Neural Network based Distance Estimation for Branched Molecular Communication Systems

TL;DR

This paper introduces RNN-based algorithms for estimating channel parameters in molecular communication systems with branched topologies, demonstrating strong performance and potential for biomedical and IoBNT applications.

Contribution

The paper presents novel RNN architectures specifically designed for distance estimation in branched molecular communication channels, a previously underexplored topology.

Findings

Deep learning models outperform traditional methods in distance estimation accuracy.

RNN architectures show robustness in simulated branched MC environments.

Potential for application in biomedical and IoBNT systems is demonstrated.

Abstract

Molecular Communications (MC) is an emerging research paradigm that utilizes molecules to transmit information, with promising applications in biomedicine such as targeted drug delivery or tumor detection. It is also envisioned as a key enabler of the Internet of BioNanoThings (IoBNT). In this paper, we propose algorithms based on Recurrent Neural Networks (RNN) for the estimation of communication channel parameters in MC systems. We focus on a simple branched topology, simulating the molecule movement with a macroscopic MC simulator. The Deep Learning architectures proposed for distance estimation demonstrate strong performance within these branched environments, highlighting their potential for future MC applications.