A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models

Zakia Batool Turabee; David J. Brown; Mufti Mahmud; Andreas Oikonomou; Andrew Burton; Nicholas Shopland; Muhammad Arifur Rahman; Dawn Clarke; Fiona Gray

doi:10.1007/978-981-96-6957-8_19

A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models

Zakia Batool Turabee^*
, David J. Brown
, Mufti Mahmud
, Andreas Oikonomou
, Andrew Burton
, Nicholas Shopland
, Muhammad Arifur Rahman
, Dawn Clarke
, Fiona Gray

^*Corresponding author for this work

Department of Information and Computer Science

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

Abstract

As a part of an Erasmus+ funded project (AI-TOP-2020-1-UK01-KA201-079167) a dataset was curated to predict engagement and meltdowns in children with autism within a classroom environment. This study introduces a privacy-preserving approach for detecting the behavioural states of children in classrooms using this dataset. By extracting 3D cloud data points, machine learning models were trained to predict states such as engagement, boredom, and frustration in children while they play a computer game acting as a Continuous Performance Test. The goal of this approach is to assist teachers and caregivers in identifying potential “rumble moments” at an early stage, enabling them to introduce evidence-based well-being interventions in a timely manner. Due to the sensitivity and privacy concerns related to video data of children with Autism Spectrum Condition (ASC), this method ensures anonymous detection of the children’s emotional and behavioral states.

Original language	English
Title of host publication	Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
Editors	Mufti Mahmud, Maryam Doborjeh, Zohreh Doborjeh, Kevin Wong, Andrew Chi Sing Leung, M. Tanveer
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	274-286
Number of pages	13
ISBN (Print)	9789819669561
DOIs	https://doi.org/10.1007/978-981-96-6957-8_19
State	Published - 2025
Event	31st International Conference on Neural Information Processing, ICONIP 2024 - Auckland, New Zealand Duration: 2 Dec 2024 → 6 Dec 2024

Publication series

Name	Communications in Computer and Information Science
Volume	2285 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	31st International Conference on Neural Information Processing, ICONIP 2024
Country/Territory	New Zealand
City	Auckland
Period	2/12/24 → 6/12/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Keywords

3D cloud datapoints
Autism Spectrum Condition (ASC)
Emotional Dysregulation
Engagement
Machine Learning
Meltdown Detection
Pose and Face Landmarks
Privacy-Preserved Model
Rumble Moments

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-981-96-6957-8_19

Cite this

Turabee, Z. B., Brown, D. J., Mahmud, M., Oikonomou, A., Burton, A., Shopland, N., Rahman, M. A., Clarke, D., & Gray, F. (2025). A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models. In M. Mahmud, M. Doborjeh, Z. Doborjeh, K. Wong, A. C. S. Leung, & M. Tanveer (Eds.), Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings (pp. 274-286). (Communications in Computer and Information Science; Vol. 2285 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-6957-8_19

Turabee, Zakia Batool ; Brown, David J. ; Mahmud, Mufti et al. / A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models. Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings. editor / Mufti Mahmud ; Maryam Doborjeh ; Zohreh Doborjeh ; Kevin Wong ; Andrew Chi Sing Leung ; M. Tanveer. Springer Science and Business Media Deutschland GmbH, 2025. pp. 274-286 (Communications in Computer and Information Science).

@inproceedings{b3e1910499d84d7285a18cd918515ed4,

title = "A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models",

abstract = "As a part of an Erasmus+ funded project (AI-TOP-2020-1-UK01-KA201-079167) a dataset was curated to predict engagement and meltdowns in children with autism within a classroom environment. This study introduces a privacy-preserving approach for detecting the behavioural states of children in classrooms using this dataset. By extracting 3D cloud data points, machine learning models were trained to predict states such as engagement, boredom, and frustration in children while they play a computer game acting as a Continuous Performance Test. The goal of this approach is to assist teachers and caregivers in identifying potential “rumble moments” at an early stage, enabling them to introduce evidence-based well-being interventions in a timely manner. Due to the sensitivity and privacy concerns related to video data of children with Autism Spectrum Condition (ASC), this method ensures anonymous detection of the children{\textquoteright}s emotional and behavioral states.",

keywords = "3D cloud datapoints, Autism Spectrum Condition (ASC), Emotional Dysregulation, Engagement, Machine Learning, Meltdown Detection, Pose and Face Landmarks, Privacy-Preserved Model, Rumble Moments",

author = "Turabee, \{Zakia Batool\} and Brown, \{David J.\} and Mufti Mahmud and Andreas Oikonomou and Andrew Burton and Nicholas Shopland and Rahman, \{Muhammad Arifur\} and Dawn Clarke and Fiona Gray",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 31st International Conference on Neural Information Processing, ICONIP 2024 ; Conference date: 02-12-2024 Through 06-12-2024",

year = "2025",

doi = "10.1007/978-981-96-6957-8\_19",

language = "English",

isbn = "9789819669561",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "274--286",

editor = "Mufti Mahmud and Maryam Doborjeh and Zohreh Doborjeh and Kevin Wong and Leung, \{Andrew Chi Sing\} and M. Tanveer",

booktitle = "Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings",

address = "Germany",

}

Turabee, ZB, Brown, DJ, Mahmud, M, Oikonomou, A, Burton, A, Shopland, N, Rahman, MA, Clarke, D & Gray, F 2025, A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models. in M Mahmud, M Doborjeh, Z Doborjeh, K Wong, ACS Leung & M Tanveer (eds), Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings. Communications in Computer and Information Science, vol. 2285 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 274-286, 31st International Conference on Neural Information Processing, ICONIP 2024, Auckland, New Zealand, 2/12/24. https://doi.org/10.1007/978-981-96-6957-8_19

A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models. / Turabee, Zakia Batool; Brown, David J.; Mahmud, Mufti et al.
Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings. ed. / Mufti Mahmud; Maryam Doborjeh; Zohreh Doborjeh; Kevin Wong; Andrew Chi Sing Leung; M. Tanveer. Springer Science and Business Media Deutschland GmbH, 2025. p. 274-286 (Communications in Computer and Information Science; Vol. 2285 CCIS).

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

TY - GEN

T1 - A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models

AU - Turabee, Zakia Batool

AU - Brown, David J.

AU - Mahmud, Mufti

AU - Oikonomou, Andreas

AU - Burton, Andrew

AU - Shopland, Nicholas

AU - Rahman, Muhammad Arifur

AU - Clarke, Dawn

AU - Gray, Fiona

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - As a part of an Erasmus+ funded project (AI-TOP-2020-1-UK01-KA201-079167) a dataset was curated to predict engagement and meltdowns in children with autism within a classroom environment. This study introduces a privacy-preserving approach for detecting the behavioural states of children in classrooms using this dataset. By extracting 3D cloud data points, machine learning models were trained to predict states such as engagement, boredom, and frustration in children while they play a computer game acting as a Continuous Performance Test. The goal of this approach is to assist teachers and caregivers in identifying potential “rumble moments” at an early stage, enabling them to introduce evidence-based well-being interventions in a timely manner. Due to the sensitivity and privacy concerns related to video data of children with Autism Spectrum Condition (ASC), this method ensures anonymous detection of the children’s emotional and behavioral states.

AB - As a part of an Erasmus+ funded project (AI-TOP-2020-1-UK01-KA201-079167) a dataset was curated to predict engagement and meltdowns in children with autism within a classroom environment. This study introduces a privacy-preserving approach for detecting the behavioural states of children in classrooms using this dataset. By extracting 3D cloud data points, machine learning models were trained to predict states such as engagement, boredom, and frustration in children while they play a computer game acting as a Continuous Performance Test. The goal of this approach is to assist teachers and caregivers in identifying potential “rumble moments” at an early stage, enabling them to introduce evidence-based well-being interventions in a timely manner. Due to the sensitivity and privacy concerns related to video data of children with Autism Spectrum Condition (ASC), this method ensures anonymous detection of the children’s emotional and behavioral states.

KW - 3D cloud datapoints

KW - Autism Spectrum Condition (ASC)

KW - Emotional Dysregulation

KW - Engagement

KW - Machine Learning

KW - Meltdown Detection

KW - Pose and Face Landmarks

KW - Privacy-Preserved Model

KW - Rumble Moments

UR - https://www.scopus.com/pages/publications/105011960330

U2 - 10.1007/978-981-96-6957-8_19

DO - 10.1007/978-981-96-6957-8_19

M3 - Conference contribution

AN - SCOPUS:105011960330

SN - 9789819669561

T3 - Communications in Computer and Information Science

SP - 274

EP - 286

BT - Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings

A2 - Mahmud, Mufti

A2 - Doborjeh, Maryam

A2 - Doborjeh, Zohreh

A2 - Wong, Kevin

A2 - Leung, Andrew Chi Sing

A2 - Tanveer, M.

PB - Springer Science and Business Media Deutschland GmbH

T2 - 31st International Conference on Neural Information Processing, ICONIP 2024

Y2 - 2 December 2024 through 6 December 2024

ER -

Turabee ZB, Brown DJ, Mahmud M, Oikonomou A, Burton A, Shopland N et al. A Privacy-Preserving Approach for Engagement and Meltdown Detection in Children with Autism Using Machine Learning Models. In Mahmud M, Doborjeh M, Doborjeh Z, Wong K, Leung ACS, Tanveer M, editors, Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 274-286. (Communications in Computer and Information Science). doi: 10.1007/978-981-96-6957-8_19