Fractal Complexity-Based Feature Extraction Algorithm of Communication Signals

Abstract

How to analyze and identify the characteristics of radiation sources and estimate the threat level by means of detecting, intercepting and locating has been the central issue of electronic support in the electronic warfare, and communication signal recognition is one of the key points to solve this issue. Aiming at accurately extracting the individual characteristics of the radiation source for the increasingly complex communication electromagnetic environment, a novel feature extraction algorithm for individual characteristics of the communication radiation source based on the fractal complexity of the signal is proposed. According to the complexity of the received signal and the situation of environmental noise, use the fractal dimension characteristics of different complexity to depict the subtle characteristics of the signal to establish the characteristic database, and then identify different broadcasting station by gray relation theory system. The simulation results demonstrate that the algorithm can achieve recognition rate of 94% even in the environment with SNR of −10dB, and this provides an important theoretical basis for the accurate identification of the subtle features of the signal at low SNR in the field of information confrontation.

Multi‐feature data mining for CT image recognition

“…[21][22][23] In the training process of deep learning training, unsupervised learning is added as pre-training, which is the main difference between the proposed training process of deep learning model and artificial neural network. Firstly, single-layer neurons are constructed layer by layer, and a single-layer network is trained at one time.…”

“…Then, the wake-sleep algorithm is used to adjust after all layers are trained, which effectively overcomes disadvantages in learning such as local optimization and instability of the gradient descent method by building a multilayer neural network on unsupervised data. [21][22][23] In the training process of deep learning training, unsupervised learning is added as pre-training, which is the main difference between the proposed training process of deep learning model and artificial neural network. Recognition method of multi-feature CT medical images with deep learning methods is proposed as follows.…”

Fuzzy clustering recognition algorithm of medical image with multi‐resolution feature

“…21,22 In medical image acquisition, it is required to calibrate the position of the camera in this paper. 21,22 In medical image acquisition, it is required to calibrate the position of the camera in this paper.…”

“…Due to the wide variety of medical images preprocessing, the differences in light environments have led to problems such as low quality. 21,22 In medical image acquisition, it is required to calibrate the position of the camera in this paper. Then, it is ensured that the camera performs translational movement along a calibrated reference line and accurately records the distance the camera moves, with baseline distance B as corresponding moving distance.…”

Editorial

“…With the advantage in characterizing multi-scale structure, fractal theory has been proposed for fractured porous media. Aiming at accurately extracting the individual characteristics of the radiation source for the increasingly complex communication electromagnetic environment, a novel feature extraction algorithm for individual characteristics of the communication radiation source based on the fractal complexity of the signal is proposed by Wang et al 15 Simulation results demonstrate that the algorithm can achieve higher recognition rate in worse environment. Fractal encoding method becomes an effective image compression method because of its high compression ratio and short decompressing time.…”