CoChat

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

Open access
Mohammadian Rad, Nastaran, Kia, Seyed Mostafa, Zarbo, Calogero, van Laarhoven, Twan, Jurman, Giuseppe, Venuti, Paola, Marchiori, Elena, Furlanello, Cesare · 2018 · Signal Processing
Cited by 94

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multi-axis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: (1) feature learning outperforms handcrafted features; (2) parameter transfer learning is beneficial in longitudinal settings; (3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; (4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.

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 · 10.1016/j.sigpro.2017.10.011

Cites

14 of 14 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 14 references

Research works printed but not linked: 32

  1. Chaspari, 2012, 8, 8
  2. Berkson, 1962, Stereotyped movements of mental defectives: I. initial survey., Am. J. Mental Deficiency
  3. Lewis, 1982, Stereotyped mannerisms in mentally retarded persons: animal models and theoretical analyses, Int. Rev. Res. Mental Retard., 11, 123, 10.1016/S0074-7750(08)60291-8 · DOI
  4. Ridley, 1982, Stereotypy in monkeys and humans, Psychol. Med., 12, 61, 10.1017/S0033291700043294 · DOI · Paper page
  5. Varni, 1979, An analysis of observational learning in autistic and normal children, J. Abnormal Child Psychol., 7, 31, 10.1007/BF00924508 · DOI
  6. Jones, 1990, The social effects of stereotyped behaviour, J. Intellectual Disability Res., 34, 261, 10.1111/j.1365-2788.1990.tb01537.x · DOI
  7. C.H. Kennedy, Evolution of stereotypy into self-injury. (2002). · doi:10.1037/10457-008
  8. Pyles, 1997, The stereotypy analysis: an instrument for examining environmental variables associated with differential rates of stereotypic behavior, Res. Development. Disabilities, 18, 11, 10.1016/S0891-4222(96)00034-0 · DOI
  9. Gardenier, 2004, Comparison of direct observational methods for measuring stereotypic behavior in children with autism spectrum disorders, Res. Development. Disabilities, 25, 99, 10.1016/j.ridd.2003.05.004 · DOI
  10. Matson, 2007, Assessing challenging behaviors in children with autism spectrum disorders: a review, Res. Development. Disabilities, 28, 567, 10.1016/j.ridd.2006.08.001 · DOI · Paper page
  11. Goldman, 2009, Motor stereotypies in children with autism and other developmental disorders, Development. Med. Child Neurol., 51, 30, 10.1111/j.1469-8749.2008.03178.x · DOI · Paper page
  12. Lee, 2007, Social engagement with peers and stereotypic behavior of children with autism, J. Positive Behav. Intervent., 9, 67, 10.1177/10983007070090020401 · DOI · Paper page
  13. Loftin, 2008, Social interaction and repetitive motor behaviors, J. Autism and Development. Disorders, 38, 1124, 10.1007/s10803-007-0499-5 · DOI · Paper page
  14. Mathie, 2004, Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement, Physiol. Measur., 25, R1, 10.1088/0967-3334/25/2/R01 · DOI · Paper page
  15. Helbostad, 2017, Mobile health applications to promote active and healthy ageing, Sensors, 17, 10.3390/s17030622 · DOI · Paper page
  16. Gjoreski, 2016, How accurately can your wrist device recognize daily activities and detect falls?, Sensors, 16, 10.3390/s16060800 · DOI · Paper page
  17. Goncalves, 2012, Automatic detection of stereotypical motor movements, Procedia Eng., 47, 590, 10.1016/j.proeng.2012.09.216 · doi:10.1016/j.proeng.2012.09.216
  18. Rodrigues, 2013, Stereotyped movement recognition in children with ASD, Sensors Actuators A, 202, 162, 10.1016/j.sna.2013.04.019 · doi:10.1016/j.sna.2013.04.019
  19. Albinali, 2012, Detecting stereotypical motor movements in the classroom using accelerometry and pattern recognition algorithms, Pervasive Mobile Comput., 8, 103, 10.1016/j.pmcj.2011.04.006 · DOI
  20. Goodwin, 2011, Automated detection of stereotypical motor movements, J. Autism Development. Disorders, 41, 770, 10.1007/s10803-010-1102-z · DOI
  21. Großekathöfer, 2017, Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis, Frontiers Neuroinformatics, 11, 9, 10.3389/fninf.2017.00009 · DOI · Paper page
  22. Amiri, 2017, Wearsense: detecting autism stereotypic behaviors through smartwatches, Healthcare, 5, 10.3390/healthcare5010011 · DOI
  23. Ince, 2008, Detection of early morning daily activities with static home and wearable wireless sensors, EURASIP J. Adv. Signal Process., 2008, 31
  24. Stockwell, 1996, Localization of the complex spectrum: the s transform, Signal Process. IEEE Trans., 44, 998, 10.1109/78.492555 · DOI · Paper page
  25. Pan, 2010, A survey on transfer learning, Knowl. Data Eng. IEEE Trans., 22, 1345, 10.1109/TKDE.2009.191 · DOI · Paper page
  26. Eyben, 2009, From speech to letters-using a novel neural network architecture for grapheme based asr, 376
  27. W. Zaremba, I. Sutskever, O. Vinyals, Recurrent neural network regularization, arXiv:1409.2329 (2014). · arXiv
  28. Srivastava, 2014, Dropout: a simple way to prevent neural networks from overfitting., J. Mach. Learn. Res., 15, 1929
  29. L. Deng, J. Platt, Ensemble deep learning for speech recognition(2014). · DOI · Paper page
  30. Tieleman, 2012, Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude, COURSERA: Neural Netw. Mach. Learn., 4
  31. Maaten, 2008, Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 2579
  32. Lara, 2012, Centinela: a human activity recognition system based on acceleration and vital sign data, Pervasive and Mobile Comput., 8, 717, 10.1016/j.pmcj.2011.06.004 · DOI · Paper page

Cited by

See all 94

Metadata

Authors
Mohammadian Rad, N., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Marchiori, E., & Furlanello, C.
Venue
Signal Processing
Publisher
Elsevier BV
Published
2018-03
Volume
144
Pages
180-191
ISSN
0165-1684
OpenAlex
W2962879080
Cited by
94
References
14
FWCI
6.22
Type
journal article
Language
en
Open access
green
Licence
www.elsevier.com/tdm/userlicense/1.0/ (tdm)

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: Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders. https://app.cochat.ai/papers/10.1016/j.sigpro.2017.10.011
The paper
Mohammadian Rad, N., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Marchiori, E., & Furlanello, C. (2018). Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders. Signal Processing. https://doi.org/10.1016/j.sigpro.2017.10.011

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.