Answers are grounded in this paper and cite their sources.
Real-time and accurate identification of modulated signals can help optimize signal demodulation, identify interference types, and improve the efficiency and reliability of communication systems in the absence of a priori information, to achieve the functions of communication system performance evaluation, signal classification, adaptive modulation, interference detection and suppression, and spectrum management. To improve the accuracy of modulation identification, an intelligent identification algorithm for modulated signals based on wavelet transform and support vector machine (SVM) is proposed. The algorithm takes the energy features of the low-frequency part of the modulated signal as the input of SVM, divides the data sample set into a test data set and a training data set, and after the SVM model is trained by the training data set, the test set is tested and recognized by this model, and the average recognition accuracy reaches 98.3% [1], which is an average of 29.2% compared to the other feature extraction methods (including the short-time Fourier, time-domain, frequency-domain, and distance features). 29.2%. Finally, the optimal machine learning method, i.e., the support vector machine algorithm, was further selected based on analytic hierarchy process.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: