Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/5799
Browse
31 results
Search Results
Master Thesis İnsan Bağırsak Mikrobiyotasından Hastalık Biyobelirteçlerinin Tespiti için Makine Öğrenmesi Temelli Sistem Geliştirilmesi(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Koçak, Ayşegül; Güngör, Burcu; Yousef, MalikThe human gut microbiota consists of a diverse ecosystem of organisms, encompasses billions of species. Recently developed next-generation sequencing methods have enabled researchers to examine the microbiota in greater detail, leading to new insights into its functions and dysfunctions. This study aims to identify metagenomic biomarkers (Microorganism-Enzyme Pairs) for colorectal cancer (CRC). The tool that we used allows for the analysis of microorganisms and enzymes within the gut microbiota. It achieves this by initially clustering enzymes based on their correlations with species and subsequently utilizing these clustering results to evaluate the ability of groups to differentiate between patient and healthy cohorts. By integrating species and enzymes, it is possible to identify pathogen microorganisms and enzyme clusters, that have the potential to distinguish cases (individuals with CRC) from controls (healthy individuals). The identified enzyme clusters and associated species could potentially act as biomarkers for colorectal cancer (CRC), enabling early diagnosis and more effective treatment. This approach holds promise for further exploration of the gut microbiota and its importance in human health and illness. Keywords: Bioinformatics, Machine Learning, Colorectal Cancer DiagnosisMaster Thesis Tree-net: Biyomedikal Görüntü Segmentasyonu için Tree-net: Darboğaz Özellik Süpervizyonu Kullanılan Yapay Sinir Ağı Modeli(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Demirci, Orhan; Yılmaz, BülentIn this thesis, we introduce Tree-NET, a novel approach for medical image segmentation utilizing bottleneck feature supervision. This method enhances traditional segmentation algorithms by keeping supervision between bottleneck features of the network. The primary goal is to improve the model's ability to learn discriminative and robust features while simultaneously reducing computational costs. Bottleneck feature supervision involves compressing the input and label data using Autoencoders and then supervising the bottleneck features with a segmentation network named 'Bridge-Net,' which can be any segmentation model of choice. We applied Tree-NET to two critical medical image segmentation tasks: skin lesion segmentation and polyp segmentation. Our experiments demonstrate significant improvements in segmentation accuracy and efficiency. For instance, the U-NET backboned Tree-NET uses only 154.43 MB for executing and storing the model, which is almost 3.5 times smaller than the original U-Net while having a close number of trainable parameters. In skin lesion segmentation, Tree-NET achieved dice, Intersection-over-Union (IoU), and accuracy scores of 0.893, 0.751, and 0.977 respectively. For polyp segmentation, the scores were 0.856, 0.795, and 0.923 for dice, IoU, and accuracy respectively. Compared to traditional segmentation models, the empirical results show that Tree-NET achieves higher accuracy with reduced training time and computational cost, thus representing a significant advancement in medical image analysis by providing more reliable and efficient tools for clinical applications.Master Thesis Meme Kanseri Histopatoloji Görüntülerinde Evrişimsel Sinir Ağları Kullanarak Tümör Tespiti(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Şahbaz, Zeki; Aksebzeci, Bekir HakanBreast cancer is one of the most common cancer types among women worldwide. Early detection significantly increases the chances of survival and effective treatment, making advancements in diagnostic methodologies crucial. This study aims to improve the detection of tumor cells in breast cancer histopathology images using deep learning and image processing techniques. Significant modifications have been made to the hyperparameters, including the tumor bounding box size, batch size, optimization algorithms, learning rate, and weight decay. These changes focus on determining the best parameters of the Faster R-CNN model. A comprehensive analysis of different parameters was conducted using the Breast Cancer Histopathological Annotation and Diagnosis (BreCaHAD) dataset. The analysis identified the best settings for model performance, shows by improvements in precision, recall, and F-score. Our research contributes to the field of medical image analysis by identifying critical factors that affect the accuracy of tumor detection, contributing to the development of more accurate diagnostic tools.Master Thesis Makine Öğrenimi Algoritmalarını Kullanarak Ağ Trafiğini Analiz Etme ve Ağ Tehditlerini Tespit Etme(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Küçükkoç, Abdurrahman; Aydın, ZaferAs information technologies progress, the possibilities of access to information increase and therefore it becomes difficult to ensure the security of information. Today, with the use of information systems in all areas of life, network threats have also increased. The increase in individual access to and use of the internet has also brought network threats. In addition, the latest developments in information technologies, developing global communication networks, the internet of things aiming to connect all objects with networks, cloud technologies, the spread of mobile internet and the renewal of devices have brought network threats and uncertainties. Network threats increase the security vulnerabilities in the information and communication systems of individuals and organisations day by day. This situation causes systems to malfunction, economic damage and cyber security to be jeopardised. In order to contribute to individuals, institutions and organisations, our thesis aims to protect information systems against network threats, to ensure data confidentiality, integrity and accessibility, to detect network threats in advance and to take measures against these threats. We believe that by analysing heterogeneous network traffic, which includes most network attacks on the Internet, and using machine learning algorithms, we will reach a result close to reality in the detection of network threats. In line with this result, we will be able to take precautions against network threats in information systems and structuresMaster Thesis Koroner Arter Hastalığının Makine Öğrenimi Yaklaşımları ile Teşhisi(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Halıcı, İkram; Güngör, Vehbi ÇağrıThe World Health Organization states that Coronary Artery Disease (CAD) ranks as a primary cause of recorded fatalities. CAD occurs as a result of the blockage of coronary artery vessels, which are located on the surface of the heart and supply the blood that the heart needs. Diagnosing the disease using traditional methods is challenging and requires costly tests. In recent years, the use of machine learning-based methods has increased as an alternative diagnostic approach. However, existing studies in the literature suffer from low detection rates and long training times. Therefore, there is still a need for reliable and low-cost diagnostic methods. In this thesis, a new model, CSA-PSO-ANN, is proposed for the diagnosis of coronary artery disease. The aim is to reduce the training time of the machine learning model and achieve a higher accuracy in diagnosing the disease. Experiments have been conducted on two publicly available datasets. Parallelization, feature selection, and hyperparameter optimization have been performed to shorten the model's training time. The performance of the model has been compared with well-known machine-learning algorithms and previous studies. The experiments showed that the proposed model effectively diagnoses the disease and outperforms other methods in terms of accuracy and F1 score performance metrics.Master Thesis Derin Öğrenme Yöntemleri Kullanarak Dermatoskopik Görüntülerden Otomatik Cilt Kanseri Tespiti ve Sınıflandırılması(Abdullah Gül Üniversitesi / Fen Bilimleri Enstitüsü, 2023) Kalaycı, Serdar; Yılmaz, BülentEarly detection of skin cancer is crucial for successful treatment and improved patient outcomes. The most prevalent form of cancer is skin cancer and if left undetected, it can spread and become more difficult to treat. A dangerous and frequently fatal type of skin cancer is melanoma. Regular skin examinations and self-examinations can help identify suspicious moles or lesions, which can then be evaluated by a dermatologist. In addition, advances in technology and artificial intelligence have enabled the development of tools for automated skin cancer screening, providing a convenient and efficient means of early detection. This can lead to more efficient diagnosis, reduced healthcare costs and improved patient care. By evaluating skin lesions from images, deep learning techniques have shown considerable potential in increasing the precision of melanoma detection. By using large datasets and complex neural networks, deep learning algorithms can effectively distinguish between benign and malignant skin lesions with high accuracy. Ensemble of CNN models helps improve the performance and reliability of the classification task. By combining the predictions of multiple CNN models lead to more accurate and robust predictions. In this thesis, for melanoma classification problem, many different data augmentations techniques applied and different convolutional neural networks architectures evaluated, applied vignetting effect filter and hair noise in accordance with the dataset and results of ensemble of the best CNN models are promising. This thesis attempts to produce a reliable model for the classification of melanoma by conducting experiments on two combined publically accessible data sets, ISIC 2019 and ISIC 2020. On the testing sets in our studies, the proposed solution attained 95.75% AUC.Master Thesis Bilgisayar Algoritmalarının GPU ile Hızlandırılması(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2023) Yalçın, Salih; Alkan, Gülay YalçınTravelling Salesman Problem (TSP) is one of the significant problems in computer science which tries to find the shortest path for a salesman who needs to visit a set of cities and it involves in many computing problems such as networks, genome analysis, logistic etc. Using parallel executing paradigms, especially GPUs, is appealing in order to reduce the problem-solving time of TSP. One of the main issues in GPUs is to have limited GPU memory which would not be enough for the entire data. Therefore, transferring data from host device would reduce the performance in execution time. In this study, we present a methodology for compressing data to represent cities in the TSP so that we include more cities in GPU memory. We implement our methodology in Iterated Local Search (ILS) algorithm with 2-opt and show that our implementation presents 29% performance improvement compared to the state-of-the-art GPU implementation.Master Thesis Erken Orman Yangını Tespiti için Otonom Heterojen Çoklu Robot Sistemi Tasarımı(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Serin, Ömer Faruk; Güler, SametThe usage of autonomous multi-robot systems for human life-endangering applications is emerging. Early wildfire detection and firefighting are two example applications. In this study, a heterogenous multi-robot system is proposed for both fire detection and response. The system employs an unmanned aerial vehicle for beyond-visual line-of-sight observations and an unmanned ground robot for fire extinguisher carrying. The proposed method uses ultrawideband (UWB) communication and ranging modules for the relative localization of robots during their movements. A specially trained YOLOv7 object detection model is used for robustly detecting forest fires and smoke while a modified version of the Vector Field Histogram Plus (VFH+) algorithm on the ground robot is used for obstacle avoidance while navigating. The structural design of the system requires no odometry or mapping of the environment hence improving the applicability of the system while decreasing system complexity. Additionally, the proposed UWB localization system is shown to be robust in long-lasting operations unlike many odometry-based approaches which accumulate errors with time. Moreover, localization of the UAV is realized with only three independent UWB-based range measurements and the altitude information of the UAV. The system is tested both in a realistic simulation environment and in real experimental setups with multiple runs. Results showed that the proposed system is improvable for better detection and practical to implement even in a dense forest environment without the need for GPS sensors, odometer data, or magnetometer.Master Thesis K-mer Sekans Gösterimine Dayalı MicroRNA-Hastalık İlişkilerinin ve MicroRNA-Tür İlişkilerinin Sınıflandırılması(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Erbaşı, Yalçın Han; Güngör, BurcuThe dysregulated gene expression brings about a variety of diseases, and dysregulation of microRNA (miRNA) has a wide impact on disease development and cellular physiology. Thus, miRNAs play important roles in a variety of fundamental and significant biological processes related to human diseases. There are a lot of research about changes in the function of miRNAs have been published in many human diseases. Computational methods serve as a complementary process to traditional wet-lab experiments, which require many resources and time in terms of detecting potential miRNA-Disease associations. Furthermore, there is a need to present a novel approach that allows assignment of an unknown miRNA to its most likely species. An easy way to filter new data would be to ensure that the new miRNA is classified below the maximum distance to the species known to originate from. In this thesis, a computational model has been proposed for identifying miRNA-disease and miRNA-Species associations by depicting the miRNAs with their k-mer sequence representation and by utilizing machine learning methodologies. The difference of our approach is which we reveal disease and species associated the sequences of miRNA store information. This put a question about the miRNA's chemical compounds and their associations with different types of species and diseases. With this study, the new disease-disease and species-Species associations disclosed can be calculated for many different species and diseases, these approaches can develop to species and disease classification. Lastly, our study may open a door to redefine species and diseases classifications which have been used nowadays, also it may provide the improvement of treatment strategies and early diagnosisMaster Thesis Grafik Teorisi Tabanlı Trafik Işığı Yöntemi(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Thahir, Adam Rizvi; Güngör, Vehbi Çağrı; Coşkun, MustafaTraffic congestion and delays caused in traffic light intersections can adversely affect countries in terms of money, time, and air pollution. With the advancement of computational power as well as artificial intelligent algorithms, researchers seek novel and optimized solutions to the traffic congestion problem. Most modern traffic light systems use manually designed traffic phase plans at intersections, and although this has proven to be relatively sufficient for today's traffic management systems, implementing a smarter traffic phase selection system is deemed to be more effective. Traditional approaches rely heavily on traffic history (static information), whereas Reinforcement Learning (RL) algorithms, which offer an 'adoptable'/dynamic traffic management system, are gaining increased research interest. Despite the usefulness of these RL based deep learning techniques, they inherently suffer from training time to apply them in real-world traffic management systems. This study aims to alleviate the training time problem of deep learning-based techniques, The research brings forth a novel graph-based approach that is able to use known occupancies of roads to predict which other roads in a given network would become congested in the future. Based on the predictions obtained, we are able to dynamically set traffic light times in all intersections within a connected network, starting from roads with known occupancies, and moving along connected roads that are anticipated to be congested. Predications are done using edge-based semi-supervised graph algorithms. Conducted simulations show that our approach can yield comparable average wait time to that of deep-learning based approach in minutes, compared to the much longer training time required by the deep-learning models. Keywords: Deep Learning, Reinforcement Learning, Traffic Flow, Congestion