Localizing and Tracking the Transmitter Bionanosensor in Mobile Molecular Communication by Deep Learning

Abstract

Mobile molecular communication (MMC) system has been widely used in the field of medical drug delivery, disease detection, and target tracking. Considering the MMC system with one mobile transmitter and multiple fixed receivers that are bionanosensors, it is of great significance to localize and track the mobile transmitter in this MMC system. The existing work mainly focused on the deep neural network (DNN), which was utilized to locate the position of the receiver in static molecular communication (MC). In this article, we consider using the Transformer-based model to predict the position of the transmitter in a 2-D unbounded MMC environment by capturing the time series of the number of molecules in each time slot at multiple receivers. The simulation results show that the Transformer-based model performs better than the DNN-based model in localizing the transmitter. When the time slot is smaller, we find that the model can approximately track the trajectory of the transmitter. In addition, we also demonstrate the factors that affect the performance of localizing and tracking the transmitter by using the model.