Recently, biogranules consist of nitrate reducing microorganisms were presented as a new generation microbial healing agent and biogranule containing specimens revealed decent healing performance under completely submerged conditions. However, their performance under intermittent wetting conditions, a common case for various concrete structures, remains unknown. This study presents the self-healing performance of biogranule containing biomortar specimens under intermittent wet/dry conditions. In-house produced biogranules were incorporated into mortar specimens at a dose of 1.45% w/w cement (1.00% of bacteria w/w cement) and self-healing performance of cracked specimens were investigated under alternating wet/dry conditions for a crack width range of 50 to 600 um. Upon alternating wet/dry treatment for 4 weeks, cracks up to a 400 um crack width were effectively healed in biomortar specimens. Their water tightness regain was 44% better than control specimens due to their enhanced healing performance. Overall, non-axenic biogranules appear to be useful in development of self-healing bioconcrete for applications under spraying or intermittent wetting conditions.Article Ball Lens Based Mobile Microscope(Gazi Univ, 2016) Icoz, KutayIn this paper we report a low cost, simple and mobile microscope based on attachment of a ball lens to a cell phone. The system's noise and parameters affecting the image quality is investigated. The ball lens provides approximately 100X magnification and together with the cell phone's integrated lens and image sensor, 3,4-micron resolution is reached. The field-of-view of the system is 1500x1500 mu m where the price of the ball lens and the holder is less than 10 cents. By using this system as an optical light microscope, we are able to acquire images of micro particles and micro sensors. When combined with image processing methods, this optical system is capable of doing complex analysis as an alternative to commercial optical light microscopes.