An efficient RBF‐DCNN based DOA estimation in multipath and impulse noise wireless environment

Abstract

The typical MultiPath (MP) propagation environment attains lots of MP signals as of the antenna array, and the Impulse Noise (IPN) accompanies these MP signals. The Directions‐of‐Arrivals (DOA) of an MP signal is tough to be assessed because of these IPN. Though numerous existing techniques were generated to assess the MP signal's DOA, they cannot attain a desirable output. To achieve robust and accurate DOA estimation (DOAE) in multipath and IPN wireless environment, this work proposes an efficient Radial Basis Function based Deep Convolutional Neural Network (RBF‐DCNN) centered DOAE. Here, initially, the noises in the inputted signal are eradicated utilizing Improved Particle Filter (IPF). After denoising, the imperative features are extracted as of that signal. Next, the required features are selected as of that signal, which is utilized for Dimension Reduction (DR). The Modified Salp Swarm Optimization Algorithm (MSSOA) is employed for feature selection. Then, the dimension reduced signal is inputted to the RBF‐DCNN, which estimated the DOA centered upon the received signal's SNR value. Numerical simulation outcomes are rendered to exemplify the proposed method's effectiveness.