Discrimination of RF Harmonics Using Classification Restricted Boltzmann Machine

Abstract

This paper proposes a new detection scheme for concealed micro-electronic devices by analyzing harmonic waves which are reflected from targets with classification restricted Boltzmann machine algorithm (Class/RBM). This new method exploits the characteristics of the second and the third harmonics waves to classify metal and electronic devices, as is done in all other Pdetection schemes. Moreover the details of RBMs with different training objectives which include generative RBM, discriminative RBM, and hybrid RBM have been discussed. The simulation results indicate that these proposed RBM models can discriminate the electronic devices and metal devices with efficiency in various learning environments. © 2016 IEEE.