AEVBComm: an intelligent communication system based on \(\beta\)-VAE

In recent years, applying Deep Learning (DL) techniques has 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 \(\beta -\) $\beta -$ VAE in the proposed VAE, which is also known as \(\beta -\) $\beta -$ VAE, resulting in extremely disentangled latent space representation. Furthermore, a higher-dimensional representation of latent space is employed, reducing the Block Error Rate (BLER). 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 and 4n dimensional representation is better than 2n representation, various simulation results supporting both have been conferred under normal and noisy conditions.