Evaluation model of college students' online learning level difference based on support vector machine
by Kunzhe Liu; Xiqiang Ge; Jiefeng Wang
International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL), Vol. 33, No. 1, 2023

Abstract: There are some problems in the evaluation of online learning level differences among college students, such as low accuracy and long evaluation time. This paper proposes a new research method by extracting online learning behaviour characteristics to determine behaviour evaluation indexes and evaluation standards. The depth of the residual neural network method is used to remove interference index. Using the Lagrange multiplier method, the evaluation problem is transformed into a dual problem. The nonlinear transformation causes us to strive for the optimal classification plane. Difference in evaluation data was accessed by using big data technology, through the normalised processing the data, in order to obtain the optimal classification function. Finally, the final evaluation results are obtained, and the online learning evaluation level differences are completed. Through comparison, the accuracy of this method is 97%, and the time cost of assessment is always less than 9.5 ms.

Online publication date: Tue, 20-Dec-2022

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 Continuing Engineering Education and Life-Long Learning (IJCEELL):
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