Intelligent clustering method based on hierarchical self-organizing mapping digital signal modulation mode

Abstract

The invention discloses an intelligent clustering method based on a hierarchical self-organizing mapping digital signal modulation mode. The intelligent clustering method comprises the steps of S1, acquiring a target data sequence; S2, extracting normalized high-order cumulant and amplitude moment characteristics of the signal to obtain a characteristic space with a high-dimensional vector; and S3, processing high-dimensional feature data by adopting a hierarchical self-organizing mapping model, and clustering feature vectors of MPSK (multi-order phase shift keying) and MQAM (multi-order quadrature amplitude modulation) signals with different orders in the layering process. The method has the advantages that the principle is simple, the operation is simple and convenient, computing resources can be saved, and the time required for converging to an expected clustering result is shorter.

Description

technical field [0001] The invention mainly relates to the technical field of wireless communication, in particular to an intelligent clustering method based on a hierarchical self-organizing mapping digital signal modulation mode. Background technique [0002] Automatic Modulation Classification (AMC) refers to the practical and accurate identification of modulated signals when a priori information is insufficient. When receiving an over-the-air signal in an environment, first identify the modulation type of the signal, and then decode the received signal information. Whether in civilian or military fields, automatic modulation classification plays an important role in complex wireless non-cooperative communication environments. [0003] The received signal of the modulation type to be identified is usually from a non-cooperative system, and the received signal is always affected by various interferences, which undoubtedly makes the identification task more challenging. S...

AI Technical Summary

Problems solved by technology

[0003] The received signal of the modulation type to be identified is usually from a non-cooperative system, and the received signal is always affected by various interferences, which undoubtedly makes the identification task more challenging

Subtractive clustering can classify different types of modulation signals without setting the number of clusters in advance, but the process of adjusting the rejection threshold and acceptance threshold of the cluster density is more complicated

In addition, the characteristic quantity of the modulated signal to be identified is complex, and the support vector machine method suitable for linear classification is difficult to achieve nonlinear classification when the signal is to be identified

Images