Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
11 results
Search Results
Article Citation - Scopus: 1eTNT: Enhanced Textnettopics With Filtered LDA Topics and Sequential Forward / Backward Topic Scoring Approaches(Science and Information Organization, 2024) Voskergian, Daniel; Jayousi, Rashid; Bakir-Güngör, BurcuTextNetTopics is a novel text classification-based topic modelling approach that focuses on topic selection rather than individual word selection to train a machine learning algorithm. However, one key limitation of TextNetTopics is its scoring component, which evaluates each topic in isolation and ranks them accordingly, ignoring the potential relationships between topics. In addition, the chosen topics may contain redundant or irrelevant features, potentially increasing the feature set size and introducing noise that can degrade the overall model performance. To address these limitations and improve the classification performance, this study introduces an enhancement to TextNetTopics. eTNT integrates two novel scoring approaches: Sequential Forward Topic Scoring (SFTS) and Sequential Backward Topic Scoring (SBTS), which consider topic interactions by assessing sets of topics simultaneously. Moreover, it incorporates a filtering component that aims to enhance topics' quality and discriminative power by removing non-informative features from each topic using Random Forest feature importance values. These integrations aim to streamline the topic selection process and enhance classifier efficiency for text classification. The results obtained from the WOS-5736, LitCovid, and MultiLabel datasets provide valuable insights into the superior effectiveness of eTNT compared to its counterpart, TextNetTopics. © 2024 Elsevier B.V., All rights reserved.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 Citation - Scopus: 1TextNetTopics_TIS: Enhancing Textnettopics With Random Forest-Based Topic Importance Scoring(Institute of Electrical and Electronics Engineers Inc., 2024-10-16) Voskergian, Daniel; Bakir-Güngör, Burcu; Yousef, MalikTextNetTopics is an innovative Latent Dirichlet Allocation-based topic selection method for training text classification models. One main limitation is its computationally intensive scoring mechanism, especially when applied to many topics. This scoring mechanism involves training a machine learning model (i.e., Random Forest) on each topic using the Monte-Carlo Cross-Validation approach and assigning a score value based on a specific performance metric (e.g., accuracy or F1-score). Moreover, the measured score does not account for the interactions between all features residing in all topics. This paper presents a new topic-scoring mechanism called Topic Importance Scoring. This computationally efficient approach trains a Random Forest model on all topics simultaneously and leverages the extracted feature importance values to give each topic a score reflecting its classification potential. The experiments on three diverse datasets confirm that the proposed method's performance is superior to the Topic Performance Scoring, which was used in the original TextNetTopics method. © 2024 Elsevier B.V., All rights reserved.Conference Object Linear Vs. Non-Linear Embedding Methods in Recommendation Systems(Institute of Electrical and Electronics Engineers Inc., 2022-09-07) Gurler, Kerem; Cos¸kun, Mustafa; Karagenc, Safak; Orun, Gokhan; Kuleli Pak, Burcu Kuleli; Güngör, Vehbi Çağrı; Coskun, Mustafa; Pak, Burcu KuleliPredicting customer interest in items is very crucial in direct marketing as it can potentially boost sales. Data mining techniques are developed to predict which items a particular user might be interested in based on their purchase history or explicit feedback in form of ratings or comments. Recently, non-linear and linear methods have been developed for this purpose. In this study, we applied Neighborhood based Collaborative Filtering (CF), Matrix Factorization (MF), Singular Value Decomposition (SVD), Neural Graph CF (NGCF) and Light Graph Convolutional Network (LightGCN) on explicit user product rating data which is acquired from the online gaming and mobile entertainment platform called HADI. We compared the results of node embedding methods in terms of Precision@k, Recall@k and NDCG@k values. SVD and LightGCN showed the best test performance and SVD was significantly superior to LightGCN in terms of training speed. To further increase predictive performance of SVD, we have applied classification with Logistic Regression and Deep Random Forest on user and item embeddings created by the SVD. © 2022 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 5Identifying Taxonomic Biomarkers of Colorectal Cancer in Human Intestinal Microbiota Using Multiple Feature Selection Methods(Institute of Electrical and Electronics Engineers Inc., 2022-09-07) Jabeer, Amhar; Kocak, Aysegul; Akkaş, Huseyin; Yenisert, Ferhan; Nalbantoĝlu, Özkan Ufuk; Yousef, Malik; Bakir-Güngör, Burcu; Bakir Gungor, BurcuA variety of bacterial species called gut microbiota work together to maintain a steady intestinal environment. The gastrointestinal tract contains tremendous amount of different species including archaea, bacteria, fungi, and viruses. While these organisms are crucial immune system stabilizers, the dysbiosis of the intestinal flora has been related to gastrointestinal disorders including Colorectal cancer (CRC), intestinal cancer, irritable bowel syndrome and inflammatory bowel disease. In the last decade, next-generation sequencing (NGS) methods have accelerated the identification of human gut flora. CRC is a deathly condition that has been on the rise in the last century, affecting half a million people each year. Since early CRC diagnosis is critical for an effective treatment, there is an immediate requirement for a classification system that can expedite CRC diagnosis. In this study, via analyzing the available metagenomics data on CRC, we aim to facilitate the CRC diagnosis via finding biomarkers linked with CRC, and via building a classification model. We have obtained the metagenomic sequencing data of the healthy individuals and CRC patients from a metagenome-wide association analysis and we have classified this data according to the disease stages. Conditional Mutual Information Maximization (CMIM), Fast Correlation Based Filter (FCBF), Extreme Gradient Boosting (XGBoost), min redundancy max relevance (mRMR), Information Gain (IG) and Select K Best (SKB) feature selection algorithms were utilized to cope with the complexity of the features. We observed that the SKB, IG, and XGBoost techniques made significant contributions to decrease the microbiota in use for CRC diagnosis, thereby reducing cost and time. We realized that our Random Forest classifier outperformed Adaboost, Support Vector Machine, Decision Tree, Logitboost and stacking ensemble classifiers in terms of CRC classification performance. Our results reiterated some known and some potential microbiome associated mechanisms in CRC, which could aid the design of new diagnostics based on the microbiome. © 2022 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 2Data-Driven Methods for Optimal Setting of Legacy Control Devices in Distribution Grids(IEEE Computer Society, 2024-07-21) Savasci, Alper; Ceylan, Oǧuzhan; Paudyal, SumitThis study presents machine learning-based dispatch strategies for legacy voltage regulation devices, i.e., onload tap changers (OLTCs), step-voltage regulators (SVRs), and switched-capacitors (SCs) in modern distribution networks. The proposed approach utilizes k-nearest neighbor (KNN), random forest (RF), and neural networks (NN) to map nodal net active and reactive injections to the optimal legacy controls and resulting voltage magnitudes. To implement these strategies, first, an efficient optimal power flow (OPF) is formulated as a mixed-integer linear program that obtains optimal decisions of tap positions for OLTCs, SVRs, and on/off status of SCs. Then, training and testing datasets are generated by solving the OPF model for daily horizons with 1-hr resolution for varying loading and photovoltaic (PV) generation profile. Case studies on the 33-node feeder demonstrate high-accuracy mapping between the input feature and the output vector, which is promising for integrated Volt/VAr control schemes. © 2024 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 21Assessing Employee Attrition Using Classifications Algorithms(Association for Computing Machinery, 2020-05-15) Ozdemir, Fatma; Cos¸kun, Mustafa; Gezer, Cengiz; Güngör, Vehbi Çağrı; Coskun, Mustafa; Cagri Gungor, V.Employees leave an organization when other organizations offer better opportunities than their current organizations. Continuity and sustenance and even completion of jobs are crucial issues for the companies not to suffer financial losses. Especially if the talented employees, who are at critical positions in the companies, leave the job, it becomes difficult for the organizations to maintain their businesses. Today, organizations would like to predict attrition of their employees and plan and prepare for it. However, the HR departments of organizations are not advanced enough to make such predictions in a handcrafted manner. For this reason, organizations are looking for new systems or methods that automatize the prediction of employee attrition utilizing data mining methods. In this study, we use IBM HR data set and apply different classification methods, such as Support Vector Machine (SVM), Random Forest, J48, LogitBoost, Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Naive Bayes, Bagging, AdaBoost, Logistic Regression, to predict the employee attrition. Different from exiting studies, we systematically evaluate our findings with various classification metrics, such as F-measure, Area Under Curve, accuracy, sensitivity, and specificity. We observe that data mining methods can be useful for predicting the employee attrition. © 2022 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 3A Hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) Approach for Professional Bloggers Classification(Institute of Electrical and Electronics Engineers Inc., 2019-11) Asim, Yousra; Raza, Basit; Malik, Ahmad Kamran Kamran; Shahid, Ahmad Raza; Faheem, Muhammed Yasir; Kumar, Y. J.Despite their small numbers, some users of the online social networks demonstrate the ability to influence others. Bloggers are one of such kind of users that through their ideas and opinions on different topics, influence other users. Their identification may be beneficial for several purposes, such as online marketing for products. Much effort has been expanded towards finding the impact of such bloggers within the blogging community. We have expanded on their work by identifying influential bloggers using labeled data. We have improved upon the accuracy of the classification of professional and nonprofessional bloggers. We have made use of Adaptive Neuro-Fuzzy Inference System (ANFIS), and the Fuzzy Inference System (FIS) models. Their performance has been gauged and compared with the existing techniques and approaches, such as an Artificial Neural Network (ANN), Alternating Decision Tree (ADTree) algorithm, and Classification Based on Associations (CBA) algorithm. Adaptive techniques (ANFIS and ANN) are found better than the aforementioned rule-based classifiers. The FIS model outperformed the CBA algorithm, but showed similar performance to the ADTree algorithm. Our proposed ANFIS model showed improved results in terms of performance measures with 93% accuracy for blogger classification. © 2020 Elsevier B.V., All rights reserved.Conference Object Population Specific Classification of Colorectal Cancer With Meta-Analysis of Metagenomic Data(Institute of Electrical and Electronics Engineers Inc., 2023-10-11) Temiz, Mustafa; Yousef, Malik; Bakir-Güngör, BurcuAdvances in next-generation sequencing and '-omics' technologies makes it possible to characterize the human gut microbiome. While some of these microorganisms are important regulators of our immune system, modulation of the microbiota leads to a variety of diseases. Colorectal cancer (CRC), the third most common cancer worldwide, is caused by genetic mutations, environmental conditions, and abnormalities in the gut microbiota. Using various machine learning methods and meta-analysis techniques, this study aims to build a classification model that can help in CRC diagnosis by analyzing metagenomic datasets of different populations obtained at the species level. Using 8 different countries and 9 different metagenomic datasets, 3 different meta-analyzes are performed: within-population, cross-population, and one population is selected for testing and the rest is used as a training dataset (LODO). For CRC classification, 4 different classification algorithms (Random Forest (RF), Logitboost, Adaboost, and Decision Tree (DT)) are used. The best performance among these methods was obtained with the Random Forest algorithm with an AUC of 0.98 by using JP for the training data set and JPN populations for the test data set in the cross-population performance evaluation. © 2023 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 8Citation - Scopus: 9Meme Kanseri Histopatolojik Görüntülerinin Bilgisayar Destekli Sınıflandırılması(Institute of Electrical and Electronics Engineers Inc., 2017-10) Aksebzeci, Bekir Hakan; Kayaaltı, ÖmerNowadays, one of the most common types of cancer is breast cancer. The early and accurate diagnosis of breast cancer has great importance in the treatment of the disease. In the diagnosis of breast cancer, histopathological analysis of cell and tissue specimens taken by biopsy is considered as the gold standard. Histopathological analysis is a tedious process that is highly dependent on the knowledge and experience of the pathologists. In this study; it is aimed to develop a computer-Aided system that can reduce the workload of pathologists and help them in their diagnosis. An image set containing benign and malignant tumor images of breast cancer has been studied. To perform texture analysis on tumor images; first order statistics, Gabor and gray-level co-occurrence matrix (GLCM) feature extraction methods have been applied. Then, various classifiers were applied to the obtained feature matrices and their performances were compared. The highest classification accuracy was achieved 82.06% by Random Forests classifier with feature combination of Gabor and GLCM methods. The results presented here show that computer-Assisted diagnosis of breast cancer is a promising field. © 2018 Elsevier B.V., All rights reserved.