Multi-class LDA classifier and CNN feature extraction for student performance analysis during Covid-19 pandemic

Document Type : Research Paper


Department of computer Science, Vels Institute of Science, Technology and Advanced Studies (VISTAS), Chennai, India


In our modern world, education is essential for developing high moral values and excellence in individuals. But the spread of Covid-19 widely affects the student’s education, the majority of students have continued their education via online learning platforms. The academic performance of students has been sluggish across the globe during this pandemic. This problem is solved using a multiclass Linear Discriminant Analysis (LDA) and Convolutional Neural Network (CNN) model which predicts the student learning rate and behavior. This research aims to classify the students’ performance into low, medium, and high grades in order to assist tutors in predicting the low-ranking students. The student data log is collected from the Kaggle student performance analysis dataset and pre-processed to remove the noise and non-redundance data. By analyzing the pre-processed data, the CNN extracts feature that are based on student interest and subjective pattern sequences. Then extracted features are filtered by the Minimum Redundancy Maximum Relevance(mRMR) method. mRMR selects the best features and dilutes the least one which handles each feature separately. The feature weights are measured by Stochastic Gradient Descent (SGD) and updated for better feature learning by CNN. At the last stage, the Multi-class LDA classifier evaluates the result into categorized classes. Based on the prediction, the tutors can easily find the low ranks of students who need a high preference for improving their academic performance. Experiments showed that the proposed model achieves greater accuracy (96.5%), precision (094), recall (092), F-score (095), and requires less computation time than existing methods.


[1] M. Al-Okaily, H. Alqudah, A. Matar, A. Lutfi and A. Taamneh, Dataset on the acceptance of e-learning system
among universities students under the COVID-19 pandemic conditions, Data Brief 32 (2020) 106176.
[2] J. Di and Z. Shi, Prediction model of breast cancer based on mRMR feature selection, Inter. Conf. Neural Info.
Proces. (2020) 32–40.
[3] G. Ilieva, T. Yankova, S. Klisarova-Belcheva and S. Ivanova, Effects of COVID-19 pandemic on university students’
learning, Inf. 12(4) 2021.
[4] B. Khan, S.F. Khan, T. Rahman, I. Khan, I. Ullah, A.U. Rehman, M. Baz, H. Hamam and O. Cheikhrouhou,
Student-performulator: student academic performance using hybrid deep neural network, Sustainability 13(17)
[5] A. Khattar, P.R. Jain and S.M.K. Quadri, Effects of the disastrous pandemic COVID 19 on learning styles,
activities and mental health of young Indian students - A machine learning approach, 4th Inter. Conf. Intell.
Comput. Cont. Syst. (2020) 1190–1195.
[6] Z. Lassoued, M. Alhendawi and R. Bashitialshaaer, An exploratory study of the obstacles for achieving quality in
distance learning during the COVID-19 pandemic, Educ. Sci. 10(9) (2020) 232.
[7] S. Li and T. Liu, Performance prediction for higher education students using deep learning, Complexity 2021
(2021) 9958203.
[8] X. Li, X. Zhu, X. Zhu, Y. Ji and X. Tang, Student academic performance prediction using deep multi-source
behavior sequential network, In: H. Lauw, R.W. Wong, A. Ntoulas, E.P. Lim, S.K. Ng and S. Pan (eds), Advances
in Knowledge Discovery and Data Mining, PAKDD 2020, Lecture Notes in Computer Science, 2020.
[9] E.A. Mahareek, A.S. Desuky, H.A. El-Zhni, Simulated annealing for SVM parameters optimization in student’s
performance prediction, Bull. Elect. Engin. Inf. 10(3) (2021) 1211–1219.
[10] A.D. Minghat, A. Ana, P. Purnawarman, S. Saripudin, M. Muktiarni, V. Dwiyanti, S.S. Mustakim, Students’
perceptions of the twists and turns of e-learning in the midst of the Covid 19 outbreak, Rev. Rom. Pentru Educ.
Multid. 12(1Sup2) (2020) 15–26.
[11] M. To˘ga¸car, A deep feature learning model for pneumonia detection applying a combination of mRMR feature
selection and machine learning models, IRBM 41(4) (2020) 212–222.
[12] B. Yang, D. Li, B. Ma, X, Gu and D. Kong, Motor imagery EEG classification method based on adaptive decision
surface of LDA classifier, 11th Int. Conf. Biosci. Biochem. Bioinf. Assoc. Comput. Machin. (2021) 37–41.[13] B. Zhong, X. Pan, P.E.D. Love, L. Ding and W. Fang, Deep learning and network analysis: classifying and
visualizing accident narratives in construction, Autom. Construc. 113 (2020) 103089.
Volume 13, Issue 1
March 2022
Pages 1329-1339
  • Receive Date: 10 April 2021
  • Revise Date: 27 July 2021
  • Accept Date: 04 August 2021
  • First Publish Date: 27 October 2021