Machine Learning-Based Cooperative Spectrum Sensing in Dynamic Segmentation Enabled Cognitive Radio Vehicular Network

A vehicle ad hoc network (VANET) is a solution for road safety, congestion management, and infotainment services. Integration of cognitive radio (CR), known as CR-VANET, needed to solve the spectrum scarcity problems VANET. Several research efforts have addressed concerns CR-VANET. However, more reliable, robust, faster sensing still challenge. novel segment-based CR-VANET (Seg-CR-VANET) architecture therefore proposed in this paper. Roads are divided equally into segments, they sub-segmented based on probability value. Individual vehicles or secondary users produce local results by choosing an optimal (SS) technique using hybrid machine learning algorithm that includes fuzzy naïve Bayes algorithms. We used dynamic threshold values techniques. In cooperative SS, segment agent (SSA) made global decision tri-agent reinforcement (TA-RL) algorithm. Three environments (network, signal, vehicle) learned determine primary (licensed) users’ activities. The simulation indicate that, compared current works, Seg-CR-VANET produces better sensing.