Neural Network based Distance Estimation for Branched Molecular Communication Systems

2025-10-22

Proceedings of the 12th Annual ACM International Conference on Nanoscale Computing and Communication

AI Summary

Accurate estimation of molecular propagation distance remains a critical challenge in branched molecular communication systems due to the complexity and heterogeneity of biological media, hindering reliable channel parameter identification. Method: This work pioneers the application of recurrent neural networks (RNNs) to distance inversion in branched molecular channels. Leveraging a macroscopic molecular communication simulator, we generate time-series molecular concentration signals and design an end-to-end RNN model that directly infers propagation distance from received concentration sequences. Contribution/Results: Compared with physics-based or shallow-learning approaches, our deep learning framework achieves significantly improved accuracy and robustness in non-uniform biological environments. Experimental evaluations across diverse branching topologies and noise conditions demonstrate consistently high estimation fidelity. The proposed data-driven, scalable channel sensing paradigm advances practical deployment of bio-nano IoT and targeted drug delivery systems.

Technology Category

• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

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.

Problem

• Estimating communication channel parameters in molecular communication systems
• Developing neural network algorithms for branched topology environments
• Improving distance estimation accuracy for biomedical applications

Innovation

• RNN-based algorithms estimate MC channel parameters
• Deep Learning models enhance branched topology distance estimation
• Macroscopic simulation validates neural network performance in MC