Explainability of Neural Networks for Symbol Detection in Molecular Communication Channels

Recent molecular communication (MC) research suggests machine learning (ML) models for symbol detection, avoiding the unfeasibility of end-to-end channel models. However, ML models are applied as black boxes, lacking proof of correctness of the underlying neural networks (NNs) to detect incoming sym...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on molecular, biological, and multi-scale communications Vol. 9; no. 3; p. 1
Main Authors Gomez, Jorge Torres, Hofmann, Pit, Fitzek, Frank H.P., Dressler, Falko
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Channel models
Channels
Detectors
Explainable AI
individual conditional expectation
local interpretable model-agnostic explanation
Machine learning
Mathematical models
molecular communication
neural network
Neural networks
Receivers
Symbols
testbed
Online AccessGet full text

Cover

More Information
Summary:Recent molecular communication (MC) research suggests machine learning (ML) models for symbol detection, avoiding the unfeasibility of end-to-end channel models. However, ML models are applied as black boxes, lacking proof of correctness of the underlying neural networks (NNs) to detect incoming symbols. This paper studies approaches to the explainability of NNs for symbol detection in MC channels. Based on MC channel models and real testbed measurements, we generate synthesized data and train a NN model to detect of binary transmissions in MC channels. Using the local interpretable model-agnostic explanation (LIME) method and the individual conditional expectation (ICE), the findings in this paper demonstrate the analogy between the trained NN and the standard peak and slope detectors.
ISSN:2372-2061
2372-2061
DOI:10.1109/TMBMC.2023.3297135