Browsing by Author "Goy, Gokhan"

Now showing 1 - 7 of 7

Credit Card Fraud Detection with Machine Learning Methods
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 01.01.2019) Goy, Gokhan; Gezer, Cengiz; Gungor, Vehbi Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
With 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.
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 Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
With 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.
Evaluation of Classification Algorithms, Linear Discriminant Analysis and a New Hybrid Feature Selection Methodology for the Diagnosis of Coronary Artery Disease
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2018) Kolukisa, Burak; Hacilar, Hilal; Goy, Gokhan; Kus, Mustafa; Bakir-Gungor, Burcu; Aral, Atilla); Gungor, Vehbi Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
According 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.
miRcorrNet: machine learning-based integration of miRNA and mRNA expression profiles, combined with feature grouping and ranking
(PEERJ INC341-345 OLD ST, THIRD FLR, LONDON EC1V 9LL, ENGLAND, 2021) Yousef, Malik; Goy, Gokhan; Mitra, Ramkrishna; Eischen, Christine M.; Jabeer, Amhar; Bakir-Gungor, Burcu; 0000-0002-2272-6270; 0000-0001-7678-0355; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Goy, Gokhan; Jabeer, Amhar; Bakir-Gungor, Burcu
A better understanding of disease development and progression mechanisms at the molecular level is critical both for the diagnosis of a disease and for the development of therapeutic approaches. The advancements in high throughput technologies allowed to generate mRNA and microRNA (miRNA) expression profiles; and the integrative analysis of these profiles allowed to uncover the functional effects of RNA expression in complex diseases, such as cancer. Several researches attempt to integrate miRNA and mRNA expression profiles using statistical methods such as Pearson correlation, and then combine it with enrichment analysis. In this study, we developed a novel tool called miRcorrNet, which performs machine learning-based integration to analyze miRNA and mRNA gene expression profiles. miRcorrNet groups mRNAs based on their correlation to miRNA expression levels and hence it generates groups of target genes associated with each miRNA. Then, these groups are subject to a rank function for classification. We have evaluated our tool using miRNA and mRNA expression profiling data downloaded from The Cancer Genome Atlas (TCGA), and performed comparative evaluation with existing tools. In our experiments we show that miRcorrNet performs as good as other tools in terms of accuracy (reaching more than 95% AUC value). Additionally, miRcorrNet includes ranking steps to separate two classes, namely case and control, which is not available in other tools. We have also evaluated the performance of miRcorrNet using a completely independent dataset. Moreover, we conducted a comprehensive literature search to explore the biological functions of the identified miRNAs. We have validated our significantly identified miRNA groups against known databases, which yielded about 90% accuracy. Our results suggest that miRcorrNet is able to accurately prioritize pan-cancer regulating high-confidence miRNAs. miRcorrNet tool and all other supplementary files are available at https://github.com/ malikyousef/miRcorrNet.
miRModuleNet: Detecting miRNA-mRNA Regulatory Modules
(RONTIERS MEDIA SAAVENUE DU TRIBUNAL FEDERAL 34, LAUSANNE CH-1015, SWITZERLAND, 2022) Yousef, Malik; Goy, Gokhan; Bakır Güngör, Burcu; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Bakır Güngör, Burcu; Göy, Gökhan
Increasing evidence that microRNAs (miRNAs) play a key role in carcinogenesis has revealed the need for elucidating the mechanisms of miRNA regulation and the roles of miRNAs in gene-regulatory networks. A better understanding of the interactions between miRNAs and their mRNA targets will provide a better understanding of the complex biological processes that occur during carcinogenesis. Increased efforts to reveal these interactions have led to the development of a variety of tools to detect and understand these interactions. We have recently described a machine learning approach miRcorrNet, based on grouping and scoring (ranking) groups of genes, where each group is associated with a miRNA and the group members are genes with expression patterns that are correlated with this specific miRNA. The miRcorrNet tool requires two types of -omics data, miRNA and mRNA expression profiles, as an input file. In this study we describe miRModuleNet, which groups mRNA (genes) that are correlated with each miRNA to form a star shape, which we identify as a miRNA-mRNA regulatory module. A scoring procedure is then applied to each module to further assess their contribution in terms of classification. An important output of miRModuleNet is that it provides a hierarchical list of significant miRNA-mRNA regulatory modules. miRModuleNet was further validated on external datasets for their disease associations, and functional enrichment analysis was also performed. The application of miRModuleNet aids the identification of functional relationships between significant biomarkers and reveals essential pathways involved in cancer pathogenesis.
A New Method to Identify Affected Pathway Subnetworks and Clusters in Colon Cancer
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 11.09.2019) Goy, Gokhan; Yazici, Miray Unlu; Bakir-Gungor, Buren; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
Nowadays new technological developments that play an important role in the production of big data have brought about the interpretation, sharing and storage of data related to complex diseases. Combining multi-omic data in different molecular levels is potentially important for understanding the biological origin of complex diseases. One of these complex diseases is cancer of different types, which has one of the highest causes of death worldwide. The integration of multiple omic data in the framework of a comprehensive analysis and identification of relevant pathways contribute to the development of therapeutic approaches related to disease. In this study, RNA and methylation data (genes and p values) of colon adenocarcinoma were obtained from TCGA data portal and combined with Fisher's method. While protein subnetworks affected by the disease were identified by using subnetwork algorithm, pathways related to the disease and genes associated with these pathways were determined by functional enrichment analysis. Using gene-pathway relationship matrix, kappa scores of pathways were determined by similarity calculation. In this way, the pathways were clustered according to the hierarchically optimal number, as a result, the most important pathway clusters and related genes that are effective in disease formation identified.
Recursive Cluster Elimination based Rank Function (SVM-RCE-R) implemented in KNIME
(F1000 Research, 2020) Yousef, Malik; Bakir Gungor, Burcu; Jabeer, Amhar; Goy, Gokhan; Qureshi, Rehman; C Showe, Louise; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Bakir Gungor, Burcu; Jabeer, Amhar; Goy, Gokhan
In our earlier study, we proposed a novel feature selection approach, Recursive Cluster Elimination with Support Vector Machines (SVM-RCE) and implemented this approach in Matlab. Interest in this approach has grown over time and several researchers have incorporated SVM-RCE into their studies, resulting in a substantial number of scientific publications. This increased interest encouraged us to reconsider how feature selection, particularly in biological datasets, can benefit from considering the relationships of those genes in the selection process, this led to our development of SVM-RCE-R. SVM-RCE-R, further enhances the capabilities of SVM-RCE by the addition of a novel user specified ranking function. This ranking function enables the user to stipulate the weights of the accuracy, sensitivity, specificity, f-measure, area under the curve and the precision in the ranking function This flexibility allows the user to select for greater sensitivity or greater specificity as needed for a specific project. The usefulness of SVM-RCE-R is further supported by development of the maTE tool which uses a similar approach to identify microRNA (miRNA) targets. We have also now implemented the SVM-RCE-R algorithm in Knime in order to make it easier to applyThe use of SVM-RCE-R in Knime is simple and intuitive and allows researchers to immediately begin their analysis without having to consult an information technology specialist. The input for the Knime implemented tool is an EXCEL file (or text or CSV) with a simple structure and the output is also an EXCEL file. The Knime version also incorporates new features not available in SVM-RCE. The results show that the inclusion of the ranking function has a significant impact on the performance of SVM-RCE-R. Some of the clusters that achieve high scores for a specified ranking can also have high scores in other metrics.