Modulation signal identification method of quantum root tree mechanism evolution extreme learning machine

Abstract

According to the modulation signal identification method of the quantum root tree mechanism evolutionary extreme learning machine provided by the invention, a weighted Myriad filter is utilized to suppress impact noise, a quantum root tree mechanism is proposed to perform efficient solution, and some application limitations of the existing modulation signal identification method based on the evolutionary extreme learning machine are broken through. According to the modulation signal identification method of the quantum root tree mechanism evolution extreme learning machine, the quantum root tree mechanism is designed, the weight and the threshold of the extreme learning machine under impact noise can be solved with high precision, and the modulation identification rate is effectively improved. Simulation experiments prove the effectiveness of the modulation signal identification method of the quantum root tree mechanism evolution extreme learning machine under the impact noise, the application limitation of performance deterioration and even failure of a traditional method under the impact noise and low signal-to-noise ratio environment is broken through, and the identification rate is greatly improved compared with the traditional method.

Description

technical field [0001] The invention relates to a modulated signal identification method based on a quantum root tree mechanism in an impact noise environment, belonging to the field of communication signal processing. Background technique [0002] In recent years, communication signal automatic modulation recognition technology has been widely used in spectrum allocation, electronic countermeasures, cognitive radio and other scenarios. In the military field, it is necessary to distinguish the modulation types of various communication signals and radar signals sent by the enemy's electronic equipment before the next step of demodulation, even monitoring and interference. In the civil field, applying modulation recognition technology to the field of cognitive radio can cooperate with modules such as parameter estimation and signal demodulation to effectively avoid radio interference and optimize spectrum allocation. [0003] With the advancement of science and technology and...

AI Technical Summary

Problems solved by technology

[0008] Through the retrieval of existing technical literature, Song Lihui et al. used extreme learning machine to realize Gaussian noise in "Digital Communication Modulation Recognition Based on Extreme Learning Machine" published in "Laser Journal" (2016,37(3):119-122). The identification of the next seven types of digital modulation signals, but without considering the impact of impact noise and the evolution of extreme learning machines, it is difficult to obtain optimal parameters; Zhang Hui published "Machine Learning Based Communication Signals" (Harbin Engineering University, 2016) In "Research on Modulation Recognition Methods", the particle swarm algorithm and principal component analysis were used to evolve the parameters and structure of the extreme learning machine, and the recognition rate was improved under Gaussian noise, but the impact of the impact noise environment was not considered.

[0009] The search results of the existing literature show that most of the existing modulation signal recognition methods based on evolutionary extreme learning machines are implemented in the Gaussian noise environment, and the performance deteriorates in the impact noise environment. Therefore, a quantum rooted tree mechanism based on the impact noise is proposed. The modulation signal identification method of the evolutionary extreme learning machine, the overall process is to use the weighted Myriad filter to suppress the impact noise, and then perform feature extraction on this basis, and then evolve the parameters of the extreme learning machine through the quantum root tree mechanism to solve the existing problems based on evolutionary extreme learning. The performance degradation of the modulated signal recognition method of the machine in the impact noise environment

Images