METHOD FOR RECOGNIZING PRI MODULATION TYPE USING NEURAL NETWORK FUSE WITH GENETIC ALGORITHM AND APPARATUS THEREOF

摘要

The present invention relates to a method for recognizing a PRI modulation type and a device thereof, capable of being easily automated due to a simplified algorithm, lowering time complexity, and improving a modulation type recognition ratio. The method for recognizing a PRI modulation type according to the present invention comprises: a step of training a neural network using a heredity algorithm; a step of generating a DDTOA code using the time of arrival (TOA) of an input pulse; a step of generating a DDTOA matrix from the DDTOA code; a step of extracting seven PRI modulation type elements from the DDTOA matrix; a step of recognizing the PRI modulation type by inputting the seven elements to the neural network and outputting an output layer result of the neural network; a step of generating a result code from the output layer result of the neural network; and a step of recognizing the PRI modulation type by comparing the result code with a predetermined PRI modulation code.