Machine Learning-Based Silent Entity Localization Using Molecular Diffusion

Oyku Deniz Kose, Mustafa Can Gursoy, Murat Saraclar, Ali E. Pusane, Tuna Tugcu

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

Molecular communications has recently emerged as a new form of information transfer that uses chemical signals as information carriers. Alongside their novel applications in communications theory, chemical signals may also be utilized for various other applications, such as abnormality detection, direction finding, and entity localization. Among localization tasks, current literature mainly focuses on locating active entities that emanate chemicals, whereas the localization of a silent entity (e.g., an eavesdropper) is rarely considered. Exploiting the fact that different positions of a silent entity yields different received signals at the sensing device, this letter introduces a machine learning-based approach to detect the presence of a silent entity and localize it. Overall, the study shows that such a localization task is also achievable in cases where a clear analytical formula characterizing the received signal is not available, and provides a framework for further research on silent entity localization approaches.

Original languageEnglish (US)
Article number8964317
Pages (from-to)807-810
Number of pages4
JournalIEEE Communications Letters
Volume24
Issue number4
DOIs
StatePublished - Apr 2020
Externally publishedYes

Keywords

  • Eavesdropper
  • Localization
  • Machine learning
  • Molecular communication via diffusion
  • Silent entity

ASJC Scopus subject areas

  • Modeling and Simulation
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Machine Learning-Based Silent Entity Localization Using Molecular Diffusion'. Together they form a unique fingerprint.

  • Cite this