Conference PaperPDF Available

Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD)

Authors:

Abstract

Presently, the number of children with autism appears to be growing at disturbing rate. Unfortunately, the awareness of early sign of Autism Spectrum Disorder (ASD) is still insufficiently provided to the public. Arm flapping is a good example of a stereotypical behavior of ASD early sign. Typically, a standard Repetitive Behavior Scale-Revised (RBSR) - set of questionnaire - used by clinicians for ASD diagnosis usually involved multiple and long sessions that apparently would delay and may have nonconformity. Thus, we aim to propose a computational framework to semi-automate the diagnosis process. We used human action recognition (HAR) algorithm. HAR involved in human body detection and the skeleton representation to show the arm asymmetrical in arm flapping movement which indicates the possibility of ASD signs by extracting the body pose into stickman model. The proposed framework has been tested against the video clips of children performing arm flapping behavior taken from public dataset. The outcome of this study is expected to detect early sign of ASD based on asymmetry measurement of arm flapping behavior.
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 1/6
Measuring the Variabilities in the Body
Postures of the Children for Early
Detection of Autism Spectrum Disorder
(ASD)
International Visual Informatics Conference
IVIC 2017: Advances in Visual Informatics pp 510-520 | Cite as
Ahmed Danial Arif Yaakob (1)
Nur Intan Raihana Ruhaiyem (1) Email author (intanraihana@usm.my)
1. School of Computer Sciences, Universiti Sains Malaysia (USM), , Gelugor, Malaysia
Conference paper
First Online: 29 October 2017
1.3k Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10645)
Abstract
Presently, the number of children with autism appears to be growing at disturbing
rate. Unfortunately, the awareness of early sign of Autism Spectrum Disorder (ASD) is
still insufficiently provided to the public. Arm flapping is a good example of a
stereotypical behavior of ASD early sign. Typically, a standard Repetitive Behavior
Scale-Revised (RBSR) - set of questionnaire - used by clinicians for ASD diagnosis
usually involved multiple and long sessions that apparently would delay and may have
nonconformity. Thus, we aim to propose a computational framework to semi-
automate the diagnosis process. We used human action recognition (HAR) algorithm.
HAR involved in human body detection and the skeleton representation to show the
arm asymmetrical in arm flapping movement which indicates the possibility of ASD
signs by extracting the body pose into stickman model. The proposed framework has
been tested against the video clips of children performing arm flapping behavior taken
from public dataset. The outcome of this study is expected to detect early sign of ASD
based on asymmetry measurement of arm flapping behavior.
Keywords
Autism Spectrum Disorder ASD early detection Body postures Arm flapping
HAR algorithm Skeleton representation
This is a preview of subscription content, log in to check access.
Notes
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 2/6
1.
2.
3.
4.
5.
6.
Acknowledgments
The authors wish to thank Universiti Sains Malaysia for the support it has extended in
the completion of the present research through Short Term University Grant No:
304/PKOMP/6313259.
References
McCary, L.M., Grefer, M., Mounts, M., Roberts, J.E.: The Importance of
Differential Diagnosis in Neurodevelopmental Disorders: Implications for Idea.
American Psychological Association, Washington, D.C. (2012)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=The%20Importance%20of%20Differential%20Diagnosis%20in%20Neuro
developmental%20Disorders%3A%20Implications%20for%20Idea&author=L
M.%20McCary&author=M.%20Grefer&author=M.%20Mounts&author=JE.%2
0Roberts&publication_year=2012)
Mesibov, G., Adams, L., Klinger, L.: Autism: Understanding the Disorder.
Plenum Press, New York (1997)
CrossRef (https://doi.org/10.1007/978-1-4757-9343-7)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Autism%3A%20Understanding%20the%20Disorder&author=G.%20Mesi
bov&author=L.%20Adams&author=L.%20Klinger&publication_year=1997)
Schertz, H.H., Baker, C., Hurwitz, S., Benner, L.: Principles of early intervention
reflected in toddler research in autism spectrum disorders. Top. Early Child.
Spec. Edu. 31(1), 4–21 (2011)
CrossRef (https://doi.org/10.1177/0271121410382460)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Principles%20of%20early%20intervention%20reflected%20in%20toddler
%20research%20in%20autism%20spectrum%20disorders&author=HH.%20Sc
hertz&author=C.%20Baker&author=S.%20Hurwitz&author=L.%20Benner&jo
urnal=Top.%20Early%20Child.%20Spec.%20Edu.&volume=31&issue=1&pages
=4-21&publication_year=2011)
Liaw, L.C.B.@.A.: Phenomenological Study an Explanatory on Parents of
Autistic Children in Kuching, Sarawak (2008)
Google Scholar (https://scholar.google.com/scholar?
q=Liaw%2C%20L.C.B.%40.A.%3A%20Phenomenological%20Study%20an%20
Explanatory%20on%20Parents%20of%20Autistic%20Children%20in%20Kuch
ing%2C%20Sarawak%20%282008%29)
Boyd, B.A., Shaw, E.: Autism in the classroom: a group of students changing in
population and presentation. Prev. Sch. Fail. 54(4), 211–219 (2010)
CrossRef (https://doi.org/10.1080/10459881003744552)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Autism%20in%20the%20classroom%3A%20a%20group%20of%20stude
nts%20changing%20in%20population%20and%20presentation&author=BA.%
20Boyd&author=E.%20Shaw&journal=Prev.%20Sch.%20Fail.&volume=54&iss
ue=4&pages=211-219&publication_year=2010)
Susan, L.H., Patricia, M.R., Davidson, P.: Pervasive developmental disorders in
young children. J. Am. Med. Assoc. 285, 3141–3142 (2001)
CrossRef (https://doi.org/10.1001/jama.285.24.3141)
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 3/6
7.
8.
9.
10.
11.
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Pervasive%20developmental%20disorders%20in%20young%20children&
author=LH.%20Susan&author=MR.%20Patricia&author=P.%20Davidson&jou
rnal=J.%20Am.%20Med.%20Assoc.&volume=285&pages=3141-
3142&publication_year=2001)
Watson, L.R., Baranek, G.T., Crais, E.R., Hughes, C., Kristof, M.L., Zanzot, E.:
Gesture use of infants with autism at 9–12 months. In: The American Speech-
Language-Hearing Association Convention (2000)
Google Scholar (https://scholar.google.com/scholar?
q=Watson%2C%20L.R.%2C%20Baranek%2C%20G.T.%2C%20Crais%2C%20E.
R.%2C%20Hughes%2C%20C.%2C%20Kristof%2C%20M.L.%2C%20Zanzot%2
C%20E.%3A%20Gesture%20use%20of%20infants%20with%20autism%20at%
209%E2%80%9312%20months.%20In%3A%20The%20American%20Speech-
Language-Hearing%20Association%20Convention%20%282000%29)
Goodwin, M.S., Intille, S.S.: Recognizing stereotypical motor movements in the
laboratory and classroom: a case study with children on the autism spectrum.
In: Proceeding of the 11th International Conference on Ubiquitous Computing
(2009)
Google Scholar (https://scholar.google.com/scholar?
q=Goodwin%2C%20M.S.%2C%20Intille%2C%20S.S.%3A%20Recognizing%20
stereotypical%20motor%20movements%20in%20the%20laboratory%20and%
20classroom%3A%20a%20case%20study%20with%20children%20on%20the
%20autism%20spectrum.%20In%3A%20Proceeding%20of%20the%2011th%2
0International%20Conference%20on%20Ubiquitous%20Computing%20%282
009%29)
Westeyn, T., Vadas, K., Bian, X., Starner, T., Abowd, G.D.: Recognizing
mimicked autistic self-stimulatory behaviors using HMMs. In: Proceedings of
ISWC, pp. 164–169 (2005)
Google Scholar (https://scholar.google.com/scholar?
q=Westeyn%2C%20T.%2C%20Vadas%2C%20K.%2C%20Bian%2C%20X.%2C
%20Starner%2C%20T.%2C%20Abowd%2C%20G.D.%3A%20Recognizing%20
mimicked%20autistic%20self-
stimulatory%20behaviors%20using%20HMMs.%20In%3A%20Proceedings%2
0of%20ISWC%2C%20pp.%20164%E2%80%93169%20%282005%29)
Azizul, Z., Muty, N.: Detecting arm flapping in children with autism spectrum
disorder using human pose estimation and skeletal representation algorithms.
In: International Conference on Advanced Informatics: Concepts, Theory and
Application (2016)
Google Scholar (https://scholar.google.com/scholar?
q=Azizul%2C%20Z.%2C%20Muty%2C%20N.%3A%20Detecting%20arm%20fl
apping%20in%20children%20with%20autism%20spectrum%20disorder%20u
sing%20human%20pose%20estimation%20and%20skeletal%20representation
%20algorithms.%20In%3A%20International%20Conference%20on%20Advan
ced%20Informatics%3A%20Concepts%2C%20Theory%20and%20Application
%20%282016%29)
Sigal, L.: Human pose estimation. In: Ikeuchi, K. (ed.) Computer Vision, pp.
362–370. Springer, New York (2014). doi: 10.1007/978-0-387-31439-6_584
(https://doi.org/10.1007/978-0-387-31439-6_584)
CrossRef (https://doi.org/10.1007/978-0-387-31439-6_584)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Human%20pose%20estimation&author=L.%20Sigal&pages=362-
370&publication_year=2014)
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 4/6
12.
13.
14.
15.
16.
17.
Buehler, P., Everingham, M., Huttenlocher, D.P., Zisserman, A.: Long Term
Arm and Hand Tracking for Continuous Sign Language TV Broadcasts (2008)
Google Scholar (https://scholar.google.com/scholar?
q=Buehler%2C%20P.%2C%20Everingham%2C%20M.%2C%20Huttenlocher%
2C%20D.P.%2C%20Zisserman%2C%20A.%3A%20Long%20Term%20Arm%20
and%20Hand%20Tracking%20for%20Continuous%20Sign%20Language%20T
V%20Broadcasts%20%282008%29)
Teitelbaum, O., Benton, T., Shah, P.K., Prince, A., Kelly, J.L., Teitelbaum, P.:
Eshkol–Wachman movement notation in diagnosis: the early detection of
Asperger’s syndrom. Proc. Natl. Acad. Sci. U.S.A. 101, 11909–11914 (2004)
CrossRef (https://doi.org/10.1073/pnas.0403919101)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Eshkol%E2%80%93Wachman%20movement%20notation%20in%20diag
nosis%3A%20the%20early%20detection%20of%20Asperger%E2%80%99s%20
syndrom&author=O.%20Teitelbaum&author=T.%20Benton&author=PK.%20S
hah&author=A.%20Prince&author=JL.%20Kelly&author=P.%20Teitelbaum&j
ournal=Proc.%20Natl.%20Acad.%20Sci.%20U.S.A.&volume=101&pages=1190
9-11914&publication_year=2004)
Bai, X., Latecki, L.J.: Path similarity skeleton graph matching. IEEE Trans.
Patt. Anal. Mach. Intell. 30(7), 1282–1292 (2008)
CrossRef (https://doi.org/10.1109/TPAMI.2007.70769)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Path%20similarity%20skeleton%20graph%20matching&author=X.%20B
ai&author=LJ.%20Latecki&journal=IEEE%20Trans.%20Patt.%20Anal.%20Ma
ch.%20Intell.&volume=30&issue=7&pages=1282-
1292&publication_year=2008)
Esposito, G., Venuti, P., Apicella, F., Muratori, F.: Analysis of unsupported gait
in toddlers with autism. Brain Dev. 33, 367–373 (2011)
CrossRef (https://doi.org/10.1016/j.braindev.2010.07.006)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Analysis%20of%20unsupported%20gait%20in%20toddlers%20with%20a
utism&author=G.%20Esposito&author=P.%20Venuti&author=F.%20Apicella&
author=F.%20Muratori&journal=Brain%20Dev.&volume=33&pages=367-
373&publication_year=2011)
Hashemi, J., Spina, T.V., Tepper, M., Esler, A., Morellas, V., Papanikolopoulos,
N., Sapiro, G.: Computer vision tools for the non-invasive assessment of
autism-related behavioral markers. In: Development and Learning and
Epigenetic Robotics, pp. 1–7 (2012)
Google Scholar (https://scholar.google.com/scholar?
q=Hashemi%2C%20J.%2C%20Spina%2C%20T.V.%2C%20Tepper%2C%20M.
%2C%20Esler%2C%20A.%2C%20Morellas%2C%20V.%2C%20Papanikolopoul
os%2C%20N.%2C%20Sapiro%2C%20G.%3A%20Computer%20vision%20tools
%20for%20the%20non-invasive%20assessment%20of%20autism-
related%20behavioral%20markers.%20In%3A%20Development%20and%20L
earning%20and%20Epigenetic%20Robotics%2C%20pp.%201%E2%80%937%2
0%282012%29)
Rajagopalan, S.S., Dhall, A., Goecke, R.: Self-Stimulatory Behaviours in the
Wild for Autism Diagnosis (2013)
Google Scholar (https://scholar.google.com/scholar?
q=Rajagopalan%2C%20S.S.%2C%20Dhall%2C%20A.%2C%20Goecke%2C%20
R.%3A%20Self-
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 5/6
18.
19.
20.
Stimulatory%20Behaviours%20in%20the%20Wild%20for%20Autism%20Diag
nosis%20%282013%29)
Muhammad, A., Surip, S.S., Harris, B., Mohamed, A.S.A.: Interactive sign
language interpreter using skeleton tracking. J. Telecommun. Electron.
Comput. Eng. (JTEC) 8, 137–140 (2016)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Interactive%20sign%20language%20interpreter%20using%20skeleton%2
0tracking&author=A.%20Muhammad&author=SS.%20Surip&author=B.%20H
arris&author=ASA.%20Mohamed&journal=J.%20Telecommun.%20Electron.%
20Comput.%20Eng.%20%28JTEC%29&volume=8&pages=137-
140&publication_year=2016)
Ravi, P.L., Ruhaiyem, N.I.R.: Intelligent gameplay for improved retro games. J.
Telecommun. Electron. Comput. Eng. (JTEC) 8(6), 23–26 (2016)
Google Scholar (http://scholar.google.com/scholar_lookup?
title=Intelligent%20gameplay%20for%20improved%20retro%20games&autho
r=PL.%20Ravi&author=NIR.%20Ruhaiyem&journal=J.%20Telecommun.%20
Electron.%20Comput.%20Eng.%20%28JTEC%29&volume=8&issue=6&pages
=23-26&publication_year=2016)
Noor Muhammad, M.A., Ruhaiyem, N.I.R., Mohamed, A.S.A.: Keeping curiosity
in local historical knowledge alive by sensor based simulation game using flash
actionscript 3. In: Proceedings of the International Conference Local
Knowledge (2016)
Google Scholar (https://scholar.google.com/scholar?
q=Noor%20Muhammad%2C%20M.A.%2C%20Ruhaiyem%2C%20N.I.R.%2C%
20Mohamed%2C%20A.S.A.%3A%20Keeping%20curiosity%20in%20local%20
historical%20knowledge%20alive%20by%20sensor%20based%20simulation%
20game%20using%20flash%20actionscript%203.%20In%3A%20Proceedings
%20of%20the%20International%20Conference%20Local%20Knowledge%20%
282016%29)
Copyright information
© Springer International Publishing AG 2017
About this paper
Cite this paper as:
Yaakob A.D.A., Ruhaiyem N.I.R. (2017) Measuring the Variabilities in the Body Postures of the Children for
Early Detection of Autism Spectrum Disorder (ASD). In: Badioze Zaman H. et al. (eds) Advances in Visual
Informatics. IVIC 2017. Lecture Notes in Computer Science, vol 10645. Springer, Cham.
https://doi.org/10.1007/978-3-319-70010-6_47
First Online 29 October 2017
DOI https://doi.org/10.1007/978-3-319-70010-6_47
Publisher Name Springer, Cham
Print ISBN 978-3-319-70009-0
Online ISBN 978-3-319-70010-6
eBook Packages Computer Science Computer Science (R0)
Buy this book on publisher's site
Reprints and Permissions
8/30/2020 Measuring the Variabilities in the Body Postures of the Children for Early Detection of Autism Spectrum Disorder (ASD) | SpringerLink
https://link.springer.com/chapter/10.1007/978-3-319-70010-6_47 6/6
© 2020 Springer Nature Switzerland AG. Part of Springer Nature.
Not logged in Not affiliated 42.190.209.164
Personalised recommendations
... Bounded-zone feature extraction is believed to be a promising method for other handwriting datasets. Besides that, early intervention of any disabilities such as Autism nowadays not only depends on body posture variabilities [12] but also on handwriting recognition. ...
Conference Paper
Full-text available
Stereotypical behaviour such as arm flapping is among the prominent early signs for young children with Autism Spectrum Disorder (ASD). Diagnosis of arm flapping requires clinicians to use the standard Repetitive Behaviour Scale-Revised (RBSR) which is a structured questionnaire with the caregivers to detect the arm flapping behavioural patterns or cues. This method involves clinicians in multiple long sessions, risking a delay in diagnosis and usually an expensive process. Moreover, trained clinicians may not be available in some areas. The focus of this work is to propose a development of a computational framework to automate the diagnosis process of arm flapping. Here, we show how the human action recognition (HAR) techniques, namely, the pose estimation and the skeletal representation are utilized simultaneously to segment parts of the human body (head, neck, elbows and shoulders) into stickman model. We show how the stickman model allows us to estimate arm asymmetry (during arm flapping) which indicates possible sign of autism. The framework developed has been tested against data taken from a public database and has shown a high accuracy in detecting the repetitive behavioural pattern among young children. The results show that our method can provide efficient results in clinical assessment.
Article
Full-text available
In the wake of increasing nostalgia and the success of retro-compilations in the sixth and seventh generations of consoles, 'retro gaming' has become a motive in modern games, as well. The goal of this project is to remake and improve a classic puzzle game with intelligence gameplay element and better graphics for Android users namely "Coins Wipeout". The development of the gameplay intelligence will involve the use of a game engine - where three game mode are introduced; "Qualifier", "Knockout" and "Wipeout". The success of the project will surely contribute in success of retro games industry.
Conference Paper
Full-text available
Autism Spectrum Disorders (ASD), often referred to as autism, are neurological disorders characterised by deficits in cognitive skills, social and communicative behaviours. A common way of diagnosing ASD is by studying behavioural cues expressed by the children. We introduce a new publicly-available dataset of children videos exhibiting self-stimulatory (stimming) behaviours commonly used for autism diagnosis. These videos, posted by parents/caregivers in public domain websites, are collected and annotated for the stimming behaviours. These videos are extremely challenging for automatic behaviour analysis as they are recorded in uncontrolled natural settings. The dataset contains 75 videos with an average duration of 90 seconds per video, grouped under three categories of stimming behaviours: arm flapping, head banging and spinning. We also provide baseline results of tests conducted on this dataset using a standard bag of words approach for human action recognition. To the best of our knowledge, this is the first attempt in publicly making available a Self-Stimulatory Behaviour Dataset (SSBD) of children videos recorded in natural settings.
Article
Full-text available
This review examines how recommended practices for toddlers with autism spectrum disorders (ASD) are integrated into interventions in the first generation of research targeting toddlers with ASD. The purpose was not to review intervention effectiveness, which is addressed in other reviews; rather, it was to assess reported intervention methods in relation to principles distilled from early intervention policy and validated practice guidelines for toddlers and families. These principles include family-centered and family-supportive practice, natural environments, promotion of active child participation in learning, and functional and systematic practices that consider developmental readiness and unique variations in learning. A small minority of reported interventions (5 of 27) fully addressed each principle, revealing a substantial gap between principles and intervention research practices. The most pronounced gaps concerned natural/inclusive environments and family-centered/family-supportive practices. Recommendations for future research are presented.
Article
The aim of this paper is to introduce an interactive communication system that will benefit both people with hearing and verbal difficulties to convey in the form of the sign language naturally. The idea is to provide two ways of communication between two users by converting sign language to voice and text and provides means of returning communication feedback whereby the other party can speak or key-in text and translates it into sign language movement performed by a three-dimensional (3D) model. A Microsoft Kinect device is used to captures the sign movements by optimizing the skeleton tracking algorithm to understand specific hands movements and dictates using the pre-recorded gesture library to digitized voice and using the same apparatus, speech is translated back into sign language. Research leads in helping the disables have been carried out extensively and majority focuses on only using single type of motion sensing technology such as TOBII (eye tracking) and LEAP (leap motion) which are either costly or limited to a small workable space. Microsoft Kinect technology would be a genuinely equipment used to create a cost-effective and capable technology prototype that enables sign-language communication between signer and non-signer, thus, offers translation into Bahasa Malaysia text.
Article
There is much concern about whether the prevalence of pervasive developmental disorders (PDDs), sometimes referred to as autistic spectrum disorders, is increasing.1 No study is likely to answer that question because the last 20 years have seen dramatic changes in the diagnostic criteria, an increase in public awareness of autism and related disorders, and sweeping changes in the types and availability of therapeutic and educational services. However, problems with determining whether prevalence of the PDDs is increasing should not serve to distract from the question that can be answered—ie, what is the prevalence of PDDs now.
Conference Paper
The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated that promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests behavioral markers can be observed late in the first year of life. Many of these studies involved extensive frame-by-frame video observation and analysis of a child's natural behavior. Although non-intrusive, these methods are extremely time-intensive and require a high level of observer training; thus, they are impractical for clinical purposes. Diagnostic measures for ASD are available for infants but are only accurate when used by specialists experienced in early diagnosis. This work is a first milestone in a long-term multidisciplinary project that aims at helping clinicians and general practitioners accomplish this early detection/measurement task automatically. We focus on providing computer vision tools to measure and identify ASD behavioral markers based on components of the Autism Observation Scale for Infants (AOSI). In particular, we develop algorithms to measure three critical AOSI activities that assess visual attention. We augment these AOSI activities with an additional test that analyzes asymmetrical patterns in unsupported gait. The first set of algorithms involves assessing head motion by facial feature tracking, while the gait analysis relies on joint foreground segmentation and 2D body pose estimation in video. We show results that provide insightful knowledge to augment the clinician's behavioral observations obtained from real in-clinic assessments.
Article
The number of children with autism served in early intervention or the public school system appears to be growing at an alarming rate. This article provides a basis for understanding this dramatic increase. In addition, the authors present a brief overview of the characteristics of autism, research on early behavioral indicators of infants and toddlers at risk for the disorder, and indicators that may go overlooked in school-aged children. The authors discuss the effect of autism on the early intervention system and the educational implications of the disorder. Last, the authors address current and pending federal policy initiatives (e.g., the passage of autism insurance legislation) that affect families and practitioners.