Atypical Sample Regularizer Autoencoder for Cross-Domain Human Activity Recognition

Aria Ghora Prabono, Bernardo Nugroho Yahya () and Seok-Lyong Lee
Additional contact information
Aria Ghora Prabono: Hankuk University of Foreign Studies
Bernardo Nugroho Yahya: Hankuk University of Foreign Studies
Seok-Lyong Lee: Hankuk University of Foreign Studies

Information Systems Frontiers, No 0, 10 pages

Abstract: Abstract The sensor-based human activity recognition (HAR) using machine learning requires a sufficiently large amount of annotated data to realize an accurate classification model. This requirement stimulates the advancement of the transfer learning research area that minimizes the use of labeled data by transferring knowledge from the existing activity recognition domain. Existing approaches transform the data into a common subspace between domains which theoretically loses information, to begin with. Besides, they are based on the linear projection which is bound to linearity assumption and its limitations. Some recent works have already incorporated nonlinearity to find a latent representation that minimizes domain discrepancy based on an autoencoder that includes statistical distance minimization. However, such approach discovers latent representation for both domains at once, which causes sub-optimal representation because both domains compensate each other’s reconstruction error during the training. We propose an autoencoder-based approach on domain adaptation for sensor-based HAR. The proposed approach learns a latent representation which minimizes the discrepancy between domains by reducing statistical distance. Instead of learning representation of both domains simultaneously, our method is a two-phase approach which first learns the representation for the domain of interest independently to ensure its optimality. Subsequently, the useful information from the existing domain is transferred. We test our approach on the publicly available sensor-based HAR datasets, using cross-domain setup. The experimental result shows that our approach significantly outperforms the existing ones.

Keywords: Transfer learning; Autoencoder; Human activity recognition; Machine learning (search for similar items in EconPapers)
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10796-020-09992-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:infosf:v::y::i::d:10.1007_s10796-020-09992-5

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10796

DOI: 10.1007/s10796-020-09992-5

Access Statistics for this article

Information Systems Frontiers is currently edited by Ram Ramesh and Raghav Rao

More articles in Information Systems Frontiers from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().