Correlation Analysis on the Courses of Civil Engineering Based on Association Rules Mining
- DOI
- 10.2991/assehr.k.200801.006How to use a DOI?
- Keywords
- association rules, Apriori, Civil Engineering, course, correlation analysis
- Abstract
The talent training program is the overall design and planning of higher professional education, and has a decisive role in ensuring the quality of talent training. The training objectives, graduation requirements, curriculum system, syllabus and evaluation system contained in the talent training program have a strict logical relationship. The curriculum setting and course structure are the key points for the implementation of the talent training program. Professional education courses in Civil Engineering include mathematics curriculum group, mechanics curriculum group and design curriculum group. In this paper, seven representative courses in the three curriculum groups are selected. The final academic records of 249 students in three grades are used as research objects. By using the association rule mining algorithm — Apriori, this paper discusses the implementation process of data mining technology and clarifies the degree of relationship among the courses. The analysis results can provide important references for the curriculum system setting and structure adjustment, targeting the key and difficult curriculum, teaching reform and academic learning monitoring and forecasting.
- Copyright
- © 2020, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Chuanteng Huang AU - Shuang Pu PY - 2020 DA - 2020/08/01 TI - Correlation Analysis on the Courses of Civil Engineering Based on Association Rules Mining BT - Proceedings of the 2020 International Conference on Social Science, Economics and Education Research (SSEER 2020) PB - Atlantis Press SP - 28 EP - 32 SN - 2352-5398 UR - https://doi.org/10.2991/assehr.k.200801.006 DO - 10.2991/assehr.k.200801.006 ID - Huang2020 ER -