CoChat

Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition

Open access
Wang, Jinqiang, Zhu, Tao, Gan, Jingyuan, Chen, Liming Luke, Ning, Huansheng, Wan, Yaping · 2022 · IEEE Sensors Journal
Cited by 76

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

While deep learning models have contributed to the advancement of sensor-based human activity recognition (HAR), it usually requires large amounts of annotated sensor data to extract robust features. To alleviate the limitations of data annotation, contrastive learning has been applied to sensor-based HAR. One of the essential factors of contrastive learning is data augmentation, significantly impacting the performance of pretraining. However, current popular augmentation methods do not achieve competitive performance in contrastive learning for sensor-based HAR. Motivated by this issue, we propose a new sensor data augmentation method by resampling, which introduces variable domain information and simulates realistic activity data by varying the sampling frequency to maximize the coverage of the sampling space. The resampling augmentation method was evaluated in supervised learning and contrastive learning [SimCLR for HAR (SimCLRHAR) and MoCo for HAR (MoCoHAR)]. In the experiment, we use four datasets, UCI-HAR, MotionSense, USC-HAD, and MobiAct, using the mean F1-score as the evaluation metric for downstream tasks. The experimental results show that the resampling data augmentation outperforms all state-of-the-art augmentation methods in supervised learning and contrastive learning with a small amount of labeled data. The results also demonstrate that not all data augmentation methods have positive effects in contrastive learning frameworks.

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/jsen.2022.3214198

Cites

24 of 24 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

Show all 24 references

Research works printed but not linked: 28

  1. abadi, 2016, TensorFlow: Large-scale machine learning on heterogeneous distributed systems, arXiv 1603 04467
  2. 10.1109/JSEN.2020.3015521 · DOI · Paper page
  3. um, 2017, Data augmentation of wearable sensor data for Parkinson’s disease monitoring using convolutional neural networks, Proc 19th ACM Int Conf Multimodal Interact, 216
  4. 10.1109/DCOSS52077.2021.00019 · DOI
  5. sohn, 2016, Improved deep metric learning with multi-class N-pair loss objective, Proc Adv Neural Inf Process Syst, 1857
  6. 10.1016/j.artint.2020.103429 · DOI
  7. 10.1016/j.aei.2019.100944 · DOI · Paper page
  8. 10.1109/LSENS.2018.2878572 · DOI · Paper page
  9. 10.1109/ICSESS49938.2020.9237720 · DOI
  10. 10.3390/technologies9010002 · DOI · Paper page
  11. falcon, 2020, A framework for contrastive self-supervised learning and designing a new approach, arXiv 2009 00104
  12. bachman, 2019, Learning representations by maximizing mutual information across views, arXiv 1906 00910
  13. anguita, 2013, A public domain dataset for human activity recognition using smartphones, Proc ESANN, 3, 3
  14. 10.1109/JSEN.2019.2960926 · doi:10.1109/jsen.2019.2960926
  15. 10.1109/JIOT.2020.2985082 · DOI · Paper page
  16. 10.1109/JIOT.2020.3009358 · DOI · Paper page
  17. chen, 2021, Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities, ACM Comput Surv, 54, 1
  18. 10.1109/JSEN.2019.2956901 · DOI
  19. 10.1109/JSEN.2019.2936412 · DOI
  20. 10.1109/JSEN.2019.2897083 · DOI
  21. 10.1109/JSEN.2020.3028561 · DOI
  22. 10.1109/JSEN.2015.2475626 · DOI
  23. waring, 1779, VII. Problems concerning interpolations, Philos Trans Roy Soc London, 69, 59, 10.1098/rstl.1779.0008 · doi:10.1098/rstl.1779.0008
  24. 10.1109/CVPR42600.2020.00975 · DOI · Paper page
  25. chen, 2020, A simple framework for contrastive learning of visual representations, Proc 37th Int Conf Mach Learn, 1597
  26. woolson, 2007, Wilcoxon signed-rank test, Wiley Encyclopedia of Clinical Trials, 1
  27. mckinley, 1998, Cubic spline interpolation, College of the Redwoods, 45, 1049
  28. chen, 2020, Improved baselines with momentum contrastive learning, arXiv 2003 04297

Cited by

See all 76

Metadata

Authors
Wang, J., Zhu, T., Gan, J., Chen, L. L., Ning, H., & Wan, Y.
Venue
IEEE Sensors Journal
Published
2022-12-01
Volume
22
Issue
23
Pages
22994-23008
ISSN
  • 1530-437X (ISSN-L)
  • 1558-1748
  • 2379-9153
OpenAlex
W4286986228
Cited by
76
References
24
FWCI
5.42
Type
journal article
Language
en
Open access
green
Funders
National Natural Science Foundation of China (62006110, 61872038)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition. https://app.cochat.ai/papers/10.1109/jsen.2022.3214198
The paper
Wang, J., Zhu, T., Gan, J., Chen, L. L., Ning, H., & Wan, Y. (2022). Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition. IEEE Sensors Journal. https://doi.org/10.1109/jsen.2022.3214198

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.