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

<p>To study the direction of preschool students’ interest development, this paper proposes to mine and analyze preschool students’ interest development data using a deep learning model. This paper first introduces the basic algorithmic process of deep learning BP neural network model, then uses a genetic algorithm to optimize the traditional BP neural network to get the best performance. The deep learning model is then used to analyze the preschool students’ family income, family structure, interest cultivation direction, gender and age, and interest cultivation orientation and diversion. The lower the family income, the higher the percentage of children choosing interest classes, mostly concentrated in families with income between 2000-8000. In terms of gender, there are also differences in interest cultivation analysis, with boys favoring the cultivation of science and sports abilities such as logical thinking, technology, calculation, and sports, accounting for about 20% more than girls in general, while girls favoring the cultivation of art abilities such as dance, English, reading, and vocal music, with 15-20% more than boys. Deep learning model-based interest development for preschool students can follow the natural choices of young children and provide scientific guidance for interest triage of preschool children.</p>
</abstract>

To study the direction of preschool students’ interest development, this paper proposes to mine and analyze preschool students’ interest development data using a deep learning model. This paper first introduces the basic algorithmic process of deep learning BP neural network model, then uses a genetic algorithm to optimize the traditional BP neural network to get the best performance. The deep learning model is then used to analyze the preschool students’ family income, family structure, interest cultivation direction, gender and age, and interest cultivation orientation and diversion. The lower the family income, the higher the percentage of children choosing interest classes, mostly concentrated in families with income between 2000-8000. In terms of gender, there are also differences in interest cultivation analysis, with boys favoring the cultivation of science and sports abilities such as logical thinking, technology, calculation, and sports, accounting for about 20% more than girls in general, while girls favoring the cultivation of art abilities such as dance, English, reading, and vocal music, with 15-20% more than boys. Deep learning model-based interest development for preschool students can follow the natural choices of young children and provide scientific guidance for interest triage of preschool children.

Orientation and triage of preschool students’ interest development based on deep learning model

Applied Mathematics and Nonlinear Sciences

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

To study the direction of preschool students’ interest development, this paper proposes to mine and analyze preschool students’ interest development data using...

Orientation and triage of preschool students’ interest development based on deep learning model

Publicado en línea: 26 ago 2023

Páginas: -

Recibido: 04 oct 2022

Aceptado: 06 mar 2022

DOI: https://doi.org/10.2478/amns.2023.2.00245

Palabras clave
Genetic algorithm, Deep learning, BP neural network, Interest development

© 2023 Weiren Hao et al., published by Sciendo

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

Orientation and triage of preschool students’ interest development based on deep learning model

Publicado en línea: 26 ago 2023

Páginas: -

Recibido: 04 oct 2022

Aceptado: 06 mar 2022

DOI: https://doi.org/10.2478/amns.2023.2.00245

Palabras claveGenetic algorithm, Deep learning, BP neural network, Interest development

© 2023 Weiren Hao et al., published by Sciendo

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

Palabras clave
Genetic algorithm, Deep learning, BP neural network, Interest development