Skip to main navigation Skip to search Skip to main content

FMCW radar and inertial sensing synergy for assisted living

  • Haobo Li
  • , Aman Shrestha
  • , Francesco Fioranelli (Lead / Corresponding author)
  • , Julien Le Kernec
  • , Hadi Heidari

Research output: Contribution to journalArticlepeer-review

Abstract

This study presents preliminary results about the multi-sensory recognition of indoor daily activities and fall detection,to monitor the well-being of older people at risk of physical and cognitive chronic health conditions. Five different sensors,continuous wave (CW) radar, frequency-modulated CW (FMCW) radar, and inertial measurement unit comprising anaccelerometer, gyroscope, and magnetometer were used to simultaneously collect data from 20 subjects performing 10activities. Rather than using all of the available sensors, it is more efficient and economical to select part of them to maximisethe classification accuracy and avoid unnecessary computation to process information if it is not salient. Each individual sensorand several sensor combinations are trained with a quadratic-kernel support vector machine classifier. In addition, they arevalidated with an improved statistical approach, which uses data from unknown participants to test model rather than randomcross-validation to verify if the model generalises well for unknown subjects. Furthermore, the most suitable sensorcombinations are derived for each specific group of tested subjects selected (e.g. the oldest, youngest, tallest, and shortest sub-groups of participants out of the entire group)
Original languageEnglish
Pages (from-to)6784-6789
Number of pages6
JournalThe Journal of Engineering
Volume2019
Issue number20
DOIs
Publication statusPublished - 26 Sept 2019
EventIET International Radar Conference 2018 - Hilton Nanjing Riverside, Nanjing, China
Duration: 17 Oct 201819 Oct 2018

Fingerprint

Dive into the research topics of 'FMCW radar and inertial sensing synergy for assisted living'. Together they form a unique fingerprint.

Cite this