A Machine Learning Model to Automatic Assessment of Gross Motor Development in Children using Posenet
-
Published:2023-10-10
Issue:
Volume:44
Page:e48131
-
ISSN:1679-0375
-
Container-title:Semina: Ciências Exatas e Tecnológicas
-
language:
-
Short-container-title:Semin., Exact Tech. Scienc.
Author:
Pilati Filho Edson LuizORCID, Spinosa Rodrigo Martins de OliveiraORCID, Brancher Jacques DuílioORCID
Abstract
Gross motor skills such as sitting, jumping, and running are activities that involve the large muscles of the human body. The Test of Gross Motor Development, or TGMD, is widely used by researchers, pediatricians, physiotherapists, and educators from different countries to assess these skills in children aged 3 to 11 years. An important part of the test is that the movement, performed by the children, needs to be recorded and assessed by two or more professionals. The assessment process is laborious and takes time, and its automation is one of the main points to be developed. In recent years, methods have been proposed to automate the assessment according to the TGMD. The hypothesis investigated in this work is that it is possible to induce a machine learning model to identify whether the movement executed by the child is correct, considering only the first criterion of the TGMD-3 jumping skill. The skeleton of the children was extracted using PoseNet. A dataset of 350 images of Brazilian children between 3 and 11 years old performing the preparatory movement for the jump was used. The experimental results show an accuracy of 84%.
Publisher
Universidade Estadual de Londrina
Reference21 articles.
1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., . . . Zheng, X. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Arxiv. 2. Bisi, M., Pacini Panebianco, G., Polman, R., & Stagni, R. (2017). Objective assessment of movement competence in children using wearable sensors: An instrumented version of the TGMD-2 locomotor subtest. Gait & Posture, 56, 42–48. 3. Clark, J. E. (2005). From the Beginning: A Developmental Perspective on Movement and Mobility. Quest, 57, 37–45. 4. Estimativa de pose humana em tempo real no navegador com TensorFlow.js. (2018). TensorFlow. 5. Gallahue, D., Ozmun, J., & Goodway, J. (2013). Compreendendo o desenvolvimento motor-: bebês, crianças, adolescentes e adultos. AMGH Editora.
|
|