Abstract
Decision-making ability plays a key role in the cognitive radio system. The decision-making engine is expected to decide a suitable radio configuration (modulation mode, coding mode, coding rate, etc.) according to the complex and varying radio environment. In this paper, we propose a decision-making method for the Orthogonal Frequency Division Multiplexing (OFDM) communication system. Through this method, we can select waveform parameters for any channel condition to achieve optimal communication performance via the Back Propagation (BP) Neural Network (NN) regression. The simulation results illustrate the proposed method can provide a reasonable decision surface with various wireless channel condition.