Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zakia Batool Turabee,
  • David J. Brown,
  • Mufti Mahmud,
  • Andreas Oikonomou,
  • Andrew Burton,
  • Nicholas Shopland,
  • Muhammad Arifur Rahman,
  • Dawn Clarke,
  • Fiona Gray

摘要

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.