A machine learning algorithm for interference removal from a signal

Abstract

Wireless Communication systems involve multiple transmission of signals from one place to another through a transmission medium. These signals may interfere with each other and cause loss of information, thus reducing the efficiency of these systems. This interference needs to be taken care of for developing reliable wireless communication systems. In this paper, we have dealt with this problem by using a two-staged machine learning algorithm over a real time signal for removing multiple interference with a minimal information loss. It is based on the working of the notch filter which is used to remove a single narrow band interference from a signal. The algorithm was simulated over a Binary Phase Shift Keying (BPSK) modulated signal with a number of continuous wave (CW) interference. Based on the results obtained, signal power loss and notch characteristics were analysed for optimal performance of the algorithm. © 2015 IEEE.