Utilization of a Self Organizing Map as a Tool to Study and Predict the Success of Engineering Students at Walailak University



Many factors have an influence on the success of undergraduate students particularly in engineering programs. Some students have to drop out as a result of obtaining very poor GPA (grade point average) and/or GPAX (accumulated grade point average) after only their first year of studying. It would be helpful for students if they know how their current GPA/GPAX could be improved in order to successfully graduate. In addition, what would be the expected outcome of their study, if their current GPAs of compulsory subjects are not fairly good? In this paper, the Self Organizing Map (SOM) neural network is utilized as a tool to cluster engineering student data into different groups by means of their study results. The results are then used to produce the weight maps. The maps reflect the correlation between GPA/GPAX of the compulsory subjects and the educational status of students. The result from the SOM with some adaptations to its matching phase is also used to create a predictor which is capable of producing a fairly high degree of correctness. The meaningful results are intended to be used as a guideline for students to prepare and improve themselves. In addition, it might be useful for student advisors and counselors to give appropriate advice to students whose GPAX are critically low. This can be accomplished by advising students to register less or withdraw some subjects in order to leverage their GPAX. In addition, some students should be advised to change their field of study if they perform fairly poorly in all compulsory subjects. The approach utilized in this paper is a novel one with respect to this application domain.


Self organizing map, engineering education, education prediction

Full Text:



H Hartman and M Hartman. Leaving engineering: Lessons from Rowan University’s College of Engineering. J. Eng. Educ. 2006; 1, 49-61.

RM Felder, KD Forrest, L Baker-Ward, EJ Dietz and PH Mohr. A longitudinal study of engineering student performance and retention: I. Success and failure in the introductory course. J. Eng. Educ. 1993; 1, 15-21.

DC Dickenson. Prediction and success of freshmen Engineers. Pers. Guid. J. 1969; 6, 1008-14.

RL Elkins and JF Leutkemeyer. Characteristics of successful freshmen engineering students. J. Eng. Educ. 1974; 4, 189-91.

J Levin and J Wycokoff. Prediction persistence and success in baccalaureate engineering. J. Eng. Educ. 1991; 4, 461-8.

RM Felder, KD Forrest, L Baker-Ward, EJ Dietz and PH Mohr. A longitudinal study of engineering student performance and retention: III. Gender difference in student performance and attitudes. J. Eng. Educ. 1995; 2, 151-63.

LW Lackey, WJ Lackey, HM Grady and MT Davis. Efficacy of using a single, non-technical variable, to predict the academic success of freshmen engineering students. J. Eng. Educ. 2003; 1, 41-8.

CWT Chiu, P Pashley, M Seastrom and P Carr. Visualizing large-scale data in educational, behavioral, psychometrical and social sciences: utilities and design patterns of the SEER computational and graphical statistics. Journal of Information Visualization 2005; 4, 276-89.

T Eklund, B Back, H Vanharanta and A Visa. Using the self-organizing map as a visualization tool in financial benchmarking. Journal of Information Visualization 2003; 2, 171-81.

T Honkela. Self-Organizing Maps in Natural Language Processing, Available at: http://www.cis.hut.fi/~tho/thesis, accessed February 2007.

W Kurdthongmee. A novel Kohonen SOM-based image compression architecture suitable for moderate density FPGAs. Image Vision Comput. 26; 2008, 1094-105.

AH Dekker. Kohonen neural networks for optimal colour quantization. Network- Comp. Neural 1994; 1: 354-67.

T Kohonen. The self-organizing map. Proceedings of the IEEE 1990; 9, 1464-80.


  • There are currently no refbacks.


Online ISSN: 2228-835X


Last updated: 17 May 2019