Clustering Guided Residual Neural Networks for Multi-Tx Localization in Molecular Communications

2025-11-11

AI Summary

To address low localization accuracy of multiple molecular transmitters in diffusion-based molecular communication—primarily caused by the inherent stochasticity of molecular diffusion and overlapping concentration distributions at the receiver surface—this paper proposes a clustering-guided residual neural network framework. First, K-means clustering provides coarse transmitter location estimates; a centroid correction mechanism is then introduced to enhance the robustness of these initial estimates. Subsequently, a dual-branch neural network—AngleNN for directional refinement and SizeNN for cluster-scale modeling—is designed to mitigate distortions from non-uniform density distributions and outlier interference. The method synergistically integrates prior knowledge of molecular concentration distribution with deep learning–driven end-to-end localization optimization. Experiments demonstrate that, compared to conventional K-means, the proposed approach reduces localization error by 69% for two transmitters and by 43% for four transmitters, significantly improving both accuracy and robustness in multi-transmitter cooperative localization.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Clustering
• Search and Optimization: Distributed Search

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• 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

Abstract

Transmitter localization in Molecular Communication via Diffusion is a critical topic with many applications. However, accurate localization of multiple transmitters is a challenging problem due to the stochastic nature of diffusion and overlapping molecule distributions at the receiver surface. To address these issues, we introduce clustering-based centroid correction methods that enhance robustness against density variations, and outliers. In addition, we propose two clusteringguided Residual Neural Networks, namely AngleNN for direction refinement and SizeNN for cluster size estimation. Experimental results show that both approaches provide significant improvements with reducing localization error between 69% (2-Tx) and 43% (4-Tx) compared to the K-means.

Problem

• Addresses multi-transmitter localization challenges in molecular communication via diffusion
• Solves overlapping molecule distributions and diffusion stochasticity at receivers
• Improves localization accuracy through clustering-guided neural network approaches

Innovation

• Clustering-based centroid correction enhances robustness
• AngleNN refines transmitter direction estimation
• SizeNN estimates molecular cluster sizes accurately