CoChat

DeActive: Scaling Activity Recognition with Active Deep Learning

Open access
Hossain, H. M. Sajjad, Al Haiz Khan, MD Abdullah, Roy, Nirmalya · 2018 · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Cited by 56

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Abstract

Deep learning architectures have been applied increasingly in multi-modal problems which has empowered a large number of application domains needing much less human supervision in the process. As unlabeled data are abundant in most of the application domains, deep architectures are getting increasingly popular to extract meaningful information out of these large volume of data. One of the major caveat of these architectures is that the training phase demands both computational time and system resources much higher than shallow learning algorithms and it is posing a difficult challenge for the researchers to implement the architectures in low-power resource constrained devices. In this paper, we propose a deep and active learning enabled activity recognition model, DeActive, which is optimized according to our problem domain and reduce the resource requirements. We incorporate active learning in the process to minimize the human supervision along with the effort needed for compiling ground truth. The DeActive model has been validated using real data traces from a retirement community center (IRB #HP-00064387) and 4 public datasets. Our experimental results show that our model can contribute better accuracy while ensuring less amount of resource usages in reduced time compared to other traditional deep learning approaches in activity recognition.

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 · 10.1145/3214269

Cites

22 of 22 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 22 references

Research works printed but not linked: 45

  1. 10.3233/AIS-170427 · DOI
  2. 10.1007/978-3-642-25446-8_4 · DOI · Paper page
  3. 10.1016/j.pmcj.2014.05.006 · DOI
  4. Monica Bianchini and Franco Scarselli. 2014. On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures. IEEE Trans. Neural Netw. Learning Syst. (2014).
  5. Leon Bottou and Yoshua Bengio. 1995. Convergence properties of the k-means algorithms. In Advances in neural information processing systems. 585--592. · doi:10.5555/2998687.2998760
  6. Yu chen ho and Ching hu lu. 2009. Active-learning assisted self-reconfigurable activity recognition in a dynamic environment. In ICRA. · DOI
  7. Diane J Cook and Maureen Schmitter-Edgecombe. 2009. Assessing the quality of activities in a smart environment. Methods of information in medicine (2009).
  8. 10.1109/JSEN.2016.2628346 · DOI · Paper page
  9. Sanjoy Dasgupta. 2011. Two faces of active learning. Theor. Comput. Sci. (2011). 10.1016/j.tcs.2010.12.054 · DOI · Paper page
  10. Tom Diethe, Niall Twomey, and Peter Flach. 2015. Bayesian Active Transfer Learning in Smart Homes. In Proc. of ICML.
  11. Tushar Dobhal and Vivswan Shitole. 2015. Human Activity Recognition using Binary Motion Image and Deep Learning. Procedia Computer Science (2015).
  12. 10.5555/3041838.3041857 · doi:10.5555/3041838.3041857
  13. Gina Sprint et al. 2016. Unsupervised detection and analysis of changes in everyday physical activity data. Journal of Biomedical Informatics (2016). 10.1016/j.jbi.2016.07.020 · DOI
  14. H. M. Sajjad Hossain et al. 2016. Active learning enabled activity recognition. In IEEE PerCom. · DOI
  15. Michalis Vrigkas et al. 2015. A Review of Human Activity Recognition Methods. Front. Robotics and AI (2015). · DOI · Paper page
  16. 10.1145/2502081.2502099 · DOI
  17. Sourav Bhattacharya et al. {n. d.}. From smart to deep: Robust activity recognition on smartwatches using deep learning. In Proc. of PerCom Workshops 2016.
  18. Scott E. Reed et al. 2014. Training Deep Neural Networks on Noisy Labels with Bootstrapping. CoRR (2014).
  19. Tianqi Chen et al. 2016. Training Deep Nets with Sublinear Memory Cost. CoRR (2016).
  20. 10.1145/1409635.1409638 · DOI · Paper page
  21. 10.1145/2629528 · DOI · Paper page
  22. 10.5555/3060832.3060835 · doi:10.5555/3060832.3060835
  23. 10.5555/1703435.1703688 · doi:10.5555/1703435.1703688
  24. E. Hoque and J. Stankovic. 2012. AALO: Activity recognition in smart homes using Active Learning in the presence of Overlapped activities. In Proc. of PervasiveHealth.
  25. 10.1109/MDM.2015.42 · DOI
  26. 10.1007/11752967_11 · DOI
  27. H M Sajjad Hossain et al Joseph Taylor. 2017. SenseBox: A Low-Cost Smart Home System. In PerCom Demo Workshop.
  28. 10.1109/INFOCOM.2016.7524361 · DOI
  29. 10.5555/2959355.2959378 · doi:10.5555/2959355.2959378
  30. 10.1145/2750858.2804262 · DOI · Paper page
  31. 10.1145/2441776.2441912 · DOI · Paper page
  32. 10.5555/2976456.2976557 · doi:10.5555/2976456.2976557
  33. Xinyu Li, Dongyang Yao, and et al. 2016. Activity recognition for medical teamwork based on passive RFID. In 2016 IEEE International Conference on RFID, RFID 2016. 34--42.
  34. 10.1109/ICMLC.2010.5581050 · DOI · Paper page
  35. 10.1007/s11042-015-3188-y · DOI · Paper page
  36. 10.1109/IJCNN.2017.7966102 · DOI
  37. Youngja Park and et al. 2014. Generating balanced classifier-independent training samples from unlabeled data. Knowl. Inf. Syst. (2014). · doi:10.5555/2687513.2687570
  38. 10.5555/2283516.2283683 · doi:10.5555/2283516.2283683
  39. 10.1007/11595014_9 · DOI
  40. 10.1145/1772690.1772862 · DOI · Paper page
  41. 10.1109/ISWC.2008.4911590 · DOI · Paper page
  42. Cheng Tang and Claire Monteleoni. 2017. Convergence Rate of Stochastic k-means. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, 20-22 April 2017, Fort Lauderdale, FL, USA. 1495--1503.
  43. 10.1109/IJCNN.2014.6889457 · DOI · Paper page
  44. 10.1109/TCSVT.2016.2589879 · DOI · Paper page
  45. 10.5555/1944566.1944739 · doi:10.5555/1944566.1944739

Cited by

Metadata

Authors
Hossain, H. M. S., Al Haiz Khan, M. A., & Roy, N.
Venue
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Published
2018-07-05
Volume
2
Issue
2
Pages
1-23
ISSN
2474-9567 (ISSN-L)
OpenAlex
W2869166307
Cited by
56
References
22
FWCI
4.61
Type
journal article
Language
en
Open access
bronze
Funders
  • Alzheimer's Association (AARG-17-533039)
  • Office of Naval Research (N00014-15-1-2229)

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.