Stereotyped gesture recognition: An analysis between HMM and SVM

Marcos Y.O. Camada; Jes J.F. Cerqueira; Antonio Marcus N. Lima

doi:10.1109/INISTA.2017.8001180

Stereotyped gesture recognition: An analysis between HMM and SVM

Marcos Y.O. Camada
, Jes J.F. Cerqueira
, Antonio Marcus N. Lima

IFbaiano
Federal University of Bahia
Universidade Federal de Campina Grande

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Stereotypic behaviours are present in both human and nonhuman primates. Usually, these behaviours are a welfare indicator. However, the stereotypic behaviours may be also a symptom of some mental disorder in the humans. A specific case is Autism Spectrum Disorder (ASD). The individuals with ASD may exhibit stereotypic behaviours through some gestures. The classic stereotyped gestures of autism are: (i) Body Rocking; (ii) Hand Flapping; and (iii) Top Spinning. This paper study the performance between two machine learning algorithms to recognition the stereotyped gestures typical of autism: (i) Hidden Markov Model [HMM]; and (ii) Support Vector Machine [SVM]. Sequence of orientations data from some joints obtained through a RGB-D (Red Green Blue-Depth) camera [Kinect^®] are used for analysis. The results of these two machine learning algorithms are compared with state-of-the-art. The HMM approach proposed in this paper have shown 98.89% average recognition rate and 98.9% recall. This value is higher compared to the SVM approach and the others of art method presented.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017
Editors	Tulay Yildirim, Ireneusz Czarnowski, Piotr Jedrzejowicz
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	328-333
Number of pages	6
ISBN (Electronic)	9781509057955
DOIs	https://doi.org/10.1109/INISTA.2017.8001180
State	Published - 3 Aug 2017
Externally published	Yes
Event	2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 - Gdynia, Poland Duration: 3 Jul 2017 → 5 Jul 2017

Publication series

Name	Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

Conference

Conference	2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017
Country/Territory	Poland
City	Gdynia
Period	3/07/17 → 5/07/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

HMM
SVM
Stereotypic Behaviours
autism

Access to Document

10.1109/INISTA.2017.8001180

Cite this

Camada, M. Y. O., Cerqueira, J. J. F., & Lima, A. M. N. (2017). Stereotyped gesture recognition: An analysis between HMM and SVM. In T. Yildirim, I. Czarnowski, & P. Jedrzejowicz (Eds.), Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 (pp. 328-333). Article 8001180 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INISTA.2017.8001180

Camada, Marcos Y.O. ; Cerqueira, Jes J.F. ; Lima, Antonio Marcus N. / Stereotyped gesture recognition : An analysis between HMM and SVM. Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. editor / Tulay Yildirim ; Ireneusz Czarnowski ; Piotr Jedrzejowicz. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 328-333 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017).

@inproceedings{3ca3029e0df54944a6d6f80d9769d939,

title = "Stereotyped gesture recognition: An analysis between HMM and SVM",

abstract = "Stereotypic behaviours are present in both human and nonhuman primates. Usually, these behaviours are a welfare indicator. However, the stereotypic behaviours may be also a symptom of some mental disorder in the humans. A specific case is Autism Spectrum Disorder (ASD). The individuals with ASD may exhibit stereotypic behaviours through some gestures. The classic stereotyped gestures of autism are: (i) Body Rocking; (ii) Hand Flapping; and (iii) Top Spinning. This paper study the performance between two machine learning algorithms to recognition the stereotyped gestures typical of autism: (i) Hidden Markov Model [HMM]; and (ii) Support Vector Machine [SVM]. Sequence of orientations data from some joints obtained through a RGB-D (Red Green Blue-Depth) camera [Kinect{\textregistered}] are used for analysis. The results of these two machine learning algorithms are compared with state-of-the-art. The HMM approach proposed in this paper have shown 98.89\% average recognition rate and 98.9\% recall. This value is higher compared to the SVM approach and the others of art method presented.",

keywords = "HMM, SVM, Stereotypic Behaviours, autism",

author = "Camada, \{Marcos Y.O.\} and Cerqueira, \{Jes J.F.\} and Lima, \{Antonio Marcus N.\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017 ; Conference date: 03-07-2017 Through 05-07-2017",

year = "2017",

month = aug,

day = "3",

doi = "10.1109/INISTA.2017.8001180",

language = "English",

series = "Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "328--333",

editor = "Tulay Yildirim and Ireneusz Czarnowski and Piotr Jedrzejowicz",

booktitle = "Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017",

}

Camada, MYO, Cerqueira, JJF & Lima, AMN 2017, Stereotyped gesture recognition: An analysis between HMM and SVM. in T Yildirim, I Czarnowski & P Jedrzejowicz (eds), Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017., 8001180, Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017, Institute of Electrical and Electronics Engineers Inc., pp. 328-333, 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017, Gdynia, Poland, 3/07/17. https://doi.org/10.1109/INISTA.2017.8001180

Stereotyped gesture recognition: An analysis between HMM and SVM. / Camada, Marcos Y.O.; Cerqueira, Jes J.F.; Lima, Antonio Marcus N.
Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. ed. / Tulay Yildirim; Ireneusz Czarnowski; Piotr Jedrzejowicz. Institute of Electrical and Electronics Engineers Inc., 2017. p. 328-333 8001180 (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Stereotyped gesture recognition

T2 - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

AU - Camada, Marcos Y.O.

AU - Cerqueira, Jes J.F.

AU - Lima, Antonio Marcus N.

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Stereotypic behaviours are present in both human and nonhuman primates. Usually, these behaviours are a welfare indicator. However, the stereotypic behaviours may be also a symptom of some mental disorder in the humans. A specific case is Autism Spectrum Disorder (ASD). The individuals with ASD may exhibit stereotypic behaviours through some gestures. The classic stereotyped gestures of autism are: (i) Body Rocking; (ii) Hand Flapping; and (iii) Top Spinning. This paper study the performance between two machine learning algorithms to recognition the stereotyped gestures typical of autism: (i) Hidden Markov Model [HMM]; and (ii) Support Vector Machine [SVM]. Sequence of orientations data from some joints obtained through a RGB-D (Red Green Blue-Depth) camera [Kinect®] are used for analysis. The results of these two machine learning algorithms are compared with state-of-the-art. The HMM approach proposed in this paper have shown 98.89% average recognition rate and 98.9% recall. This value is higher compared to the SVM approach and the others of art method presented.

AB - Stereotypic behaviours are present in both human and nonhuman primates. Usually, these behaviours are a welfare indicator. However, the stereotypic behaviours may be also a symptom of some mental disorder in the humans. A specific case is Autism Spectrum Disorder (ASD). The individuals with ASD may exhibit stereotypic behaviours through some gestures. The classic stereotyped gestures of autism are: (i) Body Rocking; (ii) Hand Flapping; and (iii) Top Spinning. This paper study the performance between two machine learning algorithms to recognition the stereotyped gestures typical of autism: (i) Hidden Markov Model [HMM]; and (ii) Support Vector Machine [SVM]. Sequence of orientations data from some joints obtained through a RGB-D (Red Green Blue-Depth) camera [Kinect®] are used for analysis. The results of these two machine learning algorithms are compared with state-of-the-art. The HMM approach proposed in this paper have shown 98.89% average recognition rate and 98.9% recall. This value is higher compared to the SVM approach and the others of art method presented.

KW - HMM

KW - SVM

KW - Stereotypic Behaviours

KW - autism

UR - https://www.scopus.com/pages/publications/85030225761

U2 - 10.1109/INISTA.2017.8001180

DO - 10.1109/INISTA.2017.8001180

M3 - Conference contribution

AN - SCOPUS:85030225761

T3 - Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

SP - 328

EP - 333

BT - Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017

A2 - Yildirim, Tulay

A2 - Czarnowski, Ireneusz

A2 - Jedrzejowicz, Piotr

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 3 July 2017 through 5 July 2017

ER -

Camada MYO, Cerqueira JJF, Lima AMN. Stereotyped gesture recognition: An analysis between HMM and SVM. In Yildirim T, Czarnowski I, Jedrzejowicz P, editors, Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 328-333. 8001180. (Proceedings - 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2017). doi: 10.1109/INISTA.2017.8001180

Stereotyped gesture recognition: An analysis between HMM and SVM

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this