Multiview child motor development dataset for AI-driven assessment of child development
GigaScience · 2022
DOI: 10.1093/gigascience/giad039 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, 2022. Verfasst von Hye Hyeon Kim und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea. Hauptthemen laut MEDLINE: Child Development, Artificial Intelligence. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Center for Mental Health, National Information Society Agency.
Abstract (Originalsprache)
Background
Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities.
Results
The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance.
Conclusion
Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
- MISO Info Tech Co. Ltd., Seoul 06222, Republic of Korea.
- Maumdri Co. Ltd., Muan-gun, Jeollanam-do 58563, Republic of Korea.
- Lumanlab, Inc., Seoul 05836, Republic of Korea.
- Division of Child and Adolescent Psychiatry, Department of Psychiatry, Seoul National University College of Medicine, Seoul 03080, Republic of Korea.
- Institute of Human Behavioral Medicine, Seoul National University Medical Research Center, Seoul 03080, Republic of Korea.
ORCID-Profile: Hye Hyeon Kim, Jin Yong Kim, Joo Hyun Lee, Jong Hyun Kim, Yu Rang Park
Förderung
- National Center for Mental Health
- National Information Society Agency
Zitieren
APA
Kim, H. H., Kim, J. Y., Jang, B. K., Lee, J. H., Kim, J. H., Lee, D. H., Yang, H. M., Choi, Y. J., Sung, M. J., Kang, T. J., Kim, E., Oh, Y. S., Lim, J., Hong, S. B., Ahn, K., Park, C. L., Kwon, S. M., & Park, Y. R. (2022). Multiview child motor development dataset for AI-driven assessment of child development. GigaScience. https://doi.org/10.1093/gigascience/giad039
Vancouver
Kim HH, Kim JY, Jang BK, Lee JH, Kim JH, Lee DH, et al. Multiview child motor development dataset for AI-driven assessment of child development. GigaScience. 2022. doi:10.1093/gigascience/giad039
BibTeX
@article{Kim2022,
author = {Kim, Hye Hyeon and Kim, Jin Yong and Jang, Bong Kyung and Lee, Joo Hyun and Kim, Jong Hyun and Lee, Dong Hoon and Yang, Hee Min and Choi, Young Jo and Sung, Myung Jun and Kang, Tae Jun and Kim, Eunah and Oh, Yang Seong and Lim, Jaehyun and Hong, Soon-Beom and Ahn, Kiok and Park, Chan Lim and Kwon, Soon Myeong and Park, Yu Rang},
title = {Multiview child motor development dataset for AI-driven assessment of child development},
journal = {GigaScience},
year = {2022},
doi = {10.1093/gigascience/giad039}
}
EUVIMED