Identifying General Education Courses Enhancing Students’ Learning by Using Small Datasets
Keywords:
Classification Algorithm, Small DatasetsAbstract
The objectives of the research were 1) to identify general education courses enhancing students’ learning and 2) to compare the efficiency of the classification algorithms used to identify general education courses enhancing students’ learning by using small datasets. The research was conducted by using the data from the enrollment information of 1,302 students studying in the computer science with 26,804 enrollment information items during the academic year 2005 to 2019. The data were selected and normalized to be the datasets by using the MinMaxScaler technique that used the Heat map to show the results of the hierarchical clusters to show the relationship between variables and evaluate the efficiency of the algorithm by using the LOOCV technique.
The research findings were as follows.
- Information and Learning Literacy (9021103) and English for Learning information (9022102) were the general education courses that enhanced the students’ learning at the highest level.
- The LDA was the algorithm that had the highest efficiency in classifying to identify the general education courses that enhanced the students’ learning by using the small datasets.
References
Chao, G. et al. “A new approach to prediction of radiotherapy of bladder cancer cells in small dataset analysis,” Expert Syst. 38, 7 (2011): 7963–7969.
Ingrassia, S. and I. Morlini. Neural network modeling for small datasets. (Online) 2005 (cited 24 January 2021). Available from: https://www.researchgate.net/publication/232795375_Neural_Network_Modeling_for_Small_Datasets
Mahmoud. L and A. Zohair. “Prediction of Student’s performance by modelling small dataset size,” International Journal of Educational Technology in Higher Education. 16, 1 (2019): 1-18.
Mueen. A, B. Zafar and U. Manzoor. “Modeling and Predicting Students’ Academic Performance Using Data Mining Techniques,” Modern Education and Computer Science. 8, 11 (2016): 36-42.
Mustafa, M. K., T. Allen and K. Appiah. "A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition. (Online) 2017 (cited 5 January 2021). Available from: https://www.researchgate.net/publication/317768552_A_
comparative_review_of_dynamic_neural_networks_and_hidden_Markov_model_methods_for_mobile_on-device_speech_recognition
Pasini, A. Artificial neural networks for small dataset analysis. (Online) 2005 (cited 12 February 2021). Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4454870/
Rao, R. B., G. Fung and R. Rosales. On the dangers of cross-validation. An experimental evaluation. (Online) 2008 (cited 12 February 2021). Available from: https://people.csail.mit.edu/romer/
papers/CrossVal_SDM08.pdf
Sharma, A. and K. K. Paliwal. Linear discriminant analysis for the small sample size problem: An (Online) 2015 (cited 25 February 2021). Available from: https://core.ac.uk/download/pdf/143905484.pdf.
Tsai, C.H and D.C. Li. “Improving Knowledge Acquisition Capability of M5’ Model Tree on Small Datasets,” 2015 3rd International Conference on Applied Computing and Information Technology 2nd International Conference on Computational Science and Intelligence, 2015. pp.379-386.
Downloads
Published
How to Cite
Issue
Section
License
Every article is peer-reviewed for academic correctness by at least two external qualified experts. The opinions in the Journal of Graduate School, Pitchayatat, Ubon Ratchathani Rajabhat University (Humanities and Social Sciences) belong to the authors; not belong to the Publisher. Thus, Graduate School of Ubon Ratchathani Rajabhat University cannot to be held responsible for them. The articles in this journal are protected by the copyright of Thailand. No part of each issue may be reproduced for dissemination without written permission from the publisher.
