Advertisement

Research on College Students’ Academic Early Warning System Based on PCA-SVM

  • Xiang Chen
  • Xiuling JinEmail author
  • Geng Lin
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)

Abstract

Nowadays, how to use education industries’ data is a hot topic. Taking the scores of 70 courses of 216 students in the College of Mathematics and Data Science as the sample, the Principal Component Analysis-Support Vector Machine (PCA-SVM) model for early warning system is established by selecting the first-year course scores and graduate grades. The PCA-SVM is better than Support Vector Machine (SVM) in accuracy, probability of false alarm and F1-score. The PCA-SVM model for early warning system can provide students with more accurate academic guidance, and can provide scientific basis for teaching reform and management decision making.

Keywords

Data mining Early-warning system PCA SVM 

Notes

Acknowledgements

The first author was supported by the Science and Technology Project of Education Bureau of Fujian, China, under Grant JAT170447, and the second author was supported by the Science and Technology Project of Education Bureau of Fujian, China, under Grant JT180391.

References

  1. 1.
    Fu, Y.L.: The application of data mining’s C4.5 algorithm in the students’ result analysis. J. Chongqing Univ. Technol. (Nat. Sci.) 27(11), 78–82 (2013)Google Scholar
  2. 2.
    Li, H.L.: Study on improvement of using Naive Bayes algorithm to forecast student’s learning indicator. Inf. Research. 212(6), 22–26, 32 (2015)Google Scholar
  3. 3.
    Yu, C.Y.: Higher mathematics teaching quality evaluation model based on AHP-PCA-SVM. Bull. Sci. Technol. 29(10), 229–231 (2013)Google Scholar
  4. 4.
    Long, J.Y.: Analysis of student’s achievements based on mean cluster and decision tree algorithm. Comput. Modernization 226(6), 79–83 (2014)Google Scholar
  5. 5.
    He, C., Song, J., Zhou, T.: Curriculum association model and student performance prediction based on spectral clustering of frequent pattern. Appl. Res. Comput. 32(10), 2930–2932 (2015)Google Scholar
  6. 6.
    Li, X.L., Gu, J.S.: Empirical analysis of college grades based on quantile regression. Coll. Math. 29(3), 118–123 (2013)Google Scholar
  7. 7.
    Luo, Y.G.: Improved genetic algorithm based student score prediction model. Bull. Sci. Technol. 28(10), 223–225 (2012)Google Scholar
  8. 8.
    Yue, Q., Wen, X.: A research on evaluation model of teaching quality based on BP neural network and genetic algorithm. J. Inner Mongolia Univ. (Nat. Sci. Ed.) 49(2), 204–211 (2018)Google Scholar
  9. 9.
    Kong, Y., Cao, C.T.: Study on sports teaching quality evaluation based on comprehensive integrated valuation method and SVM. Microcomput. Appl. 33(11), 12–15 (2017)Google Scholar
  10. 10.
    Gareth, J., Daniela, W., Trevor, H., Robert, T.: An Introduction to Statistical Learning: With Applications in R. China Machine Press, Beijing (1999)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.College of Mathematics and Data ScienceMinjiang UniversityFuzhouChina

Personalised recommendations