Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
10 results
Search Results
Conference Object Ensemble Churn Prediction for Internet Service Provider with Machine Learning Techniques(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2020) Goy, Gokhan; Kolukisa, Burak; Bahcevan, Cenk; Gungor, Vehbi CagriWith the developing technology in every fields, a competitive marketing environment has been arised In this competitive environment analyzing customer behavior has become vital In particular, the ability to easily change any service provider has become vet) , critical for the company to continue its existence At the same time, the amount of financial resources spent on retaining instituters much less than to obtain new clients. In this context, the traditional methods of examining vast amount of data obtained today for establishing decision support systems have lost their validities In this study. we used a dataset which is provided by TurkNet serving as an internet service provider in Turkey. Various preprocessing steps has performed on this dataset and then classification algorithms ran. Afterwards results have obtained and compared. The results of these experiments analyzed in terms of the area under the curve value In this context the aunt successful classifier algorithm has been determined as the Random Trees algorithm with a value of 0.936.Conference Object Citation - Scopus: 1The Identification of Discriminative Single Nucleotide Polymorphism Sets for the Classification of Behçet's Disease(Institute of Electrical and Electronics Engineers Inc., 2018-09) Görmez, Yasin; Işik, Yunus Emre; Bakir-Güngör, BurcuBehçet's disease is a long-term multisystem inflammatory disorder, characterized by recurrent attacks affecting several organs. As the genotyping individuals get cheaper and easier following the developments in genomic technologies, genome-wide association studies (GWAS) emerged. By this means, via studying big-sized case-control groups for a specific disease, potential genetic variations, single nucleotide polymorphisms (SNPs) are identified. Although several genetic risk factors are identified for Behçet's disease with the help of these studies via scanning around a million of SNPs, these variations could only explain up to 20% of the disease's genetic risk. In this study, for Behçet's disease classification, via comparing all the SNPs genotyped in GWAS, with the SNPs selected via using genetic knowledge, gain ratio and information gain; both reduction in the feature size and improvement in the classification accuracy is aimed. Also, using different classification algorithms such as random forest, k-nearest neighbour and logistic regression, their effects on the classification accuracy are investigated. Our results showed that compared to other feature selection methods, with at least 81% success rate, the selection of the SNPs using the genetic information (of their GWAS p-values, indicating the significance of the SNP against the disease) provides 15% to 42% improvement in all classification algorithms. This improvement is statistically sound. While gain ratio and information gain feature selection techniques yield similar classification accuracies, the models using all SNPs could not exceed 50% accuracies and results in the worst performance. © 2019 Elsevier B.V., All rights reserved.Conference Object Multi-Method Text Summarization: Evaluating Extractive and BART-Based Approaches on CNN/Daily Mail(Institute of Electrical and Electronics Engineers Inc., 2025-06-27) Inal, Yasin; Bakal, Gokhan; Esit, MuhammedWith the exponential growth of digital content, efficient text summarization has become increasingly crucial for managing information overload. This paper presents a comprehensive approach to text summarization using both extractive and abstractive methods, implemented on the CNN/Daily Mail dataset. We leverage pre-trained BART (Bidirectional and AutoRegressive Transformers) models and fine-tuning techniques to generate high-quality summaries. Our approach demonstrates significant improvements, with our best model trained on 287 k samples achieving ROUGE-1 F1 scores of 0.4174, ROUGE-2 F1 scores of 0.1932, and ROUGE-L F1 scores of 0.2910. We provide detailed comparisons between extractive methods and various BART model configurations, analyzing the impact of training dataset size and model architecture on summarization quality. Additionally, we share our implementation through an opensource NLP toolkit to facilitate further research and practical applications in the field. © 2025 Elsevier B.V., All rights reserved.Conference Object Identify Commonly Affected Pathways in Psychiatric Diseases(Institute of Electrical and Electronics Engineers Inc., 2018-09) Bulut, Umit; Bakir-Güngör, BurcuGenome-wide association studies (GWAS) are an extraordinary source of information when it comes to revealing the common variations of human complex diseases. Until now, the large amount of data generated from these studies have not been shown its full potential enough to identify the molecular and functional framework to be able to understand how a molecular system works. Following a more specific perspective, this study focused on the identification of commonly affected pathways of psychiatric diseases. The pathway term as used in molecular biology, depicts a simplified model of a process within the cell or tissue. Lately, several GWAS datasets are publicly available for various disease types such as psychiatric, immune-related, neurodegenerative, cardiovascular and such. A study on each disease and pairwise comparison to understand the behavior of disease and system would be time consuming and exhaustive. Instead of handling the results of these studies one by one, grouping diseases by target points is a more efficient way. This work aims to get one step closer to reveal key points of diseases and target these points to develop personalized medicine approaches. Especially for complex diseases, every drug doesn't show the same effect in every people. This paper contains the definition of molecular pathways, methods to identify disease related pathways, and to find common pathways pairwise in psychiatric diseases. © 2019 Elsevier B.V., All rights reserved.Conference Object Generating Linguistic Advice for the Carbon Limit Adjustment Mechanism(Springer Science and Business Media Deutschland GmbH, 2023-10-02) Fidan, Fatma Şener; Aydogan, Sena; Akay, DiyarLinguistic summarization, a subfield of data mining, generates summaries in natural language for comprehending big data. This approach simplifies the incorporation of information into decision-making processes since no specialized knowledge is needed to understand the generated language summaries. The present research employs linguistic summarization to examine the circumstances surrounding the Carbon Border Adjustment Mechanism, one of the most significant regulations confronting exporting nations to the European Union, and will be adopted to support sustainable growth. In this paper, associated with several attributes of the countries and product flow from exporting countries to European countries were defined as nodes and relations, respectively. Before the modeling phase, fuzzy c-means automatically identified fuzzy sets and membership degrees of attributes. During the modeling phase, summary forms were generated using polyadic quantifiers. A total of 1944 linguistic summaries were produced between exporting countries and European countries. Thirty-five summaries have a truth degree greater than or equal to the threshold value of 0.9, which is considered reasonable. The provision of natural language descriptions of the Carbon Border Adjustment Mechanism is intended to aid decision-makers and policymakers in their deliberations. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 23Citation - Scopus: 52Evaluation of Classification Algorithms, Linear Discriminant Analysis and a New Hybrid Feature Selection Methodology for the Diagnosis of Coronary Artery Disease(Institute of Electrical and Electronics Engineers Inc., 2018-12) Kolukisa, Burak; Hacilar, Hilal; Göy, Gökhan; Kus, Mustafa; Bakir-Güngör, Burcu; Aral, Atilla; Güngör, Vehbi ÇağrıAccording to the World Health Organization (WHO), 31% of the world's total deaths in 2016 (17.9 million) was due to cardiovascular diseases (CVD). With the development of information technologies, it has become possible to predict whether people have heart diseases or not by checking certain physical and biochemical values at a lower cost. In this study, we have evalated a set of different classification algorithms, linear discriminant analysis and proposed a new hybrid feature selection methodology for the diagnosis of coronary heart diseases (CHD). Throughout this research effort, using three publicly available Heart Disease diagnosis datasets (UCI Machine Learning Repository), we have conducted comparative performance evaluations in terms of accuracy, sensitivity, specificity, F-measure, AUC and running time. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 3Citation - Scopus: 13NSEM: Duygu Analizi için Özgün Yıǧınlanmiş Topluluk Yöntemi(Institute of Electrical and Electronics Engineers Inc., 2018-09) Işik, Yunus Emre; Görmez, Yasin; Kaynar, Oǧuz; Aydin, Zafer; Emre Isik, YunusToday, people often share their ideas, opinions and feelings through forums, social media sites, blogs and similar platforms. For this reason, access to these data has become very easy. Increase in the number of shares makes it possible to analyze and use these data in terms of marketing and politics. However, due to the large number of data, it is impossible that this analysis will be done by humans. Determination of what type of emotion is included automatically is done by sentiment analysis methods. In these methods, the text is defined as a mathematical vector and classified by machine learning methods. Ensemble methods are one of the most important methods used as classifiers in sentiment analysis. In these methods, a classifier error is tried to be solved by another classifier. In sentiment analysis, the feature vector that describes the text is as important as the classifier. Feature vectors obtained using different methods can make mistakes in different places. For this reason, in this study, NSEM is proposed for sentiment analysis, which is a new ensemble method that uses 2 different classifiers and 2 different feature extraction methods. As a result of the analysis, the proposed method is the most successful method with an accuracy rate of 79.1%. © 2019 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 2Makine Öǧrenmesi Teknikleri Ile İnternet Servis Saǧlayıcısı için Müşteri Kayıp Tahmini(Institute of Electrical and Electronics Engineers Inc., 2020-09) Göy, Gökhan; Kolukisa, Burak; Bahçevan, Cenk Anıl; Güngör, Vehbi ÇağrıWith the developing technology in every fields, a competitive marketing environment has been arised. In this competitive environment, analyzing customer behavior has become vital. In particular, the ability to easily change any service provider has become very critical for the company to continue its existence. At the same time, the amount of financial resources spent on retaining customers much less than to obtain new clients. In this context, the traditional methods of examining vast amount of data obtained today for establishing decision support systems have lost their validities. In this study, we used a dataset which is provided by TurkNet serving as an internet service provider in Turkey. Various preprocessing steps has performed on this dataset and then classification algorithms ran. Afterwards results have obtained and compared. The results of these experiments analyzed in terms of the area under the curve value. In this context, the most successful classifier algorithm has been determined as the Random Trees algorithm with a value of 0.936. © 2020 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 2Citation - Scopus: 6Makine Öğrenmesi Yöntemleri ile Kredi Kartı Sahteciliğinin Tespiti(Institute of Electrical and Electronics Engineers Inc., 2019-09) Göy, Gökhan; Gezer, Cengiz; Güngör, Vehbi ÇağrıWith the increase in credit card usage of people, the credit card transactions increase dramatically. It is difficult to identify fraudulent transactions among the vast amount of credit card transactions. Although credit card fraud is limited in number of transactions, it causes serious problems in terms of financial losses for individuals and organizations. Even though large number of studies has been conducted to solve this problem, there is no generally accepted solution. In this paper, a publicly available data set is used. The unbalance problem of the data set was solved by using hybrid sampling methods together. On this data set, comparative performance evaluations have been conducted. Different from other studies, the Area Under the Curve (AUC) metric, which expresses the success in such data sets, has also been used in addition to standard performance metrics. Since it is also important to quickly detect credit card fraud transactions; the running time of different methods is also presented as another performance metric. © 2020 Elsevier B.V., All rights reserved.Conference Object Evaluation of Hybrid Classification Approaches: Case Studies on Credit Datasets(Springer Verlag service@springer.de, 2018) Cetiner, Erkan; Güngör, Vehbi Çağrı; Kocak, TaskinHybrid classification approaches on credit domain are widely used to obtain valuable information about customer behaviours. Single classification algorithms such as neural networks, support vector machines and regression analysis have been used since years on related area. In this paper, we propose hybrid classification approaches, which try to combine several classifiers and ensemble learners to boost accuracy on classification results. We worked with two credit datasets, German dataset which is a public dataset and a Turkish Corporate Bank dataset. The goal of using such diverse datasets is to search for generalization ability of proposed model. Results show that feature selection plays a vital role on classification accuracy, hybrid approaches which shaped with ensemble learners outperform single classification techniques and hybrid approaches which consists SVM has better accuracy performance than other hybrid approaches. © 2018 Elsevier B.V., All rights reserved.