Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
17 results
Search Results
Conference Object Citation - Scopus: 1Traffic Light Management Systems Using Reinforcement Learning(Institute of Electrical and Electronics Engineers Inc., 2022-09-07) Can, Sultan Kubra; Thahir, Adam Rizvi; Cos¸kun, Mustafa; Güngör, Vehbi Çağrı; Coskun, MustafaWhile reducing traffic congestion and decrease the number of traffic accidents in the intersections, most of the traffic light management approaches cannot adapt well to fast changing traffic dynamics and growing demands of the intersections with modern world developments. To overcome this problem, adaptive traffic controllers are developed, and detectors and sensors are added to systems to enable adoption and dynamism. Recently, reinforcement learning has shown its capability to learn the dynamics of complex environments, such as urban traffic. Although it was studied in single junction systems, one of the problems was the lack of consistency with how the real world system works. Most of the systems assume that the environment is fully observable or actions would be freely executed using simulators. This study aims to merge usefulness of reinforcement learning methods with real-world traffic constraints. Comparative performance evaluations show that the reinforcement learning algorithm (Advantage Actor-Critic (A2C)) converges well while staying stable under changing traffic dynamics. © 2022 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: 2Re-Exploring the Kayseri Culture Route by Using Deep Learning for Cultural Heritage Image Classification Cultural Heritage Image Classification by Using Deep Learning: Kayseri Culture Route(Association for Computing Machinery, 2024-05-25) Kevseroğlu, Ozlem; Kurban, RifatThe categorization of images captured during the documentation of architectural structures is a crucial aspect of preserving cultural heritage in digital form. Dealing with a large volume of images makes this categorization process laborious and time-consuming, often leading to errors. Introducing automatic techniques to aid in sorting would streamline this process, enhancing the efficiency of digital documentation. Proper classification of these images facilitates improved organization and more effective searches using specific terms, thereby aiding in the analysis and interpretation of the heritage asset. This study primarily focuses on applying deep learning techniques, specifically SqueezeNet convolutional neural networks (CNNs), for classifying images of architectural heritage. The effectiveness of training these networks from scratch versus fine-tuning pre-existing models is examined. In this study, we concentrate on identifying significant elements within images of buildings with architectural heritage significance of Kayseri Culture Route. Since no suitable datasets for network training were found, a new dataset was created. Transfer learning enables the use of pre-trained convolutional neural networks to specific image classification tasks. In the experiments, 99.8% of classification accuracy have been achieved by using SqueezeNet, suggesting that the implementation of the technique can substantially enhance the digital documentation of architectural heritage. © 2024 Elsevier B.V., All rights reserved.Conference Object Citation - WoS: 16Citation - Scopus: 20Machine Learning Analysis of Inflammatory Bowel Disease-Associated Metagenomics Dataset(Institute of Electrical and Electronics Engineers Inc., 2018-09) Hacilar, Hilal; Nalbantoĝlu, Özkan Ufuk; Bakir-Güngör, BurcuThere is an ongoing interplay between humans and our microbial communities. The microorganisms living in our gut produce energy from our food, strengthen our immune system, break down foreign products, and release metabolites and hormones, which are significant for regulating our physiology. The shifts away from this 'healthy' gut microbiome is considered to be associated with many diseases. Inflammatory bowel diseases (IBD) including Crohn's disease and ulcerative colitis, are gut related disorders affecting the intestinal tract. Although some metagenomics studies are conducted on IBD recently, our current understanding of the precise relationships between the human gut microbiome and IBD remains limited. In this regard, the use of state-of-the art machine learning approaches became popular to address a variety of questions like early diagnosis of certain diseases using human microbiota. In this study, we investigate which subset of gut microbiota are mostly associated with IBD and if disease-associated biomarkers can be detected via applying state-of-the art machine learning algorithms and proper feature selection methods. © 2019 Elsevier B.V., All rights reserved.Book Part Hosting Capacity Calculation Methods(Elsevier, 2025) Oguzhan, Ceylan; Alper, SavasciIn this chapter, we focus on hosting capacity (HC) calculations, by giving the methods to determine the maximum amount of distributed energy resources (DER) that can be integrated into power distribution network(s) without compromising reliability or performance. We detail methodologies such as power flow-based approaches, probabilistic techniques, and machine learning algorithms, with sample applications of HC calculations. Initially, we focus on power flow-based methods based on simulating power distribution network(s) to assess system voltage, current flow, and stability impacts from DER installations. Then, we will give the probabilistic approaches that use uncertainties in renewable generation and consumer demand, based on statistical techniques and Monte Carlo simulations aiming to reflect these variability. Machine learning (ML) techniques will also be given based on analyzing large data sets, detecting patterns, and predicting system responses. These kinds of methods include regression analysis and neural networks trained on historical data for optimized HC predictions. It should be stated that HC is impacted by several factors, such as network topology, load profiles, and DER characteristics, and these as well will be discussed. We will provide a practical example of an HC calculation on a 141-node distribution network using a step-by-step algorithm in Matpower, with simulation results based on an iterative deterministic method. Then, we will give the broader implications of HC assessments for grid modernization and energy policy, highlighting how accurate calculations support a more decentralized, sustainable, and resilient energy future. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 7Generating Emergency Evacuation Route Directions Based on Crowd Simulations With Reinforcement Learning(Institute of Electrical and Electronics Engineers Inc., 2022-09-07) Unal, Ahmet Emin; Gezer, Cengiz; Kuleli Pak, Burcu Kuleli; Güngör, Vehbi Çağrı; Pak, Burcu KuleliIn an emergency, it is vital to evacuate individuals from the dangerous environments. Emergency evacuation plan-ning ensures that the evacuation is safe and optimal in terms of evacuation time for all of the people in evacuation. To this end, the computer-enabled evacuation simulation systems are used to generate optimal routes for the evacuees. In this paper, a dynamic emergency evacuation route generator has been proposed based on indoor plans of the building and the locations of the evacuees. To generate the optimal routes in real-time, a reinforcement learning algorithm (proximal policy optimization) is presented. Comparative performance results show that the proposed model is successful for evacuating the individuals from the building in different scenarios. © 2022 Elsevier B.V., All rights reserved.Article Citation - Scopus: 14CoviDetector: A Transfer Learning-Based Semi Supervised Approach to Detect COVID-19 Using CXR Images(Elsevier B.V., 2023-06) Chowdhury, Deepraj; Das, Anik; Dey, Ajoy; Banerjee, Soham; Golec, Muhammed; Kollias, Dimitrios; Arya, Rajesh Chand; Uhlig, SteveCOVID-19 was one of the deadliest and most infectious illnesses of this century. Research has been done to decrease pandemic deaths and slow down its spread. COVID-19 detection investigations have utilised Chest X-ray (CXR) images with deep learning techniques with its sensitivity in identifying pneumonic alterations. However, CXR images are not publicly available due to users’ privacy concerns, resulting in a challenge to train a highly accurate deep learning model from scratch. Therefore, we proposed CoviDetector, a new semi-supervised approach based on transfer learning and clustering, which displays improved performance and requires less training data. CXR images are given as input to this model, and individuals are categorised into three classes: (1) COVID-19 positive; (2) Viral pneumonia; and (3) Normal. The performance of CoviDetector has been evaluated on four different datasets, achieving over 99% accuracy on them. Additionally, we generate heatmaps utilising Grad-CAM and overlay them on the CXR images to present the highlighted areas that were deciding factors in detecting COVID-19. Finally, we developed an Android app to offer a user-friendly interface. We release the code, datasets and results’ scripts of CoviDetector for reproducibility purposes; they are available at: https://github.com/dasanik2001/CoviDetector © 2024 Elsevier B.V., All rights reserved.Article Citation - Scopus: 8Building a Challenging Medical Dataset for Comparative Evaluation of Classifier Capabilities(Elsevier Ltd, 2024-08) Bozkurt, Berat; Coskun, Kerem; Bakal, GokhanSince the 2000s, digitalization has been a crucial transformation in our lives. Nevertheless, digitalization brings a bulk of unstructured textual data to be processed, including articles, clinical records, web pages, and shared social media posts. As a critical analysis, the classification task classifies the given textual entities into correct categories. Categorizing documents from different domains is straightforward since the instances are unlikely to contain similar contexts. However, document classification in a single domain is more complicated due to sharing the same context. Thus, we aim to classify medical articles about four common cancer types (Leukemia, Non-Hodgkin Lymphoma, Bladder Cancer, and Thyroid Cancer) by constructing machine learning and deep learning models. We used 383,914 medical articles about four common cancer types collected by the PubMed API. To build classification models, we split the dataset into 70% as training, 20% as testing, and 10% as validation. We built widely used machine-learning (Logistic Regression, XGBoost, CatBoost, and Random Forest Classifiers) and modern deep-learning (convolutional neural networks - CNN, long short-term memory - LSTM, and gated recurrent unit - GRU) models. We computed the average classification performances (precision, recall, F-score) to evaluate the models over ten distinct dataset splits. The best-performing deep learning model(s) yielded a superior F1 score of 98%. However, traditional machine learning models also achieved reasonably high F1 scores, 95% for the worst-performing case. Ultimately, we constructed multiple models to classify articles, which compose a hard-to-classify dataset in the medical domain. © 2024 Elsevier B.V., All rights reserved.Conference Object Benchmarking CNN Architectures for Eye Disease Detection With Transfer Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2025-06-27) Keles, Tolgahan; Aykanat, Muhammet Ali; Kurban, RifatIn this study, convolutional neural networks (CNN)-based approaches were compared to classify eye diseases using transfer learning techniques. A series of data augmentation strategies, including random rotation, shifting, shearing, zooming, and horizontal flipping, were applied to increase the training data's robustness and diversity. Several state-of-the-art CNNs, including ResNet50, VGG19, EfficientNetB0, Xception, InceptionV3, DenseNet121, MobileNetV2, NASNetMobile, and ConvNeXtBase, were fine-tuned through transfer learning. During training, models were evaluated based on their accuracy, training time, and validation performance, while early stopping mechanisms were employed to prevent overfitting. Experimental results demonstrated that DenseNet121 achieved the highest validation accuracy (72%) during the training phase and the best test set performance with an accuracy of 68% and an AUC-ROC of 0.93. MobileNetV2, on the other hand, provided a strong balance between classification accuracy (65%) and low inference time (7.28 ms), making it appropriate for real-time uses. The findings highlight the importance of selecting appropriate architectures by considering both predictive performance and computational efficiency, particularly in the context of medical imaging, where real-world deployment constraints are critical. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 4A Transfer Learning Application on the Reliability of Psychological Drugs' Comments(Institute of Electrical and Electronics Engineers Inc., 2023-07-25) Sen, Tarik Uveys; Bakal, GokhanAs digitalization and the Internet stay emerging concepts by gaining popularity, the accuracy of personal reviews/opinions will be a critical issue. This circumstance also particularly applies to patients taking psychological drugs, where accurate information is crucial for other patients and medical professionals. In this study, we analyze drug reviews from drugs.com to determine the effectiveness of reviews for psychological drugs. Our dataset includes over 200,000 drug reviews, which we labeled as positive, negative, or neutral according to their rating scores. We apply machine learning (ML) models, including Logistic Regression, Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) algorithms, to predict the sentiment class of each review. Our results demonstrate an F1-Weighted score of 85.3% for the LSTM model. However, by applying the transfer learning technique, we further improved the F1 score (nearly 3% increase) obtained by the LSTM model. Our findings proved that there is no contextual difference between the comments made by the patients suffering from psychological or other diseases. © 2023 Elsevier B.V., All rights reserved.