CoChat

MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition With Multidomain Deep Learning Model

Open access
Pei, Ling, Xia, Songpengcheng, Chu, Lei, Xiao, Fanyi, Wu, Qi, Yu, Wenxian, Qiu, Robert · 2021 · IEEE Internet of Things Journal
Cited by 50

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

Together with the rapid development of the Internet of Things, human activity recognition (HAR) using wearable inertial measurement units (IMUs) becomes a promising technology for many research areas. Recently, deep-learning-based methods pave a new way of understanding and performing analysis of the complex data in the HAR system. However, the performance of these methods is mostly based on the quality and quantity of the collected data. In this article, we innovatively propose to build a large data set based on virtual IMUs and then address technical issues by introducing a multiple-domain deep learning framework consisting of three technical parts. In the first part, we propose to learn the single-frame human activity from the noisy IMU data with hybrid convolutional neural networks in the semisupervised form. For the second part, the extracted data features are fused according to the principle of uncertainty-aware consistency, which reduces the uncertainty by weighting the importance of the features. The transfer learning is performed in the last part based on the newly released archive of motion capture as surface shapes data set, containing abundant synthetic human poses, which enhances the variety and diversity of the training data set and is beneficial for the process of training and feature transfer in the proposed method. The efficiency and effectiveness of the proposed method have been demonstrated in the real deep inertial poser data set. The experimental results show that the proposed methods can surprisingly converge within a few iterations and outperform all competing methods.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jiot.2021.3055859

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 37

  1. parthasarathy, 2015, Gait analysis using virtual body sensor networks for biomedical applications, Int J Pharm Med Biol Sci, 4, 123
  2. 10.1109/JSEN.2011.2121059 · DOI · Paper page
  3. 10.1109/TKDE.2019.2891659 · DOI
  4. 10.1109/CVPR.2019.00049 · DOI · Paper page
  5. 10.1109/TPAMI.2018.2858821 · DOI · Paper page
  6. laine, 2017, Temporal ensembling for semi-supervised learning, Proc Int Conf Learn Represent (ICLR), 1
  7. 10.1109/JSEN.2018.2885796 · DOI · Paper page
  8. 10.1109/MPRV.2010.7 · DOI · Paper page
  9. 10.1023/A:1021709817809 · DOI · Paper page
  10. 10.1007/s10044-016-0570-y · DOI
  11. yang, 2015, Deep convolutional neural networks on multichannel time series for human activity recognition, Proc Int Joint Conf Artif Intell (IJCAI), 3995
  12. 10.4018/978-1-60566-766-9.ch011 · DOI · Paper page
  13. joze, 2020, MMTM: Multimodal transfer module for CNN fusion, Proc IEEE Conf Comput Vis and Pattern Recog, 13289
  14. liaw, 2002, Classification and regression by randomForest, R News, 2, 18
  15. zhuang, 2015, Supervised representation learning: Transfer learning with deep autoencoders, Proc 24th Int Joint Conf Artif Intell, 4119
  16. vincent, 2010, Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, J Mach Learn Res, 11, 3371
  17. 10.1109/JIOT.2019.2949715 · DOI · Paper page
  18. xiao, 2020, A deep learning method for complex human activity recognition using virtual wearable sensors, Proc ACM SpatialDI, 1
  19. 10.1109/JIOT.2019.2901927 · DOI
  20. bhanujyothi, 2017, A comparative study of random forest & K-nearest Neighbors on HAR dataset using caret, Proc IJIRT, 3, 6
  21. 10.1109/JSEN.2018.2830743 · DOI
  22. 10.3390/s120506155 · DOI
  23. ravi, 2005, Activity recognition from accelerometer data, Proc AAAI, 5, 1541
  24. 10.3390/s130201402 · DOI · Paper page
  25. 10.1109/JBHI.2013.2253613 · DOI · Paper page
  26. 10.1109/ACCESS.2018.2868792 · doi:10.1109/access.2018.2868792
  27. 10.1109/ACCESS.2018.2880454 · DOI · Paper page
  28. avci, 2010, Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey, Proc Int Conf Archit Comput Syst (ARCS), 1
  29. donini, 2018, Empirical risk minimization under fairness constraints, Proc Adv Neural Inf Process Syst, 2791
  30. 10.1109/JIOT.2016.2558659 · DOI · Paper page
  31. 10.1016/S0031-3203(02)00262-5 · DOI · Paper page
  32. tang, 2020, Rethinking 1D-CNN for time series classification A stronger baseline
  33. sugiyama, 2007, Covariate shift adaptation by importance weighted cross validation, J Mach Learn Res, 8, 985
  34. 10.4103/0256-4602.64604 · DOI · Paper page
  35. goodfellow, 2016, Deep Learning, 1
  36. 10.18653/v1/P19-2040 · DOI
  37. 10.1109/ASRU46091.2019.9003730 · DOI

Cited by

See all 50

Metadata

Authors
Pei, L., Xia, S., Chu, L., Xiao, F., Wu, Q., Yu, W., & Qiu, R.
Venue
IEEE Internet of Things Journal
Published
2021-06-01
Volume
8
Issue
11
Pages
9383-9396
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
OpenAlex
W3127033546
Cited by
50
References
19
FWCI
3.00
Type
journal article
Language
en
Open access
green
Funders
  • NSFC (61873163, 61871265)
  • International Postdoctoral Exchange Fellowship from the China Postdoctoral Council (20200053)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.