Low SNR Multi-Emitter Signal Sorting and Recognition Method Based on Low-Order Cyclic Statistics CWD Time-Frequency Images and the YOLOv5 Deep Learning Model

Abstract

It is difficult for traditional signal-recognition methods to effectively classify and identify multiple emitter signals in a low SNR environment. This paper proposes a multi-emitter signal-feature-sorting and recognition method based on low-order cyclic statistics CWD time-frequency images and the YOLOv5 deep network model, which can quickly dissociate, label, and sort the multi-emitter signal features in the time-frequency domain under a low SNR environment. First, the denoised signal is extracted based on the low-order cyclic statistics of the typical modulation types of radiation source signals. Second, the time-frequency graph of multisource signals was obtained through CWD time-frequency analysis. The cyclic frequency was controlled to balance the noise suppression effect and operation time to achieve noise suppression of multisource signals at a low SNR. Finally, the YOLOv5s deep network model is used as a classifier to sort and identify the received signals from multiple radiation sources. The method proposed in this paper has high real-time performance. It can identify the radiation source signals of different modulation types with high accuracy under the condition of a low SNR.

Blind Detection of Broadband Signal Based on Weighted Bi-Directional Feature Pyramid Network

“…These methods have a high detection accuracy but a low detection speed. Single-stage methods are target detection based on deep convolutional networks with regression computation using end-to-end target detection methods such as YOLO series [ 18 , 19 , 20 ] and so on. These methods have faster detection speeds and can meet real-time requirements.…”

“…YOLOv5 is a single-stage target detection network proposed by Ultralytics LLC. As the most mature and stable target detection network in the YOLO series at present, it is the product of improvements based on YOLOv4 and YOLOv3 [ 18 , 19 , 20 ]. After learning the advantages of the previous versions and other networks, YOLOv5 changes the previous YOLO target detection algorithm’s characteristics, i.e., faster detection but not high accuracy.…”

“…This network improves detection accuracy and real-time performance, which not only meets the need for real-time image detection but also has a smaller structure. Therefore, in this paper, we use the standard YOLOv5 as the target detection model, and the network structure is shown in Figure 5 [ 20 ], whose network model is divided into four parts: input, backbone, neck, and prediction head.…”

“…Based on the Single Shot MultiBox Detector (SSD) target detection method [ 16 , 17 ], the papers performed blind detection and modulation identification on broadband signals using time-frequency images and constellation images as input of the neural network. Based on this, Dr. Rundong Li proposed an improved target detection network based on You Only Look Once version 3 (YOLOv3) to further improve the performance of deep learning methods in signal blind detection tasks and demonstrated that the You Only Look Once (YOLO), series of methods [ 18 , 19 , 20 ] outperformed Faster Region Convolutional Neural Network (FRCNN) [ 21 , 22 ] and traditional energy detection methods [ 7 , 10 ] on this task.…”

Time-frequency preprocessing method of radiation source signal based on cyclic statistics

“…Among them, the method of extracting time-frequency domain image features to obtain the modulation type and core parameters of radiation source signals has been widely used in radiation source devices such as detection, guidance and communication [2] .However, with the increasing sampling rate of radiation source signal and the increase of computing time, it is difficult for time-frequency analysis to meet the requirements of high real-time signal processing. References [3][4][5][6] use the time-frequency image characteristics of the signal as input to the artificial neural network to identify the signal features, which takes a long time to compute in the time-frequency transformation process. In order to solve the above problems, this paper proposes a time-frequency feature preprocessing method of radiation source signals based on low-order cyclic statistics and CWD time-frequency analysis.…”