Literature Database Entry

li2023explainability

Xin Li, "Explainability of NN-based Detectors in MIMO Molecular Channels," Master's Thesis, School of Electrical Engineering and Computer Science (EECS), TU Berlin (TUB), July 2023. (Advisor: Jorge Torres Gómez; Referees: Falko Dressler and Thomas Sikora)

Abstract

The molecular communication (MC) is an emerging field in communication engineering that utilizes molecules to convey information. MC systems has great research value and application potential in various fields, such as biotechnological sensing, medical treatment, and industrial monitoring. A fundamental requirement in the design of MC systems is the accurate detection of different types of incoming symbols with the lowest bit error rate (BER). Recent studies in MC have proposed the use of machine learning (ML) models for symbol detection, which can overcome the difficulty of evaluating the end-to-end channel models and significantly reducing the BER. However, ML models often lack transparency, as they operate as black boxes to detect incoming symbols without providing proof of correctness of the underlying neural network (NN). Blindly relying on the prediction results without fully understanding the underlying principles can lead to severe consequences. This thesis aims to apply methods of explainable artificial intelligence (XAI) to explore approaches to the explainability of NN-based symbol detectors in MC channels. Through the development of MC models and the generation of synthesized data in MATLAB, a NN model is trained for the detection of 2-bit binary symbols in a 2x2 multiple-input multiple-output (MIMO) MC channel. Subsequently, the XAI methods, such as the local interpretable model-agnostic explanation (LIME), the partial dependence plot (PDP) and the individual conditional expectation (ICE) plot are employed to analyze the behavior of the trained NN. The results in this thesis provide evidence that the trained NN is operating as threshold detectors for the four types of symbols. Based on the varying numbers of molecules received by the receivers, the transmitted information is decoded into corresponding symbols.

Quick access

BibTeX BibTeX

Contact

Xin Li

BibTeX reference

@phdthesis{li2023explainability,
    author = {Li, Xin},
    title = {{Explainability of NN-based Detectors in MIMO Molecular Channels}},
    advisor = {Torres G{\'{o}}mez, Jorge},
    institution = {School of Electrical Engineering and Computer Science (EECS)},
    location = {Berlin, Germany},
    month = {7},
    referee = {Dressler, Falko and Sikora, Thomas},
    school = {TU Berlin (TUB)},
    type = {Master's Thesis},
    year = {2023},
   }
   
   

Copyright notice

Links to final or draft versions of papers are presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or distributed for commercial purposes without the explicit permission of the copyright holder.

The following applies to all papers listed above that have IEEE copyrights: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The following applies to all papers listed above that are in submission to IEEE conference/workshop proceedings or journals: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

The following applies to all papers listed above that have ACM copyrights: ACM COPYRIGHT NOTICE. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) 869-0481, or permissions@acm.org.

The following applies to all SpringerLink papers listed above that have Springer Science+Business Media copyrights: The original publication is available at www.springerlink.com.

This page was automatically generated using BibDB and bib2web.

Last modified: 2024-05-04