<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Preschool education is vital for shaping the foundation of young children’s development across cognitive, social, emotional, and physical dimensions. Dance courses are often included in preschool curricula to foster creativity, expression, physical coordination, and emotional regulation. Understanding and interpreting emotions conveyed through dance movements can be instrumental in enhancing children’s emotional intelligence and overall well-being. This paper investigates an innovative approach to intelligent assistance in preschool dance courses by utilizing deep learning methods for emotion recognition within dance movements. The proposed model integrates deep and shallow features to improve the precision of emotion detection, offering a promising means to facilitate personalized and interactive learning experiences. First, emotions in dance are extracted through a multi-layer convolutional neural network, and high-level features are fused with low-level features. Then, the fused features of different depths are used as the basis for emotion recognition. The convolutional neural network’s fully connected layer outputs the emotional probabilities of dance movements, allowing for the identification of emotional categories in dance movements. Finally, experiments are conducted using the fusion of features from different convolutional layers, validating the effectiveness of the proposed method in emotion recognition.</p>
</abstract>

Preschool education is vital for shaping the foundation of young children’s development across cognitive, social, emotional, and physical dimensions. Dance courses are often included in preschool curricula to foster creativity, expression, physical coordination, and emotional regulation. Understanding and interpreting emotions conveyed through dance movements can be instrumental in enhancing children’s emotional intelligence and overall well-being. This paper investigates an innovative approach to intelligent assistance in preschool dance courses by utilizing deep learning methods for emotion recognition within dance movements. The proposed model integrates deep and shallow features to improve the precision of emotion detection, offering a promising means to facilitate personalized and interactive learning experiences. First, emotions in dance are extracted through a multi-layer convolutional neural network, and high-level features are fused with low-level features. Then, the fused features of different depths are used as the basis for emotion recognition. The convolutional neural network’s fully connected layer outputs the emotional probabilities of dance movements, allowing for the identification of emotional categories in dance movements. Finally, experiments are conducted using the fusion of features from different convolutional layers, validating the effectiveness of the proposed method in emotion recognition.

Intelligent Assistance Method for Preschool Education Dance Curriculum Based on Deep Learning

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Preschool education is vital for shaping the foundation of young children’s development across cognitive, social, emotional, and physical dimensions. Dance...

Intelligent Assistance Method for Preschool Education Dance Curriculum Based on Deep Learning

Pubblicato online: 10 lug 2024

Pagine: -

Ricevuto: 26 mar 2024

Accettato: 20 giu 2024

DOI: https://doi.org/10.2478/amns-2024-1833

Parole chiave
Deep Learning, Neural Networks, Machine Learning

© 2024 Qin Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Intelligent Assistance Method for Preschool Education Dance Curriculum Based on Deep Learning

Pubblicato online: 10 lug 2024

Pagine: -

Ricevuto: 26 mar 2024

Accettato: 20 giu 2024

DOI: https://doi.org/10.2478/amns-2024-1833

Parole chiaveDeep Learning, Neural Networks, Machine Learning

© 2024 Qin Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Deep Learning, Neural Networks, Machine Learning