Key points are not available for this paper at this time.
The next-generation wireless system relies heavily on the cognitive radio network (CRN), which encounters unprecedented challenges as a result of the growing demand for radio spectrum to accommodate wireless services. Cognitive radio (CR) technology efficiently handles spectrum applications, primarily focusing on spectrum sensing to overcome scarcity and enhance spectrum utilization efficiency. The main challenge for cognitive radio lies in reliably identifying the presence of primary users to minimize interference with ongoing communications. This paper explores the integration of artificial intelligence (AI) and conventional spectrum-sensing techniques with 5G networks, empowering them with predictive and proactive capabilities. AI-driven base stations make autonomous decisions, and mobile devices form dynamically flexible clusters based on learned data, significantly improving network efficiency, latency, and reliability. The proliferation of massive IoT devices has intensified the spectrum scarcity crisis, necessitating innovative solutions like spectrum sharing. Machine learning (ML) plays a pivotal role in enhancing 5G. By learning signal characteristics, ML enhances spectrum sensing and other CR applications. The paper presents a comparative study between conventional and AI-based spectrum-sensing techniques, demonstrating the superiority of the AI-driven approach in optimizing spectrum performance. The research contributions highlight the novel impact of AI-based spectrum sensing on cognitive radio networks and offer valuable insights for future wireless communication systems. The results promise transformative advancements in spectrum management and network performance, solidifying the significance of AI in shaping the future of wireless technologies.
Pant et al. (2025) studied this question.