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

<p>Deep learning significantly enhances Civic and Political Education in higher vocational colleges and universities by facilitating a nuanced understanding of students’ cognition of learning content, engagement in the learning process, and perceptions of the educational environment. This study involved collecting behavioral data from students in Civic and Political Education classes and applying the YOLOv5s algorithm—an advancement in deep learning networks—to extract and detect student behavioral features. Additionally, the enhanced ShuffleNetV2 algorithm was employed to classify and identify these features. Based on these methodologies, a student behavior recognition system was developed for Civics classrooms, and its practical application was evaluated. The findings indicate that the implementation of this recognition system resulted in increased classroom activity and engagement, with 70% of the participants demonstrating hand-raising and speaking behaviors. There was a statistically significant enhancement in students’ Civic learning behaviors following the system’s application in teaching (P&lt;0.05). This study underscores the potential of digital intelligence technology to foster precise and intelligent educational practices in Civics education.</p>
</abstract>

Deep learning significantly enhances Civic and Political Education in higher vocational colleges and universities by facilitating a nuanced understanding of students’ cognition of learning content, engagement in the learning process, and perceptions of the educational environment. This study involved collecting behavioral data from students in Civic and Political Education classes and applying the YOLOv5s algorithm—an advancement in deep learning networks—to extract and detect student behavioral features. Additionally, the enhanced ShuffleNetV2 algorithm was employed to classify and identify these features. Based on these methodologies, a student behavior recognition system was developed for Civics classrooms, and its practical application was evaluated. The findings indicate that the implementation of this recognition system resulted in increased classroom activity and engagement, with 70% of the participants demonstrating hand-raising and speaking behaviors. There was a statistically significant enhancement in students’ Civic learning behaviors following the system’s application in teaching (P<0.05). This study underscores the potential of digital intelligence technology to foster precise and intelligent educational practices in Civics education.

Exploring the Strategies of Civic Education in Higher Vocational Colleges and Universities Based on Deep Learning

Nanjing Vocational University of Industry Technology

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Deep learning significantly enhances Civic and Political Education in higher vocational colleges and universities by facilitating a nuanced understanding of...

Exploring the Strategies of Civic Education in Higher Vocational Colleges and Universities Based on Deep Learning

Online veröffentlicht: 03. Juni 2024

Seitenbereich: -

Eingereicht: 26. Feb. 2024

Akzeptiert: 02. Mai 2024

DOI: https://doi.org/10.2478/amns-2024-1357

Schlüsselwörter
Deep learning, Convolutional neural network, YOLOv5s, ShuffleNetV2, Civics education

© 2024 Jiping Huang, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Exploring the Strategies of Civic Education in Higher Vocational Colleges and Universities Based on Deep Learning

Online veröffentlicht: 03. Juni 2024

Seitenbereich: -

Eingereicht: 26. Feb. 2024

Akzeptiert: 02. Mai 2024

DOI: https://doi.org/10.2478/amns-2024-1357

SchlüsselwörterDeep learning, Convolutional neural network, YOLOv5s, ShuffleNetV2, Civics education

© 2024 Jiping Huang, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
Deep learning, Convolutional neural network, YOLOv5s, ShuffleNetV2, Civics education