A study on the evaluation of humanistic literacy cultivation model of University English teaching based on MTCNN
by Wenfang Li
International Journal of Knowledge-Based Development (IJKBD), Vol. 13, No. 2/3/4, 2023

Abstract: To give consideration to the speed and accuracy of evaluation and reduce the experimental cost and the error caused by human operation in evaluating humanistic literacy cultivation for University English teaching, an evaluation model based on MTCNN is proposed. On the basis of CNN, AMTL is used as the main tool to adjust the adaptability of different types of subtask loss in the training process, and auxiliary tasks are introduced to iterate the evaluation model to judge the loss function and the weight change of subtasks. Determine the weight value a0 = 0.297 of the method proposed in the study. This result is more accurate than the optimal weight 0.3 obtained by the traditional MTCNN. The accuracy, sensitivity and specificity values of the proposed method are 69.83, 64.94 and 72.79, respectively, which are higher than those of other methods and have good accuracy, sensitivity and specificity. It indicates that the method can mine the information of evaluation indexes and help cultivate all-round development college students.

Online publication date: Tue, 12-Sep-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 Knowledge-Based Development (IJKBD):
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