CoChat

Deep Dilation on Multimodality Time Series for Human Activity Recognition

Open access
Xi, Rui, Li, Ming, Hou, Mengshu, Fu, Mingsheng, Qu, Hong, Liu, Daibo, Haruna, Charles R. · 2018 · IEEE Access
Cited by 35

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Providing accurate information on people's activities and behaviors plays an important role in innumerable applications, such as medical, security, and entertainment. In recent years, deep learning has been applied in human activity recognition, and achieved a better performance. However, if the spatial dependency of inter-sensors is considered, it is possible to enhance the discriminative ability. In this paper, we present a novel deep learning framework for human activity recognition problems. First, on the basis of our previous work, we utilize dilated convolutional neural network to extract features of inter-sensors and intra-sensors. Since the extracted features are local and short-temporal, it is necessary to utilize RNN to model the long-temporal dependencies. However, duo to that LSTM and GRU often rely on the completely previous computations, it will result in slow inference and hard convergence. Hence, inspired by the idea of dilation operation, we present a novel recurrent model to learn the temporal dependencies at different time scales. Then, at the topmost layer, a fully-connected layer with softmax function is utilized to generate a class probability distribution, and the predicted activity is obtained. Eventually, we evaluate the proposed framework in two open human activity datasets, OPPORTUNITY and PAMAP2. Results demonstrate that the proposed framework achieves a higher classification performance than the state-of-the-art methods. Moreover, it takes the least time to recognize an activity. Besides, it also performs faster and easier to converge in the training stage.

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/access.2018.2870841

Cites

13 of 13 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 13 references

Research works printed but not linked: 26

  1. hammerla, 2016, Deep convolutional and recurrent models for human activity recognition using wearables
  2. lecun, 1998, Efficient backprop, Neural Networks, 9
  3. 10.1109/ICCVW.2017.37 · DOI
  4. van den oord, 2016, WaveNet A Generative Model for Raw Audio
  5. lei, 2017, Training RNNs as fast as CNNs
  6. abadi, 2016, Tensorflow Large-scale machine learning on heterogeneous distributed systems
  7. xi, 2018, Deep dilated convolution on multimodality time series for human activity recognition, Proc Int Joint Conf Neural Netw
  8. xu, 2012, Robust human activity and sensor location corecognition via sparse signal representation, IEEE Trans Biomed Eng, 59, 3169, 10.1109/TBME.2012.2211355 · DOI · Paper page
  9. 10.1145/1107548.1107591 · DOI · Paper page
  10. xu, 2016, Wearable sensor-based human activity recognition method with multi-features extracted from Hilbert–Huang transform, SENSORS, 16, 2048, 10.3390/s16122048 · DOI
  11. 10.1145/882085.882086 · doi:10.1145/882085.882086 · Paper page
  12. lin, 2013, Network in Network
  13. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  14. 10.1109/78.157290 · DOI · Paper page
  15. anguita, 2013, A public domain dataset for human activity recognition using smartphones, Proc ESANN
  16. yu, 2015, Multi-scale context aggregation by dilated convolutions
  17. yang, 2015, Deep convolutional neural networks on multichannel time series for human activity recognition, Proc IJCAI, 3995
  18. 10.1145/1409635.1409637 · DOI · Paper page
  19. 10.1145/2030112.2030172 · DOI
  20. 10.1007/978-3-540-72348-6_3 · DOI · Paper page
  21. altun, 2010, Human activity recognition using inertial/magnetic sensor units, Proc Int Workshop Human Behav Understand, 38, 10.1007/978-3-642-14715-9_5 · DOI · Paper page
  22. 10.1016/j.cviu.2006.10.019 · DOI · Paper page
  23. hasan, 2016, Human activity recognition using smartphone sensors with context filtering, Proc 9th Int Conf Adv Comput -Hum Interact (ACHI), 69
  24. 10.1007/s10015-017-0422-x · DOI · Paper page
  25. almaslukh, 2017, An effective deep autoencoder approach for Online smartphone-based human activity recognition, Int J Comput Sci Netw Secur (IJCSNS), 17, 160
  26. 10.1007/978-3-642-75988-8_28 · DOI · Paper page

Cited by

Metadata

Authors
Xi, R., Li, M., Hou, M., Fu, M., Qu, H., Liu, D., & Haruna, C. R.
Venue
IEEE Access
Published
2018
Volume
6
Pages
53381-53396
ISSN
2169-3536 (ISSN-L)
OpenAlex
W2892279525
Cited by
35
References
13
FWCI
2.87
Type
journal article
Language
en
Open access
gold
Funders
NSF China Projects (61472067)

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.