Yazar "Atagün, Ercan" seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analysing Content Ratings of Google Apps with Ensemble Learning(TUBITAK, 2022) Atagün, Ercan; Timuçin, Tunahan; Biroğul, S.Google Play was launched under the name of Android Market and made its reputation known all over the world. The mobile application market, which is a package manager developed by Google for Android users, contains applications that appeal to many areas and age ranges. Applications are spread over a wide range of uses. Thus, the amount and size of the data increased, and this situation began to attract the attention of researchers. The excessive increase in the number of applications makes it difficult for parents to follow up on the content. To provide the content rating of applications on Google Play, it is needed to be classified by machine learning methods. In this study, content rating classification was made by analyzing “Category, Rating, Reviews, Size, Installs, Type, Genres, Last Updated, Current Version, Android Version” features of 10757 applications on Google Play, Ensemble Learning methods (Adaboost, Bagging, Random Forest, Stacking), Logistic Regression, Artificial Neural Network, K-Nearest Neighbors algorithms. © 2022, TUBITAK. All rights reserved.Öğe Analysis of Honey Production with Environmenta Variables(Institute of Electrical and Electronics Engineers Inc., 2021) Atagün, Ercan; Albayrak, AhmetRegression algorithms are included in the supervised learning techniques of machine learning. Regression covers the operations of estimating the variable with the class label (output variable) by using the numerical values in a data with regression algorithms. When the desired performances cannot be achieved with the existing regression algorithms for a problem, Ensemble Learning models are applied. In the Ensemble Learning model, multiple predictive algorithms come together and aim to achieve a higher success than the success of an algorithm alone. In this study, honey production problem was estimated with Support vector machines. Multi-layer Perceptron Regressor, KNeighborsRegressor, Voting Regressor, RandomForestRegressor, AdaBoostRegressor, BaggingRegressor, GradientBoostingRegressor and the results were compared. It was observed that the ensemble learning models increased the prediction success with the regression processes. © 2021 IEEEÖğe Conference Scheduling with Epigenetic Algorithm(Gazi Univ, 2022) Atagün, Ercan; Biroğul, SerdarThe most important of the activities where the presentations of scientific studies take place are academic conferences. The days, halls, and sessions are determined in advance to organize multidisciplinary conferences and this process is called conference scheduling. In multidisciplinary conferences, in the scheduling of presentations, the coexistence of studies belonging to the same fields in the same sessions is very important for the conference listener and the conference speaker. In this context, the multidisciplinary conference scheduling problem is considered a multi-constraint optimization problem. Multi-constraint optimization problems are solved with heuristic optimization techniques, not traditional optimization methods. In this study, the problem of conference scheduling is addressed using multidisciplinary conference data. The solution to the conference scheduling problem was realized with Genetic Algorithm (GA) and Epigenetic Algorithm (EGA) using C# programming language. In the study, experimental results obtained with GA and EGA were examined. As a result of this examination, it was seen that EGA achieved better results in fewer iterations compared to classical GA.Öğe Genetik algoritma tabanlı konferans oturum çizelgeleme programının geliştirilmesi(Düzce Üniversitesi, 2020) Atagün, Ercan; Biroğul, SerdarAkademik konferanslar bilimsel gelişmelerin sunulduğu, tartışıldığı bir bilimsel faaliyettir. Akademik konferanslar birden çok bilim alanı çalışmasına imkan sağladığından dolayı multidisipliner niteliktedir. Multidisipliner konferanslar, doğa bilimi, sosyal bilimler, sağlık ve sanat bilimleri gibi farklı disiplinlerde çalışmaların sunumuna izin vermektedir. Multidisipliner konferansları organize etmek için günler, salonlar ve oturumlar belirlemek ve tüm oturumları ilgili ana disiplin alanına göre sunumları belirlemek gerekmektedir. Bir oturumdaki tüm bildirilerin aynı alandaki çalışmalardan oluşması günümüz konferans dinleyicisinin en önemli beklentilerinden birisidir. Dinleyici bu gereksinimi sayesinde ilgi alanı olan bildiriyi dinlemek için katılıdığı bir salonda ilgisinin olmadığı çalışmaları dinlemek durumunda kalmayacaktır. Konferans sırasında aynı oturumda farklı disiplinlerden sunumların olması konferans katılımcıları için büyük bir sorundur. Bu tez ile multidisipliner konferansların çizelgeleme probleminin Genetik Algoritma ve Epigenetik Algoritma yaklaşımı ile çözümü gerçekleştirilmiştir. Genetik Algoritmanın ve Epigenetik Algoritmanın temel kavramları verilmiş ve konferans çizelgeleme şemaları ve çizelgelemede dikkate alınacak unsurlar belirtilmiştir. Bu tez için iki farklı multidisipliner konferans veri seti kullanılmıştır. Genetik Algoritma ve Epigenetik Algoritma ile C# dilinde farklı günler, farklı oturumlar ve farklı odaların bazı kısıtlamaları altında bir uygulama geliştirilmiştir. Çalışma sonucunda Genetik Algoritma ve Epigenetik Algoritma ile elde edilen çizelgelemelerin sonuçları ve grafikleri verilmiştir. Epigenetik Algoritmanın Genetik Algoritmaya kıyasla daha başarılı sonuçlar verdiği gözlenmiştir.Öğe Topic Modeling Using LDA and BERT Techniques: Teknofest Example(Institute of Electrical and Electronics Engineers Inc., 2021) Atagün, Ercan; Hartoka, B.; Albayrak, AhmetThis paper is a natural language processing study and includes models used in natural language processing. In this paper, topic modeling, which is one of the sub-fields of natural language processing, has been studied. In order to make topic modeling, the data set was obtained by using the data scraping method, which has been very popular in recent years, over social media. The dataset is related to Teknofest competitions. The dataset was created by utilizing the Selenium library, one of the popular libraries used for the data scraping method. In order to be able to analyze on the prepared data set and to ensure the consistency of the clustering process, the text to be used before the analysis was preprocessed. After text preprocessing, clustering was performed on the data set with natural language processing techniques such as BERT and LDA . © 2021 IEEE
