Assessment of Feature Selection for Context Awareness RF Sensing Systems

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Context awareness using Radio Frequency (RF) sensing systems has attracted increased attention due to its importance in future communication systems. In this work, we investigate the importance of multiple features in the classification of different RF human mobility scenarios. Considering a practical RF system operating in the 76-81 GHz band, we focus on different types of features computed from the RF time of flight. The importance of the features is then evaluated through its score computed with four methodologies: the Mutual Information (MI), the Analysis of Variance (ANOVA), the Recursive Feature Elimination (RFE), and the Feature Weighting algorithm (RelieF). The results indicate that the methodologies do not rank the multiple features coherently and some categories of features have lower importance. Moreover, when adopting a k-nearest Neighbor classifier the RFE methodology is shown to be advantageous as it achieves the highest accuracy with the smallest number of features.

Original languageEnglish
Title of host publication2022 IEEE 95th Vehicular Technology Conference
Subtitle of host publicationSpring, VTC 2022-Spring - Proceedings
Place of PublicationNew York
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)978-1-6654-8243-1
ISBN (Print)978-1-6654-8244-8
DOIs
Publication statusPublished - Jun 2022
Event95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring - Helsinki, Finland
Duration: 19 Jun 202222 Jun 2022

Publication series

NameIEEE Vehicular Technology Conference
PublisherIEEE
Volume2022-June
ISSN (Print)1550-2252
ISSN (Electronic)2577-2465

Conference

Conference95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring
Country/TerritoryFinland
CityHelsinki
Period19/06/2222/06/22

Keywords

  • Context Awareness
  • Feature Engineering
  • Machine Learning
  • RF Active Sensing

Fingerprint

Dive into the research topics of 'Assessment of Feature Selection for Context Awareness RF Sensing Systems'. Together they form a unique fingerprint.

Cite this