Deep Learning-Based Estimation of Emission Time and Arrival Time in Diffusive Multi-Receiver Molecular Communication

Diffusive molecular communication (DMC) utilizes the emission, diffusion and reception of molecules to transmit information. It has promising prospects in the field of drug delivery. The estimation of emission time and arrival time of molecules in DMC system plays important roles in the resource consumption at the receivers. Existing traditional strategies for the derivation of emission time and arrival time mainly focus on known channel state information (CSI). In this paper, we propose a deep learning method for estimating emission time and arrival time of the molecules in DMC system with unknown CSI by using Transformer-based model, respectively. The simulation results show that the emission time and arrival time of molecules can be accurately estimated by the Transformer-based model which exhibits better estimation and generalization abilities than deep neural network (DNN) model.