Recognition of electromagnetic sources with the use of deep neural networks
Abstract
The article presents a method of recognizing sources of electromagnetic signal emission on the basis of signals generated by using deep neural networks. These signals are measured in electronic recognition receivers, processed into a digital signal and then undergo recognition. The main purpose of the article is to present software which, based on the detected signal, is to recognize it. The software can also be used as a subsystem in Electronic Intelligence (ELINT) devices, including detection of radiolocation systems, jammers, recognition of aircrafts, ships, vehicles based on the signal shape of radar cross section (RCS) and subsequently comparison them to the emitter database (EDB). The implementation of this system is presented in a simulation environment and with the help of a signal generator that has the ability to make changes in signal signatures earlier recognized, calculated and written in database. The proposed software allows to examine a significant number of different signals. The article contains a description of components of software, such as signal base, learning subsystem and signal generator. The results of the system operation are presented in the form of screenshots from individual software components. The speed of software operation, the effectiveness of recognition systems using artificial neural networks is presented by means of tables and appropriate illustrations. Also presented is the problem of learning the neural networks at the GPUs (graphics processing units) and the way of choice the learning coefficients.
- Publication:
-
XII Conference on Reconnaissance and Electronic Warfare Systems
- Pub Date:
- March 2019
- DOI:
- 10.1117/12.2524536
- Bibcode:
- 2019SPIE11055E..0DM