Random Forest (RF), rastgele oluşturulmuş birden çok karar ağacının çıktısını birleştiren, regres... more Random Forest (RF), rastgele oluşturulmuş birden çok karar ağacının çıktısını birleştiren, regresyon ve sınıflandırma problemlerini çözmek için kullanılan bir makine öğrenme algoritmasıdır. RF algoritması, karar ağaçlarının tahminlerinden yola çıkarak sonuca ulaşmayı sağlar. Ormandaki ağaç sayısının artması algoritma sonucunun kesinliğini arttırır. RF algoritması ormandaki karar ağaçları üzerinde rastgele ve sürekli olarak işlem gerçekleştirdiği için paralel mimaride platformlar üzerinde çalıştırılması ile olumlu sonuçlar elde edilebilir. Field Programmable Gate Array (FPGA) entegre devreler, paralel işlem yapabilme yeteneğine sahip olduğundan, RF algoritmasının donanım üzerinde gerçekleştirilen uygulamalarında kullanılması performansı arttırmaktadır. Gerçekleştirilen çalışmada RF algoritması sayısal bir veri seti ile hem MATLAB üzerinde hem de FPGA üzerinde çalıştırılarak sınıflandırma işlemleri gerçekleştirilmiştir. Algoritmadaki işlem modüllerinin ve tüm mantıksal tasarımların ge...
Trends in Data Engineering Methods for Intelligent Systems, 2021
Recently, deep learning techniques have achieved significant success in medical image analysis. I... more Recently, deep learning techniques have achieved significant success in medical image analysis. In this article, deep learning methods have been applied to separate brain magnetic resonance (MR) images into different abnormalities and healthy classes. The sectional brain MR of brain images is used as a database from the Open Access Imaging Studies Series (OASIS). Based on Convolutional Neural Network (CNN) method for classification and a thresholding algorithm for image segmentation, the system has been developed. The images that are improved by image processing are transferred to the CNN deep learning model and the classification process is done. Adam algorithm was used as the optimization algorithm for the classification process. As a result of the classification, 80% accuracy rate was obtained. The model’s loss rate fell to 0.3 s.
2017 International Conference on Computer Science and Engineering (UBMK), 2017
Course timetabiling is a process that must be done at the beginning of the education period in al... more Course timetabiling is a process that must be done at the beginning of the education period in all educational institutions. The purpose of the timetabling is to bring together classrooms, lectures, students and lecturers at the same time without any conflicts. Course timetabiling is a difficult problem to solve when classroom constraints, teaching staff preferences, course restrictions are taken into consideration. With a deterministic approach, it can take a lot of time to try all the possibilities and reach a definite solution, and in cases where there are a lot of constraints, no definite solution can be found. In this study, the solving effect of the genetic algorithm parameters, which is an heuristic approach used in the course timetabiling problem, is investigated. Tests were performed for different iteration of different population size with different crossover and mutation rates. As a result of the experiments, it has been observed that the election operator who decides on ...
Random Forest (RF), rastgele oluşturulmuş birden çok karar ağacının çıktısını birleştiren, regres... more Random Forest (RF), rastgele oluşturulmuş birden çok karar ağacının çıktısını birleştiren, regresyon ve sınıflandırma problemlerini çözmek için kullanılan bir makine öğrenme algoritmasıdır. RF algoritması, karar ağaçlarının tahminlerinden yola çıkarak sonuca ulaşmayı sağlar. Ormandaki ağaç sayısının artması algoritma sonucunun kesinliğini arttırır. RF algoritması ormandaki karar ağaçları üzerinde rastgele ve sürekli olarak işlem gerçekleştirdiği için paralel mimaride platformlar üzerinde çalıştırılması ile olumlu sonuçlar elde edilebilir. Field Programmable Gate Array (FPGA) entegre devreler, paralel işlem yapabilme yeteneğine sahip olduğundan, RF algoritmasının donanım üzerinde gerçekleştirilen uygulamalarında kullanılması performansı arttırmaktadır. Gerçekleştirilen çalışmada RF algoritması sayısal bir veri seti ile hem MATLAB üzerinde hem de FPGA üzerinde çalıştırılarak sınıflandırma işlemleri gerçekleştirilmiştir. Algoritmadaki işlem modüllerinin ve tüm mantıksal tasarımların ge...
Trends in Data Engineering Methods for Intelligent Systems, 2021
Recently, deep learning techniques have achieved significant success in medical image analysis. I... more Recently, deep learning techniques have achieved significant success in medical image analysis. In this article, deep learning methods have been applied to separate brain magnetic resonance (MR) images into different abnormalities and healthy classes. The sectional brain MR of brain images is used as a database from the Open Access Imaging Studies Series (OASIS). Based on Convolutional Neural Network (CNN) method for classification and a thresholding algorithm for image segmentation, the system has been developed. The images that are improved by image processing are transferred to the CNN deep learning model and the classification process is done. Adam algorithm was used as the optimization algorithm for the classification process. As a result of the classification, 80% accuracy rate was obtained. The model’s loss rate fell to 0.3 s.
2017 International Conference on Computer Science and Engineering (UBMK), 2017
Course timetabiling is a process that must be done at the beginning of the education period in al... more Course timetabiling is a process that must be done at the beginning of the education period in all educational institutions. The purpose of the timetabling is to bring together classrooms, lectures, students and lecturers at the same time without any conflicts. Course timetabiling is a difficult problem to solve when classroom constraints, teaching staff preferences, course restrictions are taken into consideration. With a deterministic approach, it can take a lot of time to try all the possibilities and reach a definite solution, and in cases where there are a lot of constraints, no definite solution can be found. In this study, the solving effect of the genetic algorithm parameters, which is an heuristic approach used in the course timetabiling problem, is investigated. Tests were performed for different iteration of different population size with different crossover and mutation rates. As a result of the experiments, it has been observed that the election operator who decides on ...
Uploads
Papers by Recep Çolak