Molecular Communications: Model-Based and Data-Driven Receiver Design and Optimization

Xuewen Qian (1) , Marco Di Renzo (1) , Andrew W. Eckford (2)

1 L2S - Laboratoire des signaux et systèmes
2 York University [Toronto]

In this paper, we consider a molecular communication system that is made of a 3D unboundeddiffusion channel model without flow, a point transmitter, and a spherical absorbing receiver. In particular,we study the impact of inter-symbol interference and analyze the performance of different threshold-basedreceiver schemes. The aim of this paper is to analyze and optimize the receivers by using the conventionalmodel-based approach, which relies on an accurate model of the system, and the emerging data-drivenapproach, which, on the other hand, does not need any apriori information about the system model andexploits deep learning tools. We develop a general analytical framework for analyzing the performanceof threshold-based receiver schemes, which are suitable to optimize the detection threshold. In addition,we show that data-driven receiver designs yield the same performance as receivers that have perfectknowledge of the underlaying channel model.

Domains: Computer Science [cs]; Information Theory [cs.IT]

Xuewen Qian, Marco Di Renzo, Andrew W. Eckford. Molecular Communications: Model-Based and Data-Driven Receiver Design and Optimization. IEEE Access, 2019, 7, pp.53555-53565. ⟨10.1109/ACCESS.2019.2912600⟩. ⟨hal-02376620⟩