AEVB-Comm: An Intelligent CommunicationSystem based on AEVBs

TL;DR

This paper introduces a CNN-based Variational Autoencoder communication system that leverages a continuous latent space with adjustable hyperparameters, achieving improved performance over traditional methods under various noise conditions.

Contribution

It presents a novel CNN-based VAE system with a beta hyperparameter for disentangled latent space and higher-dimensional representation, enhancing communication performance.

Findings

Reduced Block Error Rate (BLER) in simulations

Effective operation under AWGN and Rayleigh fading channels

Superior performance compared to traditional autoencoder systems

Abstract

In recent years, applying Deep Learning (DL) techniques emerged as a common practice in the communication system, demonstrating promising results. The present paper proposes a new Convolutional Neural Network (CNN) based Variational Autoencoder (VAE) communication system. The VAE (continuous latent space) based communication systems confer unprecedented improvement in the system performance compared to AE (distributed latent space) and other traditional methods. We have introduced an adjustable hyperparameter beta in the proposed VAE, which is also known as beta-VAE, resulting in extremely disentangled latent space representation. Furthermore, a higher-dimensional representation of latent space is employed, such as 4n dimension instead of 2n, reducing the Block Error Rate (BLER). The proposed system can operate under Additive Wide Gaussian Noise (AWGN) and Rayleigh fading channels. The CNN based VAE architecture performs the encoding and modulation at the transmitter, whereas decoding and demodulation at the receiver. Finally, to prove that a continuous latent space-based system designated VAE performs better than the other, various simulation results supporting the same has been conferred under normal and noisy conditions.