Yazar "ŞAHİN, CANAN BATUR" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Optimization of Software Vulnerabilities patterns with the Meta-Heuristic Algorithms
    (2022) ŞAHİN, CANAN BATUR
    In order to ensure the development of secure software, it is essential to predict software vulnerabilities. Nevertheless, there can be considerable losses in case of an attack on an information system. Detecting a dangerous code, which can lead to severe unknown consequences, requires great effort. There is a strong need to devise meta-heuristic-based approaches to provide effective security and prevent vulnerabilities or mitigate them. The primary focus of studies on software vulnerability prediction models is to specify the best set of predictors that are related to the presence of vulnerabilities. However, the existing vulnerability detection methods suffer from coarse detection granularity and a bias toward global features or local features. The framework proposed in the present work improves optimization algorithms for the best set of optimized vulnerability patterns correlated for software vulnerabilities based on a clock- work memory mechanism. Using the proposed framework, we found vulnerable optimized patterns based on clock-work memory mechanism feature representation learning that directly. The effectiveness of the developed algorithm was further improved with the clock-work memory mechanism based on 6 open-source projects, such as LibTIFF, Pidgin, FFmpeg, LibPNG, Asteriks, and VLC media player datasets.
  • Küçük Resim Yok
    Öğe
    Transfer Learning for Detection of Casting Defects Model In Scope of Industrial 4.0
    (2023) TANYILDIZ, Hayriye; ŞAHİN, CANAN BATUR
    Casting represents a production process where a liquid material is poured into a mold with a hollow cavity, usually of the intended shape, following which its solidification is allowed. Numerous defect types are available, including blow holes, pin holes, burrs, mold material defects, shrinkage defects, metallurgical defects, casting metal defects, etc. All industries have quality control departments to eliminate the occurrence of this defective product. But the main problem is that this inspection process is done manually. This is a very time consuming process and due to human sensitivity this is not 100% accurate. In this study, we will verify whether the \"manual inspection\" bottleneck can be eliminated by automating the inspection process with transfer learning in the manufacturing process of casting products. In this study, we will verify whether the \"manual inspection\" bottleneck can be eliminated by automating the inspection process with transfer learning in the manufacturing process of casting products. In this study, the casting images were divided into two separate classes, and the classification process was carried out by applying deep learning architectures. The benefits of this proposed approach are discussed and proposed as a more efficient way to control the quality of final products under Industry 4.0.