Investigating Musical Expression through Body Movement in Early Childhood: A Device-based Quantitative Approach to Extract Various Feature Quantities | Chapter 3 | New Horizons of Science, Technology and Culture Vol. 1

In this study, 3-year-old, 4-year-old, and 5-year-old children in three facilities (n=101) participated in the movement analysis during musical expression utilising a 3D motion capture system (MVN). Quantitative analysis, such as a three-way non-repeated analysis of variance of the captured data, yielded feature quantities that were implemented in machine learning algorithms with multiple classifiers. Results of classification regarding the developmental degree of musical expression in early childhood indicated higher accuracy with MLP-NN and SVM. Furthermore, using an eye tracking system (Tobii Glass 3) connected with MVN, simultaneous analysis of eye and body movements during musical expression improved the accuracy of MLP-NN to 74.42%. Measurements were conducted indoors at the facility under the same lighting conditions as the children's daily lives, so there was almost no effect of ambient light during eye tracking. Based on these findings, the MVN system, connected to Meta gloves, was employed to conduct detailed movement analysis focusing on hand movements during musical expression with 3-year-old, 4-year-old, and 5-year-old children in three facilities (n=86). Meta gloves, developed by MANUS Technology Group, are a small and lightweight system weighing 70 grams, which places almost no strain on the finger movements of the participating children. This system has a finger sensor that detects the absolute value of the fingertip position and the three-axis rotation angle of the finger relative to a model of the back of the hand at a frequency of 120 Hz. Because the Meta gloves are small and lightweight, the burden on fine motor control was suppressed. Quantitative analysis of this data revealed that the third metacarpal bone plays a dual role: supporting finger movements and activating the proximal and distal phalanges to facilitate the expression of imagined imagery. Admittedly, methodological limitations, such as lighting conditions and small, lightweight devices having some effect on the acquired data, are an area for further consideration. Utilising newly extracted feature quantities from this quantitative analysis is expected to improve the accuracy of classifying the developmental degree of musical expression. This, in turn, will provide objective criteria for evaluating developmental progress and necessary musical experiences, contributing to improvements in early childhood music education practices.

 

Author (s) Details

 

Mina Sano
Tokoha University, Shizuoka, Japan.

 

Please see the book here:- https://doi.org/10.9734/bpi/nhstc/v1/5557

Applying Machine Learning to Assess Musical Development in Early Childhood Using Eye and Body Movement Data | Chapter 10 | An Overview of Literature, Language and Education Research Vol. 6

Musical expression in early childhood includes a lot of elements of body movement. The author has conducted movement analysis using the MVN system as 3D motion capture to quantify the body movement in musical expression in early childhood from 2015year.

 

Recently, as well as body movement, eye movements are considered to interact with the external environment. Tobii eye tracking system was utilized to attempt to evaluate measure and score responses of children to music experience.

 

In this study, the author tried to apply machine learning to asses musical development in early childhood using eye and body movement data based on my previous studies. To carry out the feasibility of this study, firstly, effective feature quantities were extracted from the results of the quantitative analysis regarding body movement in musical expression in early childhood organized for the past four years. As a result, specifically, the movement of the right hand was characteristic, and a statistically significant difference was observed in the data of the right hand regarding the moving distance, the moving average velocity, the moving average acceleration and the moving smoothness compared to other measurement data. Secondly, based on eye-tracking data collected over four years in my study of early childhood children singing, the author conducted a simultaneous analysis of both eye movement and body movement in musical expression to acquire quantitative data in 2022 and 2023. Visual information is important to stabilize posture in humans as well as express body movements. Some recent studies assessed stable postural control situations with eye tracking but little research was reported to focus on music-induced movements, especially for early childhood. Thirdly, the feature quantities were extracted from the data for two years both eye movement and body movement in musical expression by simultaneous analysis, and were implemented into machine learning using several classifiers such as MLP(NN) and SVM. The author compared the discrimination accuracy between using feature quantities of both eye and body movement as a result of simultaneous analysis and using feature quantities of only body movement.

 

As a result, the discrimination accuracy using feature quantities of both eye and body movement by simultaneous analysis was higher than using feature quantities of only body movement. Specifically, the discrimination accuracy using MLP(NN) was higher than other several classifiers.

 

In this way, the author designed a methodology to include eye movement data such as gaze fixations and saccadic movements in coordinated simultaneous body motion captured kinetics data. It was verified that the author has progressed more appropriate method of machine learning using effective feature quantities based on the result of simultaneous analysis of both eye movement and body movement in musical expression.

Author (s) Details

Mina Sano
Tokoha University, Japan.

 

Please see the book here:- https://doi.org/10.9734/bpi/aoller/v6/2825

Quantifying Musical Element Recognition in Early Childhood: A Body Movement Analysis Approach | Chapter 9 | An Overview of Literature, Language and Education Research Vol. 7

It is widely viewed that music has the capacity to induce human body movements. Such movements range from small body parts action to full body dance. At the same time, music educators of early childhood children generally experience such movements evolve as children advance in the development stage of recognition of musical elements. Such progress is often perceived as consistent by expert educators, however, movement sophistication was hard to quantify. In this study, the author presents methods to objectively track the musical development of children by statistically processing data obtained from a 3D motion capture system. The author first, devised a four-phased Music Expression Bringing-up (MEB) program to enhance music recognition of children and devised associated the Music Test. The Music test consists of 6 areas in which each area includes 10 test items to evaluate recognition achievements based on the respective development phase. Secondly, the change in body movement in musical expression was quantitatively analyzed utilizing the MVN system as 3D motion capture by every phase of the MEB program during the practice for 3-year-old, 4-year-old and 5-year-old children. In motion capture study, 3-year-old (n=112), 4-year-old (n=94), and 5-year-old (n=111) children participated in each phase’s activity of MEB program from 2016 to 2019. Secondly, 4-year-old and 5-year-old children participated in the Music Test at the beginning of the first phase and the end of the fourth phase of MEB program practice. Thirdly, a quantitative analysis was carried out regarding both the data of body movement in musical expression and Music Test scores. As a result, applying such movement results of 4 and 5-year-old children at multiple development phases with MEB program results of relevant phases, a statistically significant relationship was attained in the analysis of variance and the relationship was depicted in Circular Affect. Results indicated as the activity phase progressed and the recognition of musical elements increased, characteristic changes in the movements of the right hand were observed, such as an increase in the moving average acceleration in the third phase of the MEB program. The integration of 3D motion capture with the MEB program provides a quantitative method for assessing musical element recognition in early childhood, offering educators a tool to track developmental progress through body movement analysis.

 

Author (s) Details

Mina Sano
Tokoha University, Shizuoka, Japan.

 

Please see the book here:- https://doi.org/10.9734/bpi/aoller/v7/3224

Exploring Effective Feature Quantities for Machine Learning to Predict Developmental Degree of Musical Expression in Early Childhood: A Recent Study | Chapter 7 | Current Research in Language, Literature and Education Vol. 7

In order to create an evaluation model based on those feature quantities, this study aims to identify the developmental features of musical expression in young children from the perspective of changing body movement aspects.

In this study, the author examined brand-new feature amounts for machine learning classification and discriminating of the level of musical expression in young children. First, the author provided evidence for the findings of statistical analysis of movement components in early childhood musical expression utilising 3D motion capture and machine learning to assess levels of musical development. In this study, full-body motions were first subjected to an ANOVA. A three-way non-repeated ANOVA was used to quantitatively assess the motion capture data of 3-, 4-, and 5-year-old children in child facilities (n=178). Consequently, there was a statistically significant variation in how the bodily parts moved. Right hand movements, including moving distance and moving average acceleration, showed a significant difference. Second, machine learning techniques such as decision trees, the Sequential Minimum Optimization algorithm (SMO), support vector machines (SVM), and neural networks (multi-layer perceptrons) were used to construct classification models for evaluating the degree of musical development as determined by educators using simultaneously recorded children's video and related motion capture data. The multi-layer perceptron gave the best confusion matrix results among the various trained classification models, and it showed reasonable classifying precision and utility to support educators in assessing children's musical development stages. As a result of multilayered perceptron machine learning, the movement of the pelvis has a significant correlation with the degree of musical progression. Its consistency in categorization accuracy suggests that the model may be used to assist educators in determining how well youngsters can express themselves musically.

The author then provided some results of eye tracking on musical expression in a recent study based on the classification and discriminating by machine learning of the developmental degree of musical expression in order to figure out additional feature quantities. In order to research human bodily reaction in relation to cognitive and emotional components, eye-tracking is now often employed. According to the author, eye-tracking data on gazepath, fixations, and saccades provides information that can help us grasp musical expression. Children at child facilities aged 3, 4, and 5 years old (n=118) took part in eye tracking while singing a song while wearing an eye tracker (Tobii3). On the calculated data, quantitative analysis using ANOVA was done. The rise in data, including the frequency and magnitude of saccades as well as the saccade's moving average velocity, revealed that saccades during early childhood musical expression tended to be greater in major keys than in minor keys. The outcome demonstrated that it was possible to extract useful feature values for machine learning from the computed data of eye movement during musical expression.

Author(s) Details:

Mina Sano,
Tokoha University, Japan.

Please see the link here: https://stm.bookpi.org/CRLLE-V7/article/view/7540

Predicting Developmental Degrees of Music Expression in Early Childhood by Machine Learning Classifiers with 3D Motion Captured Body Movement Data: A Recent Study | Chapter 5 | Modern Perspectives in Language, Literature and Education Vol. 7

 Researchers have continued to be intrigued by the interaction between a child's developmental level of music and their musical output. Currently, one notable part will be to study such connection using a quantitative technique and to discover some predicted methodology to statistically repeat such interaction. The author of this work collected developmental features of musical expressions in early infancy from viewpoints of aspects of body movement and applied a machine learning-based classification algorithm to those feature quantities obtained from the participant children. In two studies, classification models were applied to the feature quantity for 3-, 4-, and 5-year-olds. capture. A three-way nonrepeated ANOVA was used to highlight developmental degree and extract feature quantity, and a statistically significant difference in the movement data analysed of the moving average of distance such as the pelvis and right hand, the moving average of acceleration such as the right hand, and the movement smoothness of the right foot was observed. After letting classifiers train with categorical variables of developmental degree evaluated by the author with simultaneously recorded video, the author classified the developmental degree of children's musical expression using machine learning classifiers using feature quantities of motion capture data. The report of the author Multilayer Perceptron Neural Network is the best classifier, and Boosted Trees is the second best. The sensitivity result revealed that pelvic movement was closely associated to the degree of musical development. In addition to a thorough examination of kinetic feature amounts or an increase in training sample data, classifiers such as deep learning and others might be considered to improve classification accuracy.

Author (S) Details

Mina Sano
Tokoha-University, Shizuoka, Japan.

View Book :- https://stm.bookpi.org/MPLLE-V7/article/view/2870