CoChat

Real-Time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices

Open access
Cheng, Xin, Zhang, Lei, Tang, Yin, Liu, Yue, Wu, Hao, He, Jun · 2022 · IEEE Sensors Journal
Cited by 82

The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.

Abstract

Recently, deep learning has represented an important research trend in human activity recognition (HAR). In particular, deep convolutional neural networks (CNNs) have achieved state-of-the-art performance on various HAR datasets. For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations. A high number of operations in deep leaning increases computational cost and is not suitable for real-time HAR using mobile and wearable sensors. Though shallow learning techniques often are lightweight, they could not achieve good performance. Therefore, deep learning methods that can balance the trade-off between accuracy and computation cost is highly needed, which to our knowledge has seldom been researched. In this paper, we for the first time propose a computation efficient CNN using conditionally parametrized convolution for real-time HAR on mobile and wearable devices. We evaluate the proposed method on four public benchmark HAR datasets consisting of WISDM dataset, PAMAP2 dataset, UNIMIB-SHAR dataset, and OPPORTUNITY dataset, achieving state-of-the-art accuracy without compromising computation cost. Various ablation experiments are performed to show how such a network with large capacity is clearly preferable to baseline while requiring a similar amount of operations. The method can be used as a drop-in replacement for the existing deep HAR architectures and easily deployed onto mobile and wearable devices for real-time HAR applications.

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.2022.3149337

Cites

23 of 23 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 23 references

Research works printed but not linked: 30

  1. 10.1007/978-3-642-35395-6_30 · DOI · Paper page
  2. Yang, Deep convolutional neural networks on multichannel time series for human activity recognition
  3. Simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556 · arXiv
  4. Yu, 2018, Slimmable neural networks, arXiv:1812.08928 · arXiv
  5. Howard, 2017, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv:1704.04861 · arXiv
  6. 10.3390/s140406474 · DOI · Paper page
  7. Cho, 2014, Exponentially increasing the capacity-to-computation ratio for conditional computation in deep learning, arXiv:1406.7362 · arXiv
  8. Yang, CondConv: Conditionally parameterized convolutions for efficient inference, 1305
  9. 10.1109/JSEN.2019.2917225 · DOI · Paper page
  10. Andrey, 2017, Real-time human activity recognition from accelerometer data using convolutional neural networks, Appl. Soft Comput., 62, 915
  11. 10.1109/JSEN.2020.2978772 · DOI · Paper page
  12. 10.1109/TETCI.2021.3079966 · DOI
  13. 10.1109/ACCESS.2020.2981370 · DOI
  14. 10.1145/3005348 · DOI · Paper page
  15. 10.1109/CVPR.2019.00289 · DOI · Paper page
  16. Jin, 2019, Towards efficient training for neural network quantization, arXiv:1912.10207 · arXiv
  17. 10.1109/CVPR.2019.00748 · DOI · Paper page
  18. 10.48550/arXiv.1503.02531 · DOI · Paper page
  19. 10.1109/CVPR.2018.00843 · DOI
  20. Ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv:1502.03167 · arXiv
  21. Glorot, Deep sparse rectifier neural networks, 315
  22. 10.1109/CVPR.2019.00279 · DOI · Paper page
  23. 10.1145/3377882 · DOI
  24. 10.1109/ACCESS.2018.2873315 · DOI · Paper page
  25. 10.1007/s11036-019-01445-x · DOI · Paper page
  26. 10.24963/ijcai.2019/186 · DOI · Paper page
  27. 10.3390/info10060203 · DOI · Paper page
  28. 10.1007/s00521-018-03973-1 · DOI
  29. 10.1145/3410530.3414364 · DOI
  30. 10.1007/978-3-319-66808-6_18 · DOI · Paper page

Cited by

See all 82

Metadata

Authors
Cheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H., & He, J.
Venue
IEEE Sensors Journal
Published
2022-03-15
Volume
22
Issue
6
Pages
5889-5901
ISSN
  • 1530-437X (ISSN-L)
  • 1558-1748
  • 2379-9153
OpenAlex
W3033847194
Cited by
82
References
23
FWCI
5.83
Type
journal article
Language
en
Open access
green
Funders
  • National Nature Science Foundation of China (61962061)
  • Industry-Academia Cooperation Innovation Fund Projection of Jiangsu Province (BY2016001-02)
  • Natural Science Foundation of Jiangsu Province (BK20191371)

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: Real-Time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices. https://app.cochat.ai/papers/10.1109/jsen.2022.3149337
The paper
Cheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H., & He, J. (2022). Real-Time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices. IEEE Sensors Journal. https://doi.org/10.1109/jsen.2022.3149337

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.