Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Çakmak, Recep(3)
- Çevik, Sibel(2)
- Aksakal, Vecihi(1)
- Altas, Ismail Hakk(1)
- Altas, Ismail Hakki(1)
- Altaş, Ismail Hakki(1)
- Atil, Hulya(1)
- Barut, Abdulkadir(1)
- Demir, Bayram(1)
- Kalkan, Yusuf(1)
- Kiliçarslan, Tolga(1)
- Okutan, Murat(1)
- Osman Duman(1)
- Ozdogan, Hasan(1)
- Ozyildirim, BM(1)
- Sekerci, Mert(1)
- Sevim, Gencay(1)
- Soydaş, Şafak Sönmez(1)
- Takma, Cigdem(1)
- Ulutas, Ahsen(1)
- Yildirim, T(1)
- Çam, Alper Veli(1)
- Üncü, Yigit Ali(1)
Yayınlar
- MakaleYalnız künye2026Artificial Neural Network-Based prediction of production cross sections of the medical radioisotopes 67Ga and 89Zr
Okutan, Murat; Üncü, Yigit Ali; Sevim, Gencay; Sekerci, Mert; Kiliçarslan, Tolga; Demir, Bayram; Ozdogan, Hasan
In this study, the excitation functions of the 67Zn(p,n)67Ga, 68Zn(p,2n)67Ga, and 89Y(p,n)89Zr reactions were investigated. Nuclear reaction simulations were performed using the TALYS 1.95 and EMPIRE 3.2 codes, by using Two Component Exciton Model, Geometry Dependent Hybrid Model, Exciton Model, and Hybrid Monte Carlo Simulation. In parallel, a feedforward artificial neural network (ANN) trained with the Levenberg-Marquardt (LM) algorithm was employed to predict the same reaction cross-sections using experimental data. Comparative analysis revealed a strong consistency between TALYS and EMPIRE calculations, ANN predictions, and experimental results, with the ANN providing enhanced predictive performance in energy regions where experimental data are sparse or uncertain. Furthermore, activation and yield calculations confirmed the feasibility of producing clinically relevant quantities of 67Ga and 89Zr under realistic irradiation conditions. In conclusion, the use of physics-based nuclear reaction codes with data-driven ANN models has been demonstrated to be useful in medical radionuclide production studies by providing a complementary framework for cross-section estimation.
- MakaleAçık Erişim2025Efficiency analysis using the machine learning algorithms: model development and verification
Soydaş, Şafak Sönmez; Kalkan, Yusuf; Çam, Alper Veli; Barut, Abdulkadir
Recently, machine learning (ML) algorithms have been employed intensively in the field of finance as in all sectors. The issues such as financial distress prediction, bank credit risk calculation, etc., have been analyzed using ML algorithms. This study aimed to determine firm performance with the data envelopment analysis (DEA) method, sensitivity analysis, and ML algorithms and analyze the efficiency of companies via artificial neural networks (ANNs), support vector machines (SVMs), and logistic regression (LR) classification algorithms. In the study, first, 10 financial ratios were categorized into two parts, such as output and input, and efficiency scores were determined in MS Excel software. The obtained scores were included in the ML algorithm as a categorical dependent variable. Secondly, the data were extracted and included in the analysis software as 80% training and 20% test data, and the accuracy of ML algorithms was tested. Lastly, a comparative analysis of the estimation and classification algorithms of active and inactive companies was conducted. As a result of the analysis, the best classification prediction was seen as the ANN algorithm. SVM and LR algorithms also made an acceptable level of classification prediction. It was expected that the study would have contributed to the literature in terms of testing the companies whose efficiency scores were determined by the DEA method with ML techniques and determining which technique was more successful.
- BildiriYalnız künye2018Hourly Solar Irradiation Prediction by Artificial Neural Network Based on Similarity Analysis of Time Series
Ulutas, Ahsen; Çakmak, Recep; Altas, Ismail Hakki; Ozyildirim, BM; Yildirim, T
Solar energy is a renewable energy source which has intermittent and variable characteristic. Solar irradiation must be predicted in advance in an electrical grid which has solar energy based electrical power generation systems in order to operate the electrical grid stable and efficient. In this study, a multi-layered, feed forward artificial neural network (ANN) has been designed to predict the hourly solar irradiation of next day. The designed ANN has been trained by data which has been obtained via similarity analysis. Total solar irradiation on horizontal plane, relative humidity and temperature data of Trabzon province for 2015-2017 have been used as the training data set. Hourly solar irradiation prediction has been performed by utilizing the designed ANN and test data set. The prediction results have been evaluated as to root mean square (RMS), mean absolute error (MAE) and mean absolute percentage error (MAPE) performance criteria. The obtained performance criteria results show that the proposed ANN could make prediction with acceptable error.
- BildiriYalnız künye2017A Day Ahead Hourly Solar Radiation Forecasting by Artificial Neural Networks: A Case Study for Trabzon Province
Çevik, Sibel; Çakmak, Recep; Altas, Ismail Hakk
The integration of renewable energy sources to the electrical grid leads to some issues in the grid because of intermittent and variable characteristics of renewable energy sources such as wind and solar. It has been predicted that the solar based electricity production will has highest annual increase rate among the other renewable sources. Due to the intermittent and volatile nature of the solar energy in an electricity grid where photovoltaic systems are intensive, load planning is essential. Therefore, day ahead solar radiation forecasting will contribute to the load planning studies. Artificial neural networks are one of the methods that are applied frequently and successfully in forecasting studies. In this study, a cause effect based artificial neural network (ANN) has been designed and performed for day ahead hourly solar radiation forecasting in Trabzon province. A similar day selection algorithm has been utilized to get more accurate forecasting by the ANN. The designed ANN has been trained and tested in MATLAB simulation environment without using ready codes of MATLAB ANN toolbox. The obtained results reveal that the designed ANN forecasts the solar radiation with acceptable error for a place such as Trabzon which has rainy and cloudy weather conditions.
- BildiriYalnız künye2017A day ahead hourly solar radiation forecasting by artificial neural networks: A case study for Trabzon province; [Yapay Sinir Aǧlari ile Gün Öncesi Saatlik Güneş Radyasyonu Tahmini: Trabzon İli Örneǧi]
Çevik, Sibel; Çakmak, Recep; Altaş, Ismail Hakki
The integration of renewable energy sources to the electrical grid leads to some issues in the grid because of intermittent and variable characteristics of renewable energy sources such as wind and solar. It has been predicted that the solar based electricity production will has highest annual increase rate among the other renewable sources. Due to the intermittent and volatile nature of the solar energy in an electricity grid where photovoltaic systems are intensive, load planning is essential. Therefore, day ahead solar radiation forecasting will contribute to the load planning studies. Artificial neural networks are one of the methods that are applied frequently and successfully in forecasting studies. In this study, a cause effect based artificial neural network (ANN) has been designed and performed for day ahead hourly solar radiation forecasting in Trabzon province. A similar day selection algorithm has been utilized to get more accurate forecasting by the ANN. The designed ANN has been trained and tested in MATLAB simulation environment without using ready codes of MATLAB ANN toolbox. The obtained results reveal that the designed ANN forecasts the solar radiation with acceptable error for a place such as Trabzon which has rainy and cloudy weather conditions.
- Yüksek Lisans TeziAçık Erişim2016Batı Anadolu bölgesindeki depremlerin yapay sinir ağı yöntemiyle tahmini
Osman Duman
Gerçekleşecek depremleri önceden kesin bilen, genelleştirilebilecek bir yöntem günümüze kadar geliştirilememiştir. Fakat birçok yöntemle deprem tahmini yapılmaya çalışılmaktadır. Bu yöntemlerden birisi olan Yapay Sinir Ağları, belirlenen girişler ve çıkışlar arasındaki ilişkiyi öğrenerek faklı örüntülere karşı uygun çıkışlar vermektedir. Bu çalışmada Gutenberg-Richter ilişkisine bağlı ve deprem tahminlerinde kullanılan b_değerini temel alan bir ileri beslemeli geri yayılımlı yapay sinir ağı geliştirilmiştir. Türkiye'nin Batı Anadolu Bölgesinde yoğun sismik aktiviteye sahip dört faklı bölgeyi içeren deprem verileri kullanılarak yapay sinir ağı eğitilmiştir. Bu amaçla, Batı Anadolu'da yoğun sismik aktiviteye sahip Gölhisar Çameli-Muğla Rodos Bölgesi, Burdur Fay Zonu, Büyük ve Küçük Menderes Graben bölgesi ve Gediz Alaşehir Graben bölgesi üzerinde çalışılmıştır. Eğitim aşamasından sonra aynı bölgeler için daha sonraki tarihlere ait deprem verileri test etmek için kullanılmış ve ağın başarısı ortaya konmuştur. Çalışmada geliştirilen ağın tahmin sonuçları incelendiğinde; ağın gerçekleşmeyecek dediği deprem tahmin sonuçları tüm bölgelerde oldukça yüksek çıkmıştır. Bunun yanında ağın gerçekleşecek dediği deprem tahmin sonuçları, çalışılan bölgeler için belli bir oranda farklı sonuçlar vermiştir. Sonuç olarak bu yöntem kabul edilebilir oranda başarılıdır.
- MakaleYalnız künye2012Comparison of Multiple Linear Regression and Artificial Neural Network Models Goodness of Fit to Lactation Milk Yields
Takma, Cigdem; Atil, Hulya; Aksakal, Vecihi
In this study, effects of lactation length, calving year and service period on lactation milk yield of Holstein Friesians were modeled with multiple regression and artificial neural networks (ANN) and compared goodness of fit of models. Analyses were carried on five lactations milk yields of 305 Holsteins calved at 2006, 2007 and 2008 years. After several experiments, hidden layer number was taken one and hidden nodes number were found three for the chosen architecture. Moreover, convergence criteria, maximum iteration number and epoch number were taken as 1.10(-6), 50 and 20, respectively. Adjusted coefficient of determination (R-2),root mean square error (RMSE), mean absolute deviation (MAD), mean absolute percentage error performance criteria (MAPE) were used for comparison of artificial neural network and multiple linear regression models goodness of fit. After analysis R-2 values were found among 0.62-0.85 for the five lactations with neural networks model. RMSE, MAD and MAPE criteria also were found among 480.9-1682.8, 325.2-1381.7 and 6.1-20.2, respectively. These criteria were found for R-2, RMSE, MAD and MAPE among 0.30-0.75, 1964.8-30008.7, 1576.6-2458.3 and 24.7-35.6, respectively for multiple linear regression. When the models were compared, artificial neural networks model gave better fit than multiple linear regression models. Consequently, artificial neural networks was determined an alternative method to multiple regression analysis.
