Description
The text explores the role of artificial intelligence in converging RF and optical technologies for 5G/6G and IoT. It addresses emergent challenges such as quantum security, intelligent spectrum sharing and hybrid FSO-RF resilience. Covers machine learning and deep learning techniques for enhancing spectrum efficiency, latency reduction, and adaptive beamforming in converged RF and free-space optical networks. Explores Artificial Intelligence-based massive MIMO, reconfigurable intelligent surfaces, and dynamic beam alignment for next-generation wireless networks. Discusses federated learning, edge computing, and lightweight artificial intelligence models for resource-constrained Internet of Things devices in RF-optical hybrid networks. Addresses generative adversarial networks (GANs) for channel prediction, physical-layer security, and adversarial attack mitigation in intelligent communication systems. Presents reinforcement learning (RL) and graph neural networks (GNNs) for real-time resource management, QoS optimization, and network slicing in 5G/6G ecosystems. The text is primarily written for senior undergraduates, graduate students, and academic researchers in electrical engineering, electronics and communications engineering, optical communication, RF, wireless communication, telecommunication, and communication system design.