https://hdl.handle.net/20.500.12573/203 2026-07-09T05:59:28Z 2026-07-09T05:59:28Z Yengec-Tasdemir,Sena Busra Aydin,Zafer Akay,Ebru Doğan,Serkan Yilmaz,Bulent https://hdl.handle.net/20.500.12573/2542 2025-06-23T08:02:12Z 2024-01-01T00:00:00Z

An effective colorectal polyp classification for histopathological images based on supervised contrastive learning Yengec-Tasdemir,Sena Busra; Aydin,Zafer; Akay,Ebru; Doğan,Serkan; Yilmaz,Bulent Early detection of colon adenomatous polyps is pivotal in reducing colon cancer risk. In this context, accurately distinguishing between adenomatous polyp subtypes, especially tubular and tubulovillous, from hyperplastic variants is crucial. This study introduces a cutting-edge computer-aided diagnosis system optimized for this task. Our system employs advanced Supervised Contrastive learning to ensure precise classification of colon histopathology images. Significantly, we have integrated the Big Transfer model, which has gained prominence for its exemplary adaptability to visual tasks in medical imaging. Our novel approach discerns between in-class and out-of-class images, thereby elevating its discriminatory power for polyp subtypes. We validated our system using two datasets: a specially curated one and the publicly accessible UniToPatho dataset. The results reveal that our model markedly surpasses traditional deep convolutional neural networks, registering classification accuracies of 87.1% and 70.3% for the custom and UniToPatho datasets, respectively. Such results emphasize the transformative potential of our model in polyp classification endeavors

2024-01-01T00:00:00Z Bakir-Gungor, Burcu Ersoz, Nur Sebnem Yousef, Malik https://hdl.handle.net/20.500.12573/2540 2025-06-17T08:27:12Z 2025-01-01T00:00:00Z

Integrating Biological Domain Knowledge with Machine Learning for Identifying Colorectal-Cancer-Associated Microbial Enzymes in Metagenomic Data Bakir-Gungor, Burcu; Ersoz, Nur Sebnem; Yousef, Malik Advances in metagenomics have revolutionized our ability to elucidate links between the microbiome and human diseases. Colorectal cancer (CRC), a leading cause of cancer-related mortality worldwide, has been associated with dysbiosis of the gut microbiome. This study aims to develop a method for identifying CRC-associated microbial enzymes by incorporating biological domain knowledge into the feature selection process. Conventional feature selection techniques often evaluate features individually and fail to leverage biological knowledge during metagenomic data analysis. To address this gap, we propose the enzyme commission (EC)-nomenclature-based Grouping-Scoring-Modeling (G-S-M) method, which integrates biological domain knowledge into feature grouping and selection. The proposed method was tested on a CRC-associated metagenomic dataset collected from eight different countries. Community-level relative abundance values of enzymes were considered as features and grouped based on their EC categories to provide biologically informed groupings. Our findings in randomized 10-fold cross-validation experiments imply that glycosidases, CoA-transferases, hydro-lyases, oligo-1,6-glucosidase, crotonobetainyl-CoA hydratase, and citrate CoA-transferase enzymes can be associated with CRC development as part of different molecular pathways. These enzymes are mostly synthesized by Eschericia coli, Salmonella enterica, Klebsiella pneumoniae, Staphylococcus aureus, Streptococcus pneumoniae, and Clostridioides dificile. Comparative evaluation experiments showed that the proposed model consistently outperforms traditional feature selection methods paired with various classifiers.

2025-01-01T00:00:00Z Yalcin, Salih Usul, Hamdi Burak Yalcin, Gulay https://hdl.handle.net/20.500.12573/2525 2025-05-08T11:33:55Z 2025-01-01T00:00:00Z

CompreCity: Accelerating the Traveling Salesman Problem on GPU with data compression Yalcin, Salih; Usul, Hamdi Burak; Yalcin, Gulay Traveling 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 is involved in many computing problems such as networks, genome analysis, logistics 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 the host device would reduce the performance in execution time. In this study, we applied three data compression methodologies to represent cities in the TSP such as (1) Using Greatest Common Divisor (2) Shift Cities to the Origin (3) Splitting Surface to Grids. Therefore, we include more cities in GPU memory and reduce the number of data transfers from the host device. We implement our methodology in Iterated Local Search (ILS) algorithm with 2-opt and The Lin-Kernighan-Helsgaun (LKH) Algorithm. We show that our implementation presents more than 25% performance improvement for both algorithms.

2025-01-01T00:00:00Z Hacilar, Hilal Aydin, Zafer Gungor, Vehbi Cagri https://hdl.handle.net/20.500.12573/2515 2025-05-06T12:58:51Z 2024-01-01T00:00:00Z

Network intrusion detection based on machine learning strategies: performance comparisons on imbalanced wired, wireless, and software-defined networking (SDN) network traffics Hacilar, Hilal; Aydin, Zafer; Gungor, Vehbi Cagri The rapid growth of computer networks emphasizes the urgency of addressing security issues. Organizations rely on network intrusion detection systems (NIDSs) to protect sensitive data from unauthorized access and theft. These systems analyze network traffic to detect suspicious activities, such as attempted breaches or cyberattacks. However, existing studies lack a thorough assessment of class imbalances and classification performance for different types of network intrusions: wired, wireless, and software-defined networking (SDN). This research aims to fill this gap by examining these networks' imbalances, feature selection, and binary classification to enhance intrusion detection system efficiency. Various techniques such as SMOTE, ROS, ADASYN, and SMOTETomek are used to handle imbalanced datasets. Additionally, eXtreme Gradient Boosting (XGBoost) identifies key features, and an autoenco der (AE) assists in feature extraction for the classification task. The study evaluates datasets such as AWID, UNSW, and InSDN, yielding the best results with different numbers of selected features. Bayesian optimization fine-tunes parameters, and diverse machine learning algorithms (SVM, kNN, XGBoost, random forest, ensemble classifiers, and autoencoders) are employed. The optimal results, considering F1-measure, overall accuracy, detection rate, and false alarm rate, have been achieved for the UNSW-NB15, preprocessed AWID, and InSDN datasets, with values of [0.9356, 0.9289, 0.9328, 0.07597], [0.997, 0.9995, 0.9999, 0.0171], and [0.9998, 0.9996, 0.9998, 0.0012], respectively. These findings demonstrate that combining Bayesian optimization with oversampling techniques significantly enhances classification performance across wired, wireless, and SDN networks when compared to previous research conducted on these datasets.

2024-01-01T00:00:00Z