A Low-Complexity Modulation Classification Algorithm for MIMO–OSTBC System

Intelligent identification technology for high‐order digital modulation signals under low signal‐to‐noise ratio conditions

“…Traditional algorithm research mainly focuses on energy detection and the use of expert features and decision criteria to obtain the ability to recognise different signals. The modulation recognition method based on the likelihood ratio calculates the test statistic and compares it with a preset threshold to form a decision criterion [3][4][5]. This method is suitable for offline processing, where considerable prior information exists and there are no special requirements for the number of identification types.…”

Automatic modulation recognition based on CNN and GRU

“…ALRT takes unknown variables as random variables and calculates the likelihood function by computing the average value. GLRT calculates the probability density function of the input signal on the basis of the maximum likelihood estimation of unknown quantity and determines the modulation mode accordingly [2][3][4] . The LB classification method can theoretically obtain the optimal classification performance, but it requires substantial prior knowledge and a considerable amount of computation.…”