Youssef Hamdy M, Osman Radwa Ahmed, El-Bary Alaa A
Mechanical Engineering Department, College of Engineering and Architecture, Umm Al Qura University, Makkah 21955, Saudi Arabia.
Basic and Applied Science, College of Engineering, Arab Academy for Science, Technology and Maritime Transport, Alexandria P.O. Box 1029, Egypt.
Sensors (Basel). 2024 Apr 26;24(9):2761. doi: 10.3390/s24092761.
Modern homes are experiencing unprecedented levels of convenience because of the proliferation of smart devices. In order to improve communication between smart home devices, this paper presents a novel approach that particularly addresses interference caused by different transmission systems. The core of the suggested framework is an intelligent Internet of Things (IoT) system designed to reduce interference. By using adaptive communication protocols and sophisticated interference management algorithms, the framework minimizes interference caused by overlapping transmissions and guarantees effective data sharing. This can be accomplished by creating an optimization model that takes into account the dynamic nature of the smart home environment and intelligently allocates resources. By maximizing the signal quality at the destination and optimizing the distribution of frequency channels and transmission power levels, the model seeks to minimize interference. A deep learning technique is used to augment the optimization model by adaptively learning and predicting interference patterns from real-time observations and historical data. The experimental results show how effective the suggested hybrid strategy is. While the deep learning model adjusts to shifting interference dynamics, the optimization model efficiently controls resource allocation, leading to better data reception performance at the destination. The system's robustness is assessed in various kinds of situations to demonstrate its flexibility in responding to changing smart home settings. This work not only offers a thorough framework for interference reduction but also clarifies how deep learning and mathematical optimization can work together to improve the dependability of data reception in smart homes.
由于智能设备的大量涌现，现代家庭正经历着前所未有的便利程度。为了改善智能家居设备之间的通信，本文提出了一种新颖的方法，特别针对不同传输系统所造成的干扰。所建议框架的核心是一个旨在减少干扰的智能物联网（IoT）系统。通过使用自适应通信协议和复杂的干扰管理算法，该框架将重叠传输所造成的干扰降至最低，并保证有效的数据共享。这可以通过创建一个考虑到智能家居环境动态特性的优化模型并智能地分配资源来实现。通过最大化目的地的信号质量并优化频道和传输功率水平的分配，该模型力求将干扰降至最低。一种深度学习技术被用于增强优化模型——通过从实时观测和历史数据中自适应地学习和预测干扰模式。实验结果表明了所建议的混合策略的有效性。当深度学习模型适应不断变化的干扰动态时，优化模型有效地控制资源分配，从而在目的地实现更好的数据接收性能。在各种情况下评估了该系统的稳健性，以证明其在应对不断变化的智能家居设置方面的灵活性。这项工作不仅提供了一个全面的减少干扰框架，还阐明了深度学习和数学优化如何协同工作以提高智能家居中数据接收的可靠性。
