A Study on Correlation of Subjects on Electrical Engineering Course Using Artificial Neural Network (ANN)

Autor/inn/en	Zakaria, Fathiah; Che Kar, Siti Aishah; Abdullah, Rina; Ismail, Syila Izawana; Md Enzai, Nur Idawati
Titel	A Study on Correlation of Subjects on Electrical Engineering Course Using Artificial Neural Network (ANN)
Quelle	In: Asian Journal of University Education, 17 (2021) 2, S.144-155 (12 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1823-7797
Schlagwörter	Correlation; Teaching Methods; Artificial Intelligence; Universities; Engineering Education; Electronic Equipment; Academic Failure; Calculus; Models; Databases; Grades (Scholastic); Computer Software; Undergraduate Students; Foreign Countries; Mathematics Instruction; Malaysia + Suchen Sie Ihr Suchwort? Korrelation; Teaching method; Lehrmethode; Unterrichtsmethode; Künstliche Intelligenz; University; Universität; Ingenieurausbildung; Elektronisches Gerät; Analysis; Differenzialrechnung; Infinitesimalrechnung; Integralrechnung; Analogiemodell; Datenbank; Notenspiegel; Ausland; Mathematics lessons; Mathematikunterricht
Abstract	This paper presents a study of correlation between subjects of Diploma in Electrical Engineering (Electronics/Power) at Universiti Teknologi MARA(UiTM) Cawangan Terengganu using Artificial Neural Network (ANN). The analysis was done to see the effect of mathematical subjects (Pre-calculus and Calculus 1) and core subject (Electric Circuit 1) on Electronics 1. Electronics 1 is found to be a core subject with the history of high failure rate percentage (more than 25%) in previous semesters. This research has been conducted on current final semester students (Semester 5). Seven (7) models of ANN are developed to observe the correlation between the subjects. In order to develop an ANN model, ANN design and parameters need to be chosen to find the best model. In this study, historical data from students' database were used for training and testing purpose. Total number of datasets used are 58 sets. 70% of the datasets are used for training process and 30% of the datasets are used for testing process. The Regression Coefficient, (R) values from the developed models was observed and analyzed to see the effect of the subject on the performance of students. It can be proven that Electric Circuit 1 has significant correlation with the Electronics 1 subject respected to the highest R value obtained (0.8100). The result obtained proves that student's understanding on Electric Circuit 1 subject (taken during semester 2) has direct impact on the performance of students on Electronics 1 subject (taken during semester 3). Hence, early preventive measures could be taken by the respective parties. (As Provided).
Anmerkungen	UiTM Press. Asian Centre for Research on University Learning and Teaching, Faculty of Education, Penerbit UiTM, Universiti Teknologi MARA, Bangunan Fakulti Pengurusan Hotel dan Pelancongan, 40450 Shah Alam, Selangor Darul Ehsan, Malaysia. Web site: https://ajue.uitm.edu.my/
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01