The prediction of undergraduate student performance in chemistry course using multilayer perceptron

Che Akmal, Che Yahaya and Che Yahaya, Yaakub and Ahmad Firdaus, Zainal Abidin and Mohd Faizal, Ab Razak and Nuresa Fatin, Hasbullah and Mohamad Fadli, Zolkipli (2020) The prediction of undergraduate student performance in chemistry course using multilayer perceptron. In: IOP Conference Series: Materials Science and Engineering, The 6th International Conference on Software Engineering & Computer Systems, 25-27 September 2019 , Pahang, Malaysia. pp. 1-8., 769 (012027). ISSN 1757-899X

The prediction of undergraduate student.pdf
Available under License Creative Commons Attribution.

Download (1MB) | Preview


Chemical industries are the essential factors to convert from raw materials into the target products that we use in our daily life. This has brought a tremendous change in the way things operate. In the interest of demanding the chemical engineers is increasing, simultaneously the failure rate of a student in a chemistry course also rising. The students that register the chemistry course often fail whether in the first semester or following semester. Moreover, students also unable to recognize whether they can adapt in this course and graduate successfully. The objective of this research is to predict the students in the chemical course either quit or graduate in the future by using enhanced Multilayer Perceptron (MLP) machine learning classification with Adaboost. The accuracy of the results from this study is 92.23% percent.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: Chemistry; Undergraduate; Education; Machine Learning; Multilayer Perceptron; Neural Network
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computer System And Software Engineering
Institute of Postgraduate Studies
Depositing User: Pn. Hazlinda Abd Rahman
Date Deposited: 23 Dec 2020 02:35
Last Modified: 23 Dec 2020 02:36
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item