http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15608 2026-04-23T06:58:45Z 2026-04-23T06:58:45Z Mehmet, BURUKANLI Musa, ÇIBUK http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15733 2025-08-21T07:27:22Z 2024-01-01T00:00:00Z

Intrusion Detection and Performance Analysis Using Copula Functions Mehmet, BURUKANLI; Musa, ÇIBUK Nowadays, interest in technology is growing as technology advances and makes our jobs easier. These rapid technological advancements bring with them a slew of unwanted negative attacks, such as cyber-attacks and unauthorized access. To prevent such negative attacks, intrusion detection systems are frequently used. In this research, we make some suggestions for novel and reliable classifiers for intrusion detection systems that are based on copulas. Using copula-based classifiers, we hope to detect intrusion in computer networks. Student's-t, Gumbel, Clayton, Gaussian, Independent and Frank classifiers, which are frequently used in the literature, have been preferred as copula-based classifiers. These classifiers were used to perform classification on the KDD'99 dataset. The 10-fold cross-validation method has been used in the classification phase. When the experimental results were examined, the proposed Gaussian copula-based classifier outperformed state-of-the-art basic methods on the KDD'99 dataset with a success rate of 99.41%. As a direct consequence of this, classifiers based on the copula have shown promising results in the field of intrusion detection. Classifiers that are based on the copula have been found to be a competitive alternative to the most recent and cutting-edge fundamental approaches.

2024-01-01T00:00:00Z Maksut, SELOĞLU http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15732 2025-08-21T07:24:22Z 2024-01-01T00:00:00Z

An Investigation of the Fresh and Hardened Properties of Nano Zinc Oxide Reinforced 3D Printed Geopolymer Mortars Maksut, SELOĞLU It is well known that even small amounts of nanomaterials can improve the mortar structure and enhance its fresh state and hardened properties. This paper investigates the fresh state and hardened properties of nano zinc oxide-reinforced 3D-printed geopolymer mortars. The mechanical properties of 7, 28, 90, and 180 days of 3Dprinted geopolymer mortars cured at ambient temperature were investigated. For this purpose, 3D-printed geopolymer mortar samples containing 0%, 0.25%, 0.50%, and 0.75% nano zinc oxide were produced. Flow table and buildability tests were applied to these samples to determine the fresh state properties. Ultrasonic pulse velocity, flexural strength, and compressive strength tests were applied to the hardened 3Dprinted geopolymer mortar samples. The best mechanical test results were obtained from 3D-printed geopolymer mortar samples containing 0.5% nano zinc oxide at the end of all curing times. In the ZN 50 series cured for 28 days, approximately 29% higher strength was obtained in FS and 66% higher in compressive strength compared to the ZN 0 series without nanomaterials. It has been noted that incorporating a tiny quantity of nano zinc oxide into 3D-printed geopolymer mortars improves their mechanical performance.

2024-01-01T00:00:00Z Nuray, YAVUZKANAT http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15731 2025-08-21T07:21:59Z 2024-01-01T00:00:00Z

Exploring Radiation Shielding Properties of Lanthanide Elements Nuray, YAVUZKANAT In this work, the radiation shielding properties of Lanthanide elements were studied using the EpiXS program and GATE simulation, which agreed well with each other, based on some key parameters such as MAC, LAC, HVL, MFP, EABF, and EBF. It was observed that at lower energies of gamma-rays, the values of MAC and LAC are maximum, which decrease with the increase in energy due to reduced photoelectric interactions. Photoelectric absorption edges couple with peaks in attenuation values; peaks for elements of the lower atomic number, La, Ce, Pr, and Nd, appear as two while the peaks for elements of higher atomic number are three due to the additional absorptions by L-shell sub- levels or Mshell. These peaks take place when the energy of photons meets the energy level of electron binding. While Lutetium has the highest and Europium has the lowest LAC values, Lutetium also has the lowest HVL and MFP values; thus, it has the best radiation shielding properties. The EABF and EBF reach their maximum in the medium energy range and then decrease. Lutetium has the lowest photon buildup, and Lanthanum has the highest EABF and EBF values for all the studied elements at all penetration depths.

2024-01-01T00:00:00Z Kazım, FIRILDAK Gaffari, ÇELİK Muhammed Fatih, TALU http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/15730 2025-08-21T07:18:52Z 2024-01-01T00:00:00Z

SimCLR-based Self-Supervised Learning Approach for Limited Brain MRI and Unlabeled Images Kazım, FIRILDAK; Gaffari, ÇELİK; Muhammed Fatih, TALU In this study, a SimCLR-based model is proposed for the classification of unlabeled brain tumor images in medical imaging using a self-supervised learning (SSL) technique. Additionally, the performances of different SSL techniques (Barlow Twins, NnCLR, and SimCLR) are analyzed to evaluate the performance of the proposed model. Three different datasets, consisting of pituitary, meningioma, and glioma brain tumors as well as non-tumor images, were used as the dataset. Out of a total of 7,671 images, 6,128 were used as unlabeled data, and the model was trained with both labeled and unlabeled data. The proposed model achieved high performance with unlabeled data, reducing the need for manual labeling. As a result, the model demonstrated superior performance compared to other models, with high performance values such as 99.35% c_acc and 96.31% p_acc

2024-01-01T00:00:00Z