Yazar "Altaher, Raoof" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Classification of data anonymization techniques
    (CRC Press, 2025) Koyuncu, Hakan; Altaher, Raoof
    In a world where data is becoming more valuable, finding new ways to keep our privacy safe against the tide of tech progress is more important than ever. This chapter dives deep into the world of anonymizing data in plain sight, blending deep thought with real-world uses, especially when it comes to the innovative industries of today and digital security. The chapter delves into the entire realm of data anonymization, encompassing basic techniques such as masking and expanding data, as well as intricate methods such as mathematically guaranteeing privacy and encrypting data while maintaining its usability. The discussion also focuses on how artificial intelligence (AI) is changing the game, making data anonymization more accessible. When talking about the new industrial revolution, it highlights how crucial AI is for making things run smoothly, from the Internet of Things to factories of the future, all while keeping our digital selves under wraps. Moreover, the chapter walks through the minefield of moral and legal rules, stressing the double challenge of following laws like the General Data Protection Regulation and California Consumer Privacy Act and the moral duty to keep individual privacy intact. It thoughtfully weighs the balance between keeping privacy sacred and making the most of data for the good of society and business. This key piece of work weaves together the theory and practice of making data anonymous, shining a spotlight on the vital role of AI and the need to keep evolving to meet the privacy challenges of our digital age. It sets the stage for more studies, policymaking, and ethical discussions on keeping our data safe, showing just how essential these strategies are in our data-soaked world.
  • Küçük Resim
    Öğe
    Novel hybrid optimization techniques for enhanced generalization and faster convergence in deep learning models: the nestyogi approach to facial biometrics
    (Multidisciplinary Digital Publishing Institute (MDPI), 2024) Altaher, Raoof; Koyuncu, Hakan
    In the rapidly evolving field of biometric authentication, deep learning has become a cornerstone technology for face detection and recognition tasks. However, traditional optimizers often struggle with challenges such as overfitting, slow convergence, and limited generalization across diverse datasets. To address these issues, this paper introduces NestYogi, a novel hybrid optimization algorithm that integrates the adaptive learning capabilities of the Yogi optimizer, anticipatory updates of Nesterov momentum, and the generalization power of stochastic weight averaging (SWA). This combination significantly improves both the convergence rate and overall accuracy of deep neural networks, even when trained from scratch. Extensive data augmentation techniques, including noise and blur, were employed to ensure the robustness of the model across diverse conditions. NestYogi was rigorously evaluated on two benchmark datasets Labeled Faces in the Wild (LFW) and YouTube Faces (YTF), demonstrating superior performance with a detection accuracy reaching 98% and a recognition accuracy up to 98.6%, outperforming existing optimization strategies. These results emphasize NestYogi’s potential to overcome critical challenges in face detection and recognition, offering a robust solution for achieving state-of-the-art performance in real-world applications.