Yazar "Dalloul, Ahmed Hany Assad" seçeneğine göre listele

Listeleniyor 1 - 1 / 1
  • Küçük Resim
    Yayın
    Enabling 5G and 6G technologies through millimeter-wave and VLC integration for enhanced remote health monitoring systems
    (Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, 2025-07-01) Dalloul, Ahmed Hany Assad; Miramirkhani, Farshad; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Elektronik Mühendisliği Yüksek Lisans Programı; Işık University, School of Graduate Studies, Electronics Engineering M.S. Program
    This thesis examines the pivotal role of wireless networks in healthcare, emphasizing the need for high-performance technologies like 5G and emerging 6G to enable efficient data transfer between medical devices such as sensors and remote monitoring equipment. We delve into the current research landscape surrounding 5G mmWave technology in remote health monitoring systems, focusing on its applications, main challenges, and future trends. We explore the wireless connectivity requirements of reconfigurable hybrid optical-radio-based Medical Body Sensor Networks (MBSNs), proposing an extension of conventional MBSNs to more flexible and generic solutions. This thesis introduces a comprehensive literature review across diverse domains including antenna design, small implantable antennas, on-body wearable solutions, and adaptable detection and imaging systems. Our research further investigates methodological approaches in monitoring systems, analyzing channel characteristics, advancements in wireless capsule endoscopy, and sensing and imaging techniques. Additionally, we explore how 6G's framework integrates Visible Light Communication (VLC) in healthcare, demonstrating how VLC-enabled MBSNs can revolutionize remote patient monitoring and real-time health data transmission by accurately estimating VLC channel parameters, such as channel DC gain and RMS delay spread. We introduce a sophisticated ray tracing technique and ML-based algorithm to model channels and estimate path loss and RMS delay spread within different hospital settings such as ICU ward and family-type patient room. The detailed results of the hospital scenarios are listed using various machine learning algorithms such as LSTM, GRU, RNN, Linear Regression SVR, and KNN. The estimation was illustrated and detailed comprehensively by choosing the best-performing ML technique.