Action quality assessment methods for ASD behaviour evaluation

Dinghuang Zhang; Dalin Zhou; Honghai Liu

doi:10.1109/ICMLC58545.2023.10327994

Action quality assessment methods for ASD behaviour evaluation

Dinghuang Zhang, Dalin Zhou, Honghai Liu

School of Computing

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

81 Downloads (Pure)

Abstract

Given the current increasing prevalence of autism, expensive and time-consuming manual diagnosis is highly detrimental to the management of the condition. With the development of computer-based methods of human behavioural analysis, these methods are expected to provide more accurate, objective and reproducible methods of early screening and diagnosis of autism. To advance the field of behavioural quantification in autism research, this study utilises human skeletal behavioural data from publicly available autism datasets and ADOS scores from clinical professionals in a first attempt to build deep neural networks that can predict ADOS scores from behavioural data using the AQA approach. This paper finds a moderately correlated between the ground truth ADOS score and the predicted ADOS score, it reveals the potential use of the AQA method in ASD diagnoses.

Original language	English
Title of host publication	2023 International Conference on Machine Learning and Cybernetics (ICMLC)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9798350303780
ISBN (Print)	9798350303797
DOIs	https://doi.org/10.1109/ICMLC58545.2023.10327994
Publication status	Published - 28 Nov 2023
Event	The 22nd International Conference on Machine Learning and Cybernetics - Adelaide, Australia Duration: 9 Jul 2023 → 11 Jul 2023

Publication series

Name	2023 International Conference on Machine Learning and Cybernetics (ICMLC)
Publisher	IEEE
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	The 22nd International Conference on Machine Learning and Cybernetics
Abbreviated title	ICMLC
Country/Territory	Australia
City	Adelaide
Period	9/07/23 → 11/07/23

Keywords

AQA
ASD
behaviour evaluation
CNN-LSTM
skeleton

Access to Document

10.1109/ICMLC58545.2023.10327994

Zhang_Zhou_Liu_2023_AAM
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 294 KB

Cite this

@inproceedings{bf157be039e7432d9999e4b66320e2c2,

title = "Action quality assessment methods for ASD behaviour evaluation",

abstract = "Given the current increasing prevalence of autism, expensive and time-consuming manual diagnosis is highly detrimental to the management of the condition. With the development of computer-based methods of human behavioural analysis, these methods are expected to provide more accurate, objective and reproducible methods of early screening and diagnosis of autism. To advance the field of behavioural quantification in autism research, this study utilises human skeletal behavioural data from publicly available autism datasets and ADOS scores from clinical professionals in a first attempt to build deep neural networks that can predict ADOS scores from behavioural data using the AQA approach. This paper finds a moderately correlated between the ground truth ADOS score and the predicted ADOS score, it reveals the potential use of the AQA method in ASD diagnoses.",

keywords = "AQA, ASD, behaviour evaluation, CNN-LSTM, skeleton",

author = "Dinghuang Zhang and Dalin Zhou and Honghai Liu",

year = "2023",

month = nov,

day = "28",

doi = "10.1109/ICMLC58545.2023.10327994",

language = "English",

isbn = "9798350303797",

series = "2023 International Conference on Machine Learning and Cybernetics (ICMLC)",

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

booktitle = "2023 International Conference on Machine Learning and Cybernetics (ICMLC)",

address = "United States",

note = "The 22nd International Conference on Machine Learning and Cybernetics, ICMLC ; Conference date: 09-07-2023 Through 11-07-2023",

}

Zhang, D, Zhou, D & Liu, H 2023, Action quality assessment methods for ASD behaviour evaluation. in 2023 International Conference on Machine Learning and Cybernetics (ICMLC). 2023 International Conference on Machine Learning and Cybernetics (ICMLC), Institute of Electrical and Electronics Engineers Inc., The 22nd International Conference on Machine Learning and Cybernetics, Adelaide, Australia, 9/07/23. https://doi.org/10.1109/ICMLC58545.2023.10327994

Action quality assessment methods for ASD behaviour evaluation. / Zhang, Dinghuang; Zhou, Dalin; Liu, Honghai.
2023 International Conference on Machine Learning and Cybernetics (ICMLC). Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Conference on Machine Learning and Cybernetics (ICMLC)).

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

TY - GEN

T1 - Action quality assessment methods for ASD behaviour evaluation

AU - Zhang, Dinghuang

AU - Zhou, Dalin

AU - Liu, Honghai

PY - 2023/11/28

Y1 - 2023/11/28

N2 - Given the current increasing prevalence of autism, expensive and time-consuming manual diagnosis is highly detrimental to the management of the condition. With the development of computer-based methods of human behavioural analysis, these methods are expected to provide more accurate, objective and reproducible methods of early screening and diagnosis of autism. To advance the field of behavioural quantification in autism research, this study utilises human skeletal behavioural data from publicly available autism datasets and ADOS scores from clinical professionals in a first attempt to build deep neural networks that can predict ADOS scores from behavioural data using the AQA approach. This paper finds a moderately correlated between the ground truth ADOS score and the predicted ADOS score, it reveals the potential use of the AQA method in ASD diagnoses.

AB - Given the current increasing prevalence of autism, expensive and time-consuming manual diagnosis is highly detrimental to the management of the condition. With the development of computer-based methods of human behavioural analysis, these methods are expected to provide more accurate, objective and reproducible methods of early screening and diagnosis of autism. To advance the field of behavioural quantification in autism research, this study utilises human skeletal behavioural data from publicly available autism datasets and ADOS scores from clinical professionals in a first attempt to build deep neural networks that can predict ADOS scores from behavioural data using the AQA approach. This paper finds a moderately correlated between the ground truth ADOS score and the predicted ADOS score, it reveals the potential use of the AQA method in ASD diagnoses.

KW - AQA

KW - ASD

KW - behaviour evaluation

KW - CNN-LSTM

KW - skeleton

U2 - 10.1109/ICMLC58545.2023.10327994

DO - 10.1109/ICMLC58545.2023.10327994

M3 - Conference contribution

SN - 9798350303797

T3 - 2023 International Conference on Machine Learning and Cybernetics (ICMLC)

BT - 2023 International Conference on Machine Learning and Cybernetics (ICMLC)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - The 22nd International Conference on Machine Learning and Cybernetics

Y2 - 9 July 2023 through 11 July 2023

ER -

Action quality assessment methods for ASD behaviour evaluation

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this