Elderly Care: Using Deep Learning for Multi-Domain Activity Classification

Shaoxuan Li , Mu Jia, Julien Le Kernec, Shufan Yang, Francesco Fioranelli, Olivier Romain

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

6 Downloads (Pure)


Nowadays, health monitoring issues are increasing as the worldwide population is aging. In this paper, the radar modality is used to classify with radar signature automatically. The classic approach is to extract features from micro-Doppler signatures for classification. This data representation domain has its limitations for activities presenting similar accelerations like a frontal fall and picking up an object from the floor that lead to wrongly labeled activities. In this work, we propose to combine multiple radar data domains with deep learning. Features are extracted from four domains, namely, Range-Time, Range-Doppler, Doppler-Time, and Cadence Velocity Diagram. The extracted features are set as the input of a Convolutional Neural Network, yielding 91% accuracy with 10-fold cross-validation based on the University of Glasgow “Radar signatures of human activities” open dataset.
Original languageEnglish
Title of host publication2020 International Conference on UK-China Emerging Technologies (UCET)
Number of pages4
ISBN (Electronic)978-1-7281-9488-2
ISBN (Print)978-1-7281-9489-9
Publication statusPublished - 2020
EventUCET 2020 : International Conference on UK-China Emerging Technologies (UCET) - Glasgow, United Kingdom
Duration: 20 Aug 202021 Aug 2020


ConferenceUCET 2020
CountryUnited Kingdom


  • Machine Learning
  • Radar
  • Assisted Living
  • Human Activity Recognition
  • Multi-domain

Fingerprint Dive into the research topics of 'Elderly Care: Using Deep Learning for Multi-Domain Activity Classification'. Together they form a unique fingerprint.

Cite this