Improved Fuzzy Algorithm for College Students’ Academic Early Warning

The existing fuzzy clustering algorithms are mostly fuzzy comprehensive evaluation algorithms based on specific elements, but the main problem of such fuzzy algorithms is the lack of overall research on the responsible individuals and the lack of hierarchy in the algorithms. It is suitable for data...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematical problems in engineering Ročník 2022; s. 1 - 9
Hlavní autor: Chen, Siyu
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Hindawi 15.04.2022
John Wiley & Sons, Inc
Témata:
Algorithms
Clustering
College students
Colleges & universities
Data mining
Decision making
Early warning systems
Extracurricular activities
Mathematical problems
Performance evaluation
Students
Teaching
ISSN:1024-123X, 1563-5147
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The existing fuzzy clustering algorithms are mostly fuzzy comprehensive evaluation algorithms based on specific elements, but the main problem of such fuzzy algorithms is the lack of overall research on the responsible individuals and the lack of hierarchy in the algorithms. It is suitable for data mining of academic early warning systems. Therefore, an improved fuzzy algorithm based on fuzzy performance evaluation based on composite elements is proposed, and it is applied to the performance evaluation system to solve the complex problems in performance evaluation. In the process of building smart campuses in colleges and universities, academic prewarning, as the main part of smart campuses, mainly uses data mining technology to ensure students complete their studies smoothly and at the same time provides certain decision-making support for colleges and universities. Based on the research topic of the relevant departments of a certain school, this paper aims to build an academic early warning system suitable for the school to ensure that students can successfully complete their studies. The main research contents are divided into two parts: “study early warning model research” and “design and implementation of an academic early warning system.” Through analysis and experiments, it is proved that the model evaluation effect based on the algorithm improvement is the best, with recall reaching 85%, precision reaching 78.96%, and AUC reaching 80.25%.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1024-123X
1563-5147
DOI:10.1155/2022/5764800