The Use of Transfer Learning for Activity Recognition in Instances of Heterogeneous Sensing

Netzahualcoyotl Hernandez-Cruz, Chris Nugent, Shuai Zhang, Ian Mcchesney

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
121 Downloads (Pure)


Transfer learning is a growing field that can address the variability of activity recognition problems by reusing the knowledge from previous experiences to recognise activities from different conditions, resulting in the leveraging of resources such as training and labelling efforts. Although integrating ubiquitous sensing technology and transfer learning seem promising, there are some research opportunities that, if addressed, could accelerate the development of activity recognition. This paper presents TL-FmRADLs; a framework that converges the feature fusion strategy with a teacher/learner approach over the active learning technique to automatise the self-training process of the learner models. Evaluation TL-FmRADLs is conducted over InSync; an open access dataset introduced for the first time in this paper. Results show promising effects towards mitigating the insufficiency of labelled data available by enabling the learner model to outperform the teacher’s performance.
Original languageEnglish
Article number7660
Pages (from-to)e7660
Number of pages28
JournalApplied Sciences
Issue number16
Early online date20 Aug 2021
Publication statusPublished (in print/issue) - Aug 2021


  • Transfer learning
  • teacher/learner
  • activity recognition
  • machine-learning
  • transfer learning
  • Teacher/learner
  • Activity recognition
  • Machine-learning


Dive into the research topics of 'The Use of Transfer Learning for Activity Recognition in Instances of Heterogeneous Sensing'. Together they form a unique fingerprint.

Cite this