| Abstract |
Modern urban development depends on optimizing cognitive sensor communications in smart cities, which is the focus of this investigation. In the era of expanding sensor networks, efficient data transmission is paramount for the success of smart city initiatives. The current state of sensor communication faces challenges like suboptimal adaptability, inefficient energy usage, and limited fault detection. This study proposes a solution through the application of an Adaptive Neuro-Fuzzy Inference System (ANFIS), identifying these challenges as opportunities for improvement. The novelty lies in ANFIS's introduction as an intelligent and adaptive solution. Its ability to learn from sensor data, adapt to changing conditions, and optimize communication parameters sets it apart in enhancing cognitive sensor communication. The research methodology involves a systematic approach, encompassing data collection, pre-processing, and ANFIS model development. The model is rigorously trained, validated, and tested for real-world effectiveness. Integration into the smart city communication system is explored, emphasizing applications in context-aware communication, energy-efficient protocols, and fault detection. Performance is evaluated using metrics like accuracy, reliability, and efficiency, demonstrating the model's efficacy in addressing drawbacks and enhancing overall sensor communication in smart cities. The findings contribute to advancing intelligent systems for urban infrastructure and services. © 2024 IEEE. |
