An Electromagnetic Signal Spectrum Sensing Method Based on Deep Clustering Network

Abstract

The invention discloses an electromagnetic signal spectrum sensing method based on a deep clustering network, comprising the following steps: S1, sorting and locating samples according to input signals, and performing regular processing on radiation source signals; The class network clusters the input radiation source signals; S3, using the clustered radiation source signals, combined with the input positioning results, using the target tracking algorithm to realize the front and back correlation of signals at multiple times, and form the trajectory of the electronic target; S4 1. According to the movement trajectory of electronic targets, analyze the movement rules among multiple electronic targets, use the set update algorithm and platform assignment algorithm to carry out platform aggregation, and discover potential target platforms; the invention inputs the sorted and positioned signals samples, the system will automatically distinguish signals from different devices, and based on the device information, the subsequent work of electronic target association and platform aggregation can be carried out.

Description

technical field [0001] The invention relates to the technical field of electromagnetic signal identification, in particular to an electromagnetic signal spectrum sensing method based on a deep clustering network. Background technique [0002] Electromagnetic signal spectrum sensing is a key research direction in the field of electronic countermeasures. In modern information warfare, only by correctly analyzing the situation of the enemy's radar signals can we take corresponding countermeasures in a timely manner and give full play to the effectiveness of our weapons and troops. [0003] In the equipment identification based on the radiation source signal, the traditional identification algorithm relies on the radar knowledge base maintained manually. After the signal is captured, it is compared with the radar signal in the knowledge base one by one. However, such methods still rely to a certain extent on human intervention. And can't do anything about the emerging radar si...

AI Technical Summary

Problems solved by technology

However, when the dimensionality of the input signal increases, calculating the distance on the sparse high-dimensional features will lead to the loss of information, so an additional feature selection process or dimensionality reduction is required.

However, the process of classical clustering is discrete and cannot be optimized together with the input coding part, which also leads to poor performance of the algorithm.

Images