CitZO‐SVM: Machine Learning‐Based Spectrum Sensing and Channel Allocation for Cognitive Radio Networks
C. Supraja, Kavitha Thandapani · International Journal of Communication Systems · 2025
ABSTRACT In the fifth generation (5G) network, the cognitive radio network (CRN) is emerging as a solution for spectrum utilization by considering minimal spectrum usage. It is used with efficient spectrum sensing information and optimal channel assignment algorithms to optimize secondary user throughput. In this paper, a chaotic iterative zebra optimization‐based support vector machine (CitZO‐SVM) is proposed with the objective of improving the accuracy and reducing the complexity in CRN. To improve the sensing performance, the regularization parameters of SVM are optimized using the CitZO algorithm. The CitZO algorithm is modeled by integrating the chaotic iterative mapping and conventional Zebra optimization algorithm. Then, the channel assignment is employed optimally based on cooperative game theory by considering the utility factor and energy efficiency. Low complexity spectrum sensing and channel assignment algorithm are developed with less computational cost. The effectiveness of the proposed approach is verified through simulation results. The performance of the proposed approach is evaluated with 2.4 and 24 GHz bandwidth. The proposed technique achieves the throughput and the probability of 92.04 and 0.969 for 2.4 GHz frequency. The proposed methodology results in efficient spectrum utilization when compared to the existing channel assignment schemes.