A Hybrid Machine Learning Signal Classification Method Based on PCA Dimensionality Reduction

Abstract

The invention discloses a hybrid machine learning signal classification method based on PCA dimensionality reduction, comprising the following steps: Step 1, for linear frequency modulation signal LFM, binary phase shift keying BPSK signal, binary frequency shift keying 2FSK and four-phase For phase-shift keying QPSK signals, according to the instantaneous autocorrelation classification method, set the zero-crossing threshold and standard deviation threshold to separate the LFM signal, QPSK signal from other signals; step 2, the second-level classification, for the remaining signal BPSK The signal and the 2FSK signal adopt three characteristics of normalized amplitude duty cycle, normalized central instantaneous phase absolute value variance and normalized central instantaneous frequency absolute value variance, and use principal component analysis PCA algorithm to realize feature dimensionality reduction; steps 3. The objective function of the optimal classification is obtained by using the SVM classifier, and the distinction between BPSK and 2FSK signals is realized. The invention adopts the machine learning technology to realize classification, has high degree of automation and good classification effect.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a hybrid machine learning signal classification method based on PCA dimensionality reduction. Background technique [0002] Radar and electronic warfare systems need to automatically learn to recognize the electromagnetic signals they detect. The intra-pulse characteristics of radar signals are important parameters for electromagnetic signal sorting and identification in radar and electronic warfare systems. Therefore, in order to reliably sort and identify radar signals, it is necessary to analyze the intra-pulse features of radar signals. Conventional intrapulse analysis methods use threshold judgment based on manual experience, which is not highly automated and has insufficient adaptability to unknown situations. Due to limited training samples, manual experience thresholds may have poor classification results. Contents of the invention [0003] In view of the above-...

AI Technical Summary

Problems solved by technology

Conventional intrapulse analysis methods use threshold judgment based on manual experience, which is not highly automated and has insufficient adaptability to unknown situations. Due to limited training samples, manual experience thresholds may have poor classification results.

Images