| Autor: |
Meenakshi, Sanchez, Domenic T., Peconcillo Jr., Larry B., De Vera, John V., Mahajan, Rupali, Kumar, Tribhuwan, Bhosle, Amol A. |
| Předmět: |
|
| Zdroj: |
International Journal of Next-Generation Computing; Oct2022, Vol. 13 Issue 3, p678-689, 12p |
| Abstrakt: |
The process of teaching and learning is the most powerful tool that teachers and professors have, because it is the main way that students change in the ways that teachers and professors want them to. TQM is recommended as a way to control, monitor, and improve the quality of teaching and learning strategies in the classroom. In line with the principles of TQM, evaluations of things like results and feedback are used to improve teaching and learning. The level of academic success that a program's students have may say a lot about how good that programme is. You can predict how well a student will do in school in the future by looking at how well they did in the past. After more research, it might be possible to find a link between the students' grades and their skills and interests. When teachers have this kind of information, they are better able to focus on the students who are having the most trouble. This article shows how to use feature selection and machine learning to improve the quality of teaching and learning in higher education by predicting how well a student will do in school. The performance of university students is used as an input to a classification model. First, ant colony optimization is used to choose the most important features. Then, KNN, Naive Bayes, and decision tree algorithms are used to classify the chosen data. Based on accuracy, recall, and F1 score, KNN performs better. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
