Explainable Asymmetric Auto-Encoder for End-to-End Learning of IoBNT Communications

The Internet of Bio-Nano Things (IoBNT) is envisioned to be a heterogeneous network of artificial and natural units that are connected to the Internet. Hence, it extends the connectivity and control to unconventional domains, such as the human body. A potential use case for IoBNT is the communication from the outside to the inside of the human body. In this scenario, typically the Receiver (RX) inside the human body has limited computational complexity, while the Transmitter (TX) outside has large computational resources. In this paper, we address this scenario and propose a novel Asymmetric Auto-Encoder (AAEC) architecture for end-to-end learning of a Molecular Communication (MC) system. It applies a Neural Network (NN) at the TX and a low-complexity slope detector at the RX. We discuss the different layers of the NN-based TX and the corresponding training approach. Moreover, we investigate the explainability of the NN-based TX and show through the use of meta modeling that it can be approximated by a linear model. In addition, we demonstrate that the proposed AAEC resembles an MC system with Zero Forcing (ZF) precoding for low and moderate Inter Symbol Interference (ISI). Finally, through numerical results, we confirmed the aforementioned findings and showed that the proposed AAEC outperforms MC systems with and without ZF precoding, especially in high ISI scenarios.