CoChat

Automatic Annotation for Human Activity Recognition in Free Living Using a Smartphone

Open access
Cruciani, Federico, Cleland, Ian, Nugent, Chris, McCullagh, Paul, Synnes, Kåre, Hallberg, Josef · 2018 · Sensors
Cited by 60

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Abstract

Data annotation is a time-consuming process posing major limitations to the development of Human Activity Recognition (HAR) systems. The availability of a large amount of labeled data is required for supervised Machine Learning (ML) approaches, especially in the case of online and personalized approaches requiring user specific datasets to be labeled. The availability of such datasets has the potential to help address common problems of smartphone-based HAR, such as inter-person variability. In this work, we present (i) an automatic labeling method facilitating the collection of labeled datasets in free-living conditions using the smartphone, and (ii) we investigate the robustness of common supervised classification approaches under instances of noisy data. We evaluated the results with a dataset consisting of 38 days of manually labeled data collected in free living. The comparison between the manually and the automatically labeled ground truth demonstrated that it was possible to obtain labels automatically with an 80–85% average precision rate. Results obtained also show how a supervised approach trained using automatically generated labels achieved an 84% f-score (using Neural Networks and Random Forests); however, results also demonstrated how the presence of label noise could lower the f-score up to 64–74% depending on the classification approach (Nearest Centroid and Multi-Class Support Vector Machine).

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 · 10.3390/s18072203

Cites

9 of 9 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 9 references

Research works printed but not linked: 33

  1. Morales, 2017, Physical activity recognition by smartphones, a survey, Biocybern. Biomed. Eng., 37, 388, 10.1016/j.bbe.2017.04.004 · DOI
  2. Ermes, 2008, Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions, IEEE Trans. Inf. Technol. Biomed., 12, 20, 10.1109/TITB.2007.899496 · DOI · Paper page
  3. Incel, 2013, A Review and Taxonomy of Activity Recognition on Mobile Phones, BioNanoScience, 3, 145, 10.1007/s12668-013-0088-3 · DOI · Paper page
  4. Schröder, M., Yordanova, K., Bader, S., and Kirste, T. (2016, January 23–24). Tool support for the online annotation of sensor data. Proceedings of the 3rd International Workshop on Sensor-based Activity Recognition and Interaction, Rostock, Germany. · DOI
  5. Cruciani, F., Donnelly, M.P., Nugent, C.D., Parente, G., Paggetti, C., and Burns, W. (2010, January 13–15). DANTE: A video based annotation tool for smart environments. Proceedings of the International Conference on Sensor Systems and Software, Miami, FL, USA. · DOI
  6. Woznowski, P., Tonkin, E., Laskowski, P., Twomey, N., Yordanova, K., and Burrows, A. (2017, January 13–17). Talk, text or tag?: The development of a self-annotation app for activity recognition in smart environments. Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops, Big Island, HI, USA. · DOI
  7. Cleland, 2014, Evaluation of prompted annotation of activity data recorded from a smart phone, Sensors, 14, 15861, 10.3390/s140915861 · DOI
  8. Yordanova, K., Paiement, A., Schröder, M., Tonkin, E., Woznowski, P., Olsson, C.M., Rafferty, J., and Sztyler, T. (arXiv, 2018). Challenges in Annotation of useR Data for UbiquitOUs Systems: Results from the 1st ARDUOUS Workshop, arXiv.
  9. Stikic, 2011, Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors, IEEE Trans. Pattern Anal. Mach. Intell., 33, 2521, 10.1109/TPAMI.2011.36 · DOI · Paper page
  10. Azkune, 2015, Extending knowledge-driven activity models through data-driven learning techniques, Expert Syst. Appl., 42, 3115, 10.1016/j.eswa.2014.11.063 · DOI
  11. Cruciani, F., Nugent, C., Cleland, I., McCullagh, P., Synnes, K., and Hallberg, J. (2018, January 19–23). Personalized Online Training for Physical Activity Monitoring using Weak Labels. Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Athens, Greece. · DOI
  12. Siirtola, 2012, Recognizing Human Activities User-independently on Smartphones Based on Accelerometer Data, Int. J. Interact. Multimed. Artif. Intelligence, 1, 38
  13. Leuenberger, 2014, Activity classification based on inertial and barometric pressure sensors at different anatomical locations, Physiol. Meas., 35, 1245, 10.1088/0967-3334/35/7/1245 · DOI
  14. Dernbach, S., Das, B., Krishnan, N.C., Thomas, B.L., and Cook, D.J. (2017, January 26–29). Simple and Complex Activity Recognition through Smart Phones. Proceedings of the IEEE Eighth International Conference on Intelligent Environments, Guanajuato, Mexico.
  15. Bernardos, 2013, Activity logging using lightweight classification techniques in mobile devices, Pers. Ubiquit. Comput., 17, 675, 10.1007/s00779-012-0515-4 · DOI · Paper page
  16. Kose, M., Incel, O.D., and Ersoy, C. (2012, January 6). Online human activity recognition on smart phones. Proceedings of the Workshop on Mobile Sensing: From Smartphones and Wearables to Big Data, Beijing, China.
  17. Su, 2014, Activity recognition with smartphone sensors, Tsinghua Sci. Technol., 19, 235, 10.1109/TST.2014.6838194 · DOI · Paper page
  18. Kim, 2010, Human activity recognition and pattern discovery, IEEE Perv. Comput., 9, 48, 10.1109/MPRV.2010.7 · DOI · Paper page
  19. Lee, Y.S., and Cho, S.B. (2011, January 23–25). Activity Recognition Using Hierarchical Hidden Markov Models on a Smartphone with 3D Accelerometer. Proceedings of the 6th International Conference on Hybrid Artificial Intelligence Systems, Wroclaw, Poland. · DOI · Paper page
  20. Hassan, 2018, A robust human activity recognition system using smartphone sensors and deep learning, Future Gener. Comput. Syst., 81, 307, 10.1016/j.future.2017.11.029 · DOI · Paper page
  21. Kotsiantis, 2006, Handling imbalanced datasets : A review, Science, 30, 25
  22. Zimmerman, 2009, The observer XT: A tool for the integration and synchronization of multimodal signals, Behav. Res. Methods, 41, 731, 10.3758/BRM.41.3.731 · DOI
  23. Kelly, 2016, Pervasive Sound Sensing: A Weakly Supervised Training Approach, IEEE Trans. Cybern., 46, 123, 10.1109/TCYB.2015.2396291 · doi:10.1109/tcyb.2015.2396291
  24. Buehler, P., Everingham, M., and Zisserman, A. (2009, January 20–25). Learning sign language by watching TV (using weakly aligned subtitles). Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops 2009), Miami, FL, USA. · DOI
  25. Anguita, 2013, Energy efficient smartphone-based activity recognition using fixed-point arithmetic, J. Univers. Comput. Sci., 19, 1295
  26. Pei, 2013, Human behavior cognition using smartphone sensors, Sensors, 13, 1402, 10.3390/s130201402 · DOI
  27. Bhattacharya, 2014, Using unlabeled data in a sparse-coding framework for human activity recognition, Perv. Mobile Comput., 15, 242, 10.1016/j.pmcj.2014.05.006 · DOI
  28. Cao, 2018, GCHAR: An efficient Group-based Context—Aware human activity recognition on smartphone, J. Parallel Distrib. Comput., 118, 67, 10.1016/j.jpdc.2017.05.007 · DOI
  29. Blunck, 2018, Robust Human Activity Recognition using smartwatches and smartphones, Eng. Appl. Artif. Intell., 72, 190, 10.1016/j.engappai.2018.04.002 · DOI · Paper page
  30. Marshall, 2009, Translating Physical Activity Recommendations into a Pedometer-Based Step Goal, Am. J. Prev. Med., 36, 410, 10.1016/j.amepre.2009.01.021 · DOI · Paper page
  31. Cruciani, F., Nugent, C., Cleland, I., and McCullagh, P. (2017, January 11–15). Rich Context Information for Just-In-Time Adaptive Intervention promoting physical activity. Proceedings of 39th Annual International Conference of the IEEE on the Engineering in Medicine and Biology Society (EMBC), Seogwipo, Korea. · DOI
  32. Cavagna, 1991, The two power limits conditioning step frequency in human running, J. Physiol., 437, 95, 10.1113/jphysiol.1991.sp018586 · DOI
  33. Schleinitz, 2017, The German Naturalistic Cycling Study—Comparing cycling speed of riders of different e-bikes and conventional bicycles, Saf. Sci., 92, 290, 10.1016/j.ssci.2015.07.027 · doi:10.1016/j.ssci.2015.07.027

Cited by

See all 60

Metadata

Authors
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K., & Hallberg, J.
Venue
Sensors
Publisher
MDPI AG
Published
2018-07-09
Volume
18
Issue
7
Pages
2203
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2833792958
Cited by
60
References
9
FWCI
4.36
Type
journal article
Language
en
Open access
gold
Funders
H2020 Marie Skłodowska-Curie Actions (676157)

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: Automatic Annotation for Human Activity Recognition in Free Living Using a Smartphone. https://app.cochat.ai/papers/10.3390/s18072203
The paper
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K., & Hallberg, J. (2018). Automatic Annotation for Human Activity Recognition in Free Living Using a Smartphone. Sensors. https://doi.org/10.3390/s18072203

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.