Sensor-Driven Traffic and Time Control Optimization Using MANET and Quaternion GAN-Kookaburra Networks: A Review

Abstract

The rapid growth of intelligent transportation systems has necessitated advanced traffic and time control optimization techniques capable of handling dynamic and large-scale environments. This paper presents a systematic review of recent advances in sensor-driven transmission control systems integrated with Mobile Ad Hoc Networks (MANET), Quaternion-based deep learning models, Generative Adversarial Networks (GANs), and bio-inspired Kookaburra optimization algorithms. Sensor-driven systems enable real-time traffic monitoring and adaptive control, while MANET facilitates decentralized communication among vehicles and infrastructure. Recent studies demonstrate that machine learning and deep learning approaches significantly improve traffic flow prediction and congestion management. Graph Neural Networks and multi-agent reinforcement learning models have shown strong performance in distributed traffic engineering, achieving efficient congestion minimization and scalability. Additionally, optimization techniques such as genetic algorithms and reinforcement learning enhance signal timing efficiency and reduce travel delays. Emerging approaches, including quaternion neural networks and GAN-based modeling, provide improved representation of spatiotemporal traffic data. Furthermore, bio-inspired optimization methods such as Kookaburra optimization demonstrate superior convergence and energy efficiency in network routing and control systems. This review analyzes existing methodologies, presents comparative insights, and identifies research gaps for developing scalable, intelligent, and real-time traffic control systems.