Stratified Transfer Learning for Cross-domain Activity Recognition
Preprint
Abstract
In activity recognition, it is often expensive and time-consuming to acquire sufficient activity labels. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labels. Existing approaches typically consider learning a global domain shift while ignoring the intra-affinity between classes, which will hinder the performance of the algorithms. In this paper, we propose a novel and general cross-domain learning framework that can exploit the intra-affinity of classes to perform intra-class knowledge transfer. The proposed framework, referred to as Stratified Transfer Learning (STL), can dramatically improve the classification accuracy for cross-domain activity recognition. Specifically, STL first obtains pseudo labels for the target domain via majority voting technique. Then, it performs intra-class knowledge transfer iteratively to transform both domains into the same subspaces. Finally, the labels of target domain are obtained via the second annotation. To evaluate the performance of STL, we conduct comprehensive experiments on three large public activity recognition datasets~(i.e. OPPORTUNITY, PAMAP2, and UCI DSADS), which demonstrates that STL significantly outperforms other state-of-the-art methods w.r.t. classification accuracy (improvement of 7.68%). Furthermore, we extensively investigate the performance of STL across different degrees of similarities and activity levels between domains. And we also discuss the potential of STL in other pervasive computing applications to provide empirical experience for future research.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Deep learning for sensor-based activity recognition: A surveyPattern Recognition Letters, 2019
- OKRELM: online kernelized and regularized extreme learning machine for wearable-based activity recognitionInternational Journal of Machine Learning and Cybernetics, 2017
- Collegial activity learning between heterogeneous sensorsKnowledge and Information Systems, 2017
- A solution to the single-question crowd wisdom problemNature, 2017
- Cross-Domain Recognition by Identifying Joint Subspaces of Source Domain and Target DomainIEEE Transactions on Cybernetics, 2016
- The Opportunity challenge: A benchmark database for on-body sensor-based activity recognitionPattern Recognition Letters, 2013
- Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor UnitsThe Computer Journal, 2013
- Transfer learning for activity recognition: a surveyKnowledge and Information Systems, 2013
- A Survey on Human Activity Recognition using Wearable SensorsIEEE Communications Surveys & Tutorials, 2012
- Geodesic flow kernel for unsupervised domain adaptation2012