AGA-BP algorithm for the evaluation model of teaching quality of dance drama performance
by Yueying Xiao
International Journal of Networking and Virtual Organisations (IJNVO), Vol. 28, No. 2/3/4, 2023

Abstract: Firstly, the evaluation system was determined, then the AGA and BP neural network algorithms were improved, and finally the entropy weight method was used to construct the dance drama performance teaching quality evaluation model. The optimal hidden layer node of the BP algorithm is 5 and the maximum number of iterations is 120. The corresponding MSE values of the two neural network algorithms, BP and AGA-BP, are 0.0486 and 0.0246 respectively at the maximum number of 120 iterations. The number of convergence of the AGA-BP algorithm is about 6; the convergence value of the sum of squared errors is 0.21, with a 75% improvement in convergence speed and an 80% reduction in the average sum of squared errors. The prediction results of the dance performance quality evaluation show that the prediction accuracy of the AGA-BP prediction model ranges from 0.97 to 1.00.

Online publication date: Wed, 04-Oct-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Networking and Virtual Organisations (IJNVO):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com