2023 Fiscal Year Final Research Report
Quantitative study by simultaneous analysis of eye movements and whole body movements during musical expression in early childhood
| Project/Area Number |
21K02369
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 09030:Childhood and nursery/pre-school education-related
|
|---|
| Research Institution | Tokoha University |
|---|
Principal Investigator |
Sano Mina 常葉大学, 保育学部, 教授 (00341785)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 身体的な動きと眼球運動の同時解析 / 幼児の音楽的表現の発達過程 / 定量的分析 / 判別精度 / 機械学習 |
|---|
| Outline of Final Research Achievements |
This study aims to verify a discriminative method for assessing developmental stages of musical expression in early childhood utilizing machine learning based on various feature quantities extracted from the simultaneous analysis of full body movement data in coordinated manner with eye movement data during musical expression. 3-year-old, 4-year-old, and 5-year-old children in six children’s facilities participated in the simultaneous analysis of both full-body movement and eye movement during musical expression(n=103). The feature quantities were implemented to machine learning using various classifiers to examine a discrimination accuracy. Discrimination accuracy by machine learning was improved when feature quantities of body movement and eye movement were simultaneously analyzed (74.42%). The research findings show that feature quantities based on both body movements and eye movements are effective in capturing the developmental process of musical expression in early childhood.
|
| Free Research Field |
音楽教育 幼児教育
|
| Academic Significance and Societal Importance of the Research Achievements |
先行研究に見られなかった幼児の音楽的表現の発達過程を判別する定量的な手法を発展させるために、筆者は分類判別のより客観的な指標を提示した。その研究成果によって、あまり経験の無い保育・幼児教育者も個々の幼児により適切な音楽経験を提供することができるため、音楽教育支援および保育・幼児教育の向上に資することができるという点に社会的意義がある。本研究で、筆者は、これまでの音楽的表現における身体的な動きの定量的分析に加えて、身体的な動きと眼球運動の同時解析を行った。定量的分析結果から抽出した特徴量により機械学習を行った結果、判別精度の改善により同時解析の有効性を検証したことに、学術的意義があると考える。
|
