# Deep Learning for Cross-Technology Communication Design

## TL;DR

This paper introduces DeepCTC, a deep learning autoencoder approach for efficient cross-technology communication in OFDM systems, enabling simultaneous in-technology and CTC transmissions with flexible weighting and heterogeneous receiver support.

## Contribution

It presents a novel DL-based autoencoder design for joint optimization of in-technology and CTC communication, outperforming classical methods in flexibility and efficiency.

## Key findings

- Successful decoding of in-technology and CTC messages with low error rates
- Supports heterogeneous OFDM receivers in CTC broadcasts
- Demonstrates feasibility of deep learning for cross-technology communication

## Abstract

Recently, it was shown that a communication system could be represented as a deep learning (DL) autoencoder. Inspired by this idea, we target the problem of OFDM-based wireless cross-technology communication (CTC) where both in-technology and CTC transmissions take place simultaneously. We propose DeepCTC, a DL-based autoencoder approach allowing us to exploit DL for joint optimization of transmitter and receivers for both in-technology as well as CTC communication in an end-to-end manner. Different from classical CTC designs, we can easily weight in-technology against CTC communication. Moreover, CTC broadcasts can be efficiently realized even in the presence of heterogeneous CTC receivers with diverse OFDM technologies. Our numerical analysis confirms the feasibility of DeepCTC as both in-technology and CTC messages can be decoded with sufficient low block error rate.