Computer vision-based approach for detecting arm-flapping as autism suspect behaviour
by Esraa T. Sadek; Noha A. Seada; Said Ghoniemy
International Journal of Medical Engineering and Informatics (IJMEI), Vol. 15, No. 2, 2023

Abstract: Autism spectrum disorder (ASD) is a neurodevelopmental condition that is characterised by frequent and restrictive motor activities, besides social and communicative disorders. It is considered one of the most rapidly evolving neurodevelopmental disorders in children recently. Repetitive motor behaviours, like arm-flapping and head rocking, may lead to attention distraction and self-injury in severe cases. In this research, a computer-vision-based neural network framework is proposed to automatically detect significant arm-flapping behaviour in autistics. The proposed framework goes through four main phases which are data pre-processing, pose estimation and skeleton representation, data post-processing, and action classification. The proposed framework was tested on three datasets and proved its applicability in real-world applications. The attained accuracy was better compared to that of the state-of-the-art methods. The proposed solution can be used to assist clinicians, and parents to automatically detect this behaviour to offer the child the appropriate medical care once a behavioural abnormality is detected.

Online publication date: Tue, 07-Mar-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Medical Engineering and Informatics (IJMEI):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com