<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>To improve the teaching level of saxophone performance in colleges and universities, this paper constructs a saxophone performance education optimization platform based on Bayesian theory. Bayesian clustering is used to informally cluster the saxophone performance education situation in colleges and universities, and the maximum likelihood algorithm is used to calculate the student behavior parameters. The Bayesian network tracking technique analyzes all learning behavior indicators to serve as a reference to obtain labels of learner motivation. To ensure the validity of the feedback metrics, the Bayesian stochastic calculation method was invoked to calculate the AUC (metric) mean ratio of the three feedback metrics. A practical teaching analysis was conducted to verify the platform’s timeliness. The results show that: The response time of login and resource search of the platform constructed in this paper is less than 2.5s and 1.2s, respectively, and the AUC mean ratio of three feedback metrics, namely, download rate, registration rate, and click rate, has improved by about 0.75%. Moreover, the positive attitude of university students towards learning has reached 88%. This shows the reliability of the educational platform constructed in this paper in optimizing higher education saxophone performance education, which can effectively improve the teaching level of saxophone performance education.</p>
</abstract>

To improve the teaching level of saxophone performance in colleges and universities, this paper constructs a saxophone performance education optimization platform based on Bayesian theory. Bayesian clustering is used to informally cluster the saxophone performance education situation in colleges and universities, and the maximum likelihood algorithm is used to calculate the student behavior parameters. The Bayesian network tracking technique analyzes all learning behavior indicators to serve as a reference to obtain labels of learner motivation. To ensure the validity of the feedback metrics, the Bayesian stochastic calculation method was invoked to calculate the AUC (metric) mean ratio of the three feedback metrics. A practical teaching analysis was conducted to verify the platform’s timeliness. The results show that: The response time of login and resource search of the platform constructed in this paper is less than 2.5s and 1.2s, respectively, and the AUC mean ratio of three feedback metrics, namely, download rate, registration rate, and click rate, has improved by about 0.75%. Moreover, the positive attitude of university students towards learning has reached 88%. This shows the reliability of the educational platform constructed in this paper in optimizing higher education saxophone performance education, which can effectively improve the teaching level of saxophone performance education.

Reform and innovation of saxophone teaching mode in colleges and universities based on Bayesian model

Conservatory of Music, Guiyang University

Applied Mathematics and Nonlinear Sciences

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

To improve the teaching level of saxophone performance in colleges and universities, this paper constructs a saxophone performance education optimization...

Reform and innovation of saxophone teaching mode in colleges and universities based on Bayesian model

Online veröffentlicht: 09. Aug. 2023

Seitenbereich: -

Eingereicht: 28. Okt. 2022

Akzeptiert: 17. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00155

Schlüsselwörter
Bayesian theory, Saxophone performance education optimization platform, Maximum likelihood algorithm, AUC mean ratio, Network tracking technique

© 2023 Yukun Lyu et al., published by Sciendo

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

Reform and innovation of saxophone teaching mode in colleges and universities based on Bayesian model

Online veröffentlicht: 09. Aug. 2023

Seitenbereich: -

Eingereicht: 28. Okt. 2022

Akzeptiert: 17. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00155

SchlüsselwörterBayesian theory, Saxophone performance education optimization platform, Maximum likelihood algorithm, AUC mean ratio, Network tracking technique

© 2023 Yukun Lyu et al., published by Sciendo

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

Schlüsselwörter
Bayesian theory, Saxophone performance education optimization platform, Maximum likelihood algorithm, AUC mean ratio, Network tracking technique