Abstract: The rapid proliferation of Internet of Things (IoT) devices has intensified the demand for efficient spectrum utilization, making traditional static spectrum allocation insufficient. Cognitive Radio (CR) technology emerges as a promising solution by enabling dynamic spectrum access through intelligent spectrum sensing and adaptive decision-making. This review paper presents a comprehensive analysis of intelligent spectrum sensing and data fusion techniques in Cognitive Radio–enabled IoT networks. It systematically examines conventional spectrum sensing approaches, including energy detection, matched filtering, and cyclostationary detection, highlighting their limitations in noisy, heterogeneous, and large-scale IoT environments. To address these challenges, the paper explores machine learning and deep learning–based spectrum sensing methods that enhance detection accuracy, robustness, and adaptability. Furthermore, the role of data fusion is critically reviewed, focusing on data-level, feature-level, and decision-level fusion strategies that improve sensing reliability by combining observations from multiple IoT nodes. Intelligent data fusion techniques based on neural networks, fuzzy logic, and reinforcement learning are also discussed, emphasizing their capability to reduce uncertainty and communication overhead. The integration of spectrum sensing and data fusion within edge and fog computing paradigms is analyzed to support real-time and energy-efficient IoT applications. Finally, the paper identifies open research challenges related to scalability, security, latency, and standardization, and outlines future research directions toward 6G-enabled cognitive IoT systems. This review aims to serve as a valuable reference for researchers and practitioners working on intelligent spectrum management in next-generation IoT networks

Keywords: Cognitive Radio, Spectrum Sensing, Data Fusion, Internet of Things, Machine Learning, Cooperative Sensing, Dynamic Spectrum Access.

Downloads: | DOI: 10.17148/IARJSET.2025.121260