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

<p>During rapid chemistry, cultural convergence, and technological advancement, music education management has increasingly become an interdisciplinary discipline integrating musicology, pedagogy, management, educational economics, ethics, and related technological sciences. However, in the current structure of general music education, there is still a discrepancy between the reality and the ideal in terms of philosophy, content, methods, and evaluation in the practice of family, school, and social music education. In order to solve such problems, this paper focuses on the current knowledge-tracking mechanism in music learning education. Firstly, we analyze and compare the DKT model, DKVMN model, and LSTM neural network and propose a new LMKT model after studying the advantages and disadvantages. In order to analyze the characteristics of student learning data, the student learning process was observed visually on two online publicly available real data sets, ASSISTMents2009 and ASSISTMents2015. The results show that the AUC value of the LMKT model proposed in this paper (73.83%) is 4.62% and 1.15% higher than that of the DKT model (69.21%) and the DKVMN model (72.68%), respectively, and that knowledge tracking is less effective as the number of clusters increases when the number of student clusters K is greater than 6. When the number of K is less than 6, the knowledge-tracking effect becomes better as the number of clusters increases. It is finally concluded that the LMKT model shows a better tracking effect, and the clustering feature improves the knowledge-tracking ability of the model.</p>
</abstract>

During rapid chemistry, cultural convergence, and technological advancement, music education management has increasingly become an interdisciplinary discipline integrating musicology, pedagogy, management, educational economics, ethics, and related technological sciences. However, in the current structure of general music education, there is still a discrepancy between the reality and the ideal in terms of philosophy, content, methods, and evaluation in the practice of family, school, and social music education. In order to solve such problems, this paper focuses on the current knowledge-tracking mechanism in music learning education. Firstly, we analyze and compare the DKT model, DKVMN model, and LSTM neural network and propose a new LMKT model after studying the advantages and disadvantages. In order to analyze the characteristics of student learning data, the student learning process was observed visually on two online publicly available real data sets, ASSISTMents2009 and ASSISTMents2015. The results show that the AUC value of the LMKT model proposed in this paper (73.83%) is 4.62% and 1.15% higher than that of the DKT model (69.21%) and the DKVMN model (72.68%), respectively, and that knowledge tracking is less effective as the number of clusters increases when the number of student clusters K is greater than 6. When the number of K is less than 6, the knowledge-tracking effect becomes better as the number of clusters increases. It is finally concluded that the LMKT model shows a better tracking effect, and the clustering feature improves the knowledge-tracking ability of the model.

Analysis of the application of music curriculum education integrating modern network technology

Applied Mathematics and Nonlinear Sciences

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

During rapid chemistry, cultural convergence, and technological advancement, music education management has increasingly become an interdisciplinary discipline...

Analysis of the application of music curriculum education integrating modern network technology

Pubblicato online: 01 giu 2023

Pagine: -

Ricevuto: 18 lug 2022

Accettato: 07 dic 2022

DOI: https://doi.org/10.2478/amns.2023.1.00326

Parole chiave
Modern web technology, Music education, Application analysis, Knowledge tracking model

© 2023 Shipei Tu, published by Sciendo

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

Analysis of the application of music curriculum education integrating modern network technology

Pubblicato online: 01 giu 2023

Pagine: -

Ricevuto: 18 lug 2022

Accettato: 07 dic 2022

DOI: https://doi.org/10.2478/amns.2023.1.00326

Parole chiaveModern web technology, Music education, Application analysis, Knowledge tracking model

© 2023 Shipei Tu, published by Sciendo

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

Parole chiave
Modern web technology, Music education, Application analysis, Knowledge tracking model