Yazar "Çakmak, Muhammet" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    AUTOENCODER-BASED INTRUSION DETECTION IN CRITICAL INFRASTRUCTURES
    (Karabük Üniversitesi, 2024) Altunay, Hakan Can; Albayrak, Zafer; Çakmak, Muhammet
    Securing critical infrastructure systems such as electricity, energy, health, management, transportation, and production facilities against cyber attacks is the issue on which states spend the most time and money when creating security strategies. Every day, different methods have emerged to prevent attackers who endanger our personal and national security with varying types of attacks. The most important of these methods is intrusion detection systems. This study proposes an autoencoder-based intrusion detection system model to detect security anomalies in critical infrastructures. The accuracy of this proposed model in attack detection has been tested with the current and complex UNSW-NB15 dataset. In the proposed model, training and testing steps were carried out using the attack packages in the data set. These packages are then divided into two: normal or attack. According to the results obtained in the experiments, it has been confirmed that the proposed intrusion detection system can effectively detect attacks with high performance.
  • [ X ]
    Öğe
    Automatic Maize Leaf Disease Recognition Using Deep Learning
    (Sakarya University, 2024) Çakmak, Muhammet
    Maize leaf diseases exhibit visible symptoms and are currently diagnosed by expert pathologists through personal observation, but the slow manual detection methods and pathologist's skill influence make it challenging to identify diseases in maize leaves. Therefore, computer-aided diagnostic systems offer a promising solution for disease detection issues. While traditional machine learning methods require perfect manual feature extraction for image classification, deep learning networks extract image features autonomously and function without pre-processing. This study proposes using the EfficientNet deep learning model for the classification of maize leaf diseases and compares it with another established deep learning model. The maize leaf disease dataset was used to train all models, with 4188 images for the original dataset and 6176 images for the augmented dataset. The proposed models were compared with ResNet50, VGG19, DenseNet121 and Inception V3 models according to their accuracy, sensitivity, F1-Score and precision values. The EfficientNet B6 model achieved 98.10% accuracy on the original dataset, while the EfficientNet B3 model achieved the highest accuracy of 99.66% on the augmented dataset. © 2024, Sakarya University. All rights reserved.
  • [ X ]
    Öğe
    The Impact of Denial-of-Service Attacks and Queue Management Algorithms on Cellular Networks
    (2024) Çakmak, Muhammet
    In today's digital landscape, Distributed Denial of Service (DDoS) attacks stand out as a formidable threat to organisations all over the world. As known technology gradually advances and the proliferation of mobile devices, cellular network operators face pressure to fortify their infrastructure against these risks. DDoS incursions into Cellular Long-Term Evolution (LTE) networks can wreak havoc, elevate packet loss, and suboptimal network performance. Managing the surges in traffic that afflict LTE networks is of paramount importance. Queue management algorithms emerge as a viable solution to wrest control over congestion at the Radio Link Control (RLC) layer within LTE networks. These algorithms work proactively, anticipating, and mitigating congestion by curtailing data transfer rates and fortifying defences against potential DDoS onslaughts. In the paper, we delve into a range of queue management methods Drop-Tail, Random Early Detection (RED), Controlled Delay (CoDel), Proportional Integral Controller Enhanced (PIE), and Packet Limited First In, First Out queue (pFIFO). Our rigorous evaluation of these queue management algorithms hinges on a multifaceted assessment that encompasses vital performance parameters. We gauge the LTE network's resilience against DDoS incursions, measuring performance based on end-to-end delay, throughput, packet delivery rate (PDF), and fairness index values. The crucible for this evaluation is none other than the NS3 simulator, a trusted platform for testing and analysis. The outcomes of our simulations provide illuminating insights. CoDel, RED, PIE, pFIFO, and Drop-Tail algorithms emerge as top performers in succession. These findings underscore the critical role of advanced queue management algorithms in fortifying LTE networks against DDoS attacks, offering robust defences and resilient network performance.