Abstract
A low probability of intercept (LPI) communication system based on structured radio beams using machine learning is proposed. Information symbols can be physically encrypted on the structured radio beam realized by superposition of plane spiral orbital angular momentum (PS-OAM) modes. Performance of decryptor based on support vector machine (SVM) is analyzed. The accuracy achieves higher than 99.5%, which is much better than the interceptor based on k-means. The influence of the deflection angle, number of receiver array elements and the time delay of interceptor are further analyzed. Simulation results shows that the LPI scheme can achieve security communication within practical SNR range.
Highlights
Orbital angular momentum (OAM) describes the beam vorticity of the electromagnetic wave by exp(−jlφ), where l denotes different OAM modes, and all its integer values constitute a complete set of eigen-modes for electromagnetic wave in azimuthal domain
We propose a low probability of intercept (LPI) communication scheme based on structured radio beams using machine learning methods
Message of ‘‘0010-1100’’ is successively mapped into L0010 = {1, 3, 4, 5, 6, 7, 8} and L1100 = {2, 4, 6, 7, 8}, where Lsymbol represents the group of plane spiral OAM (PS-OAM) modes corresponding to the symbol selected
Summary
Orbital angular momentum (OAM) describes the beam vorticity of the electromagnetic wave by exp(−jlφ), where l denotes different OAM modes, and all its integer values constitute a complete set of eigen-modes for electromagnetic wave in azimuthal domain. As for structured radio beams, beam scanning can be realized by adjusting the initial phase difference of each grouping mode, during which the beam pattern remains constant [6]. By grouping different PS-OAM modes, radio beams carrying rich structured information can be subtly controlled [7]. We propose a low probability of intercept (LPI) communication scheme based on structured radio beams using machine learning methods. Due to the diversity of intensity and phase distribution in the mainlobe of structured radio beams, elaborately designed groups of PS-OAM modes can be regarded as a promising encryption scheme for LPI communication. To avoid using groups with similar beam patterns, the modes selection scheme based on Euclidean distance between sampled signal is carried out to obtain the low conflict modes grouping vocabulary. The generated structured radio beam (φ) can be controlled and scanned by adjusting the initial phases φ0 of different mode components
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call