Yazar "Altunay, Hakan Can" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ 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.
  • Küçük Resim
    Öğe
    ICCA: An Improved Intrusion Detection Algorithm for Healthcare Data Classification and URLs phishing
    (Budapest Tech Polytechnical Institution, 2026) Alarbi, Abdalraouf; Albayrak, Zafer; Çakmak, Muhammet; Altunay, Hakan Can
    Classification is a fundamental task in machine learning that involves assigning data instances to one or more predefined categories or classes. Among the various classification algorithms available is the Core Classification Algorithm (CCA). However, CCA has limitations, particularly when dealing with high-dimensional data, which can negatively affect its classification performance. To address these limitations, this study proposes a new algorithm called the Improved Core Classification Algorithm (ICCA), which enhances the performance of CCA by incorporating novel features and techniques. In this article, the principles and design of ICCA were described and its performance was compared to that of CCA and other state-of-the-art classification methods on four datasets from the healthcare and phishing URLs domains. Experimental results on four datasets demonstrate that ICCA consistently outperforms the original CCA, achieves the highest accuracy on the high-dimensional phishing and cardiovascular datasets, and remains competitive on imbalanced medical data. Overall, this work contributes to the advancement of classification algorithms and provides a valuable tool for various real-world applications. © 2026, Budapest Tech Polytechnical Institution. All rights reserved.