See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/358565981

An Intelligent System for Predicting Students Performance

Article · February 2022

DOI: 10.9790/0661-2401013642

CITATIONS READS

0 165

2 authors, including:

David Tufe Nzadon

Cyberspace Networks
10 PUBLICATIONS 9 CITATIONS

SEE PROFILE

All content following this page was uploaded by David Tufe Nzadon on 12 February 2022.

The user has requested enhancement of the downloaded file.

IOSR Journal of Computer Engineering (IOSR-JCE)
e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 24, Issue 1, Ser. I (Jan. –Feb. 2022), PP 36-42
www.iosrjournals.org

AN Intelligent System for Predicting Students

Performance
Manga, I.1 El-Yakub, M.B2 and Nzadon, D.T3
1
(Department of Computer Science. Adamawa State University Mubi, Nigeria).
2
(Department of Computer Science. Adamawa State University Mubi, Nigeria).
3
(Department of Computer Science. Adamawa State University Mubi, Nigeria).

Abstract: One of the causes of the gradual decline of the Nigerian Educational System can be attributed to the
inadequacies and flaws in universities admission process. In this paper, we seek to address this problem by
predicting the first-year performances of prospective students using Fuzzy Logic based on prior academic
achievements presented during admission process. A range of conventional secondary school subjects were
used as the input variables in a Mamdani Model. MATLAB fuzzy logic toolbox was used to model the fuzzy rules
logic in this study with computer science course (CSC) criteria in the x axis, General studies course (GST)
criteria is in y axis, and solution criteria Performance (P) is in z axis. The results show that a student with a
model output of CSC=0.857, MTH=0.796, PHY=0.864, GST=0.638, CHM=0.489 model output P=0.446.
Output P=0.446 means that the student will most likely perform above the 95th percentile of the Grade Point
Average (GPA). The design was successfully tested and implemented.
Keywords: Fuzzy Logic, Student Performance, Fuzzy Inference.
---------------------------------------------------------------------------------------------------------------------------------------
Date of Submission: 01-01-2022 Date of Acceptance: 12-01-2022
---------------------------------------------------------------------------------------------------------------------------------------

I. Introduction
The increasing demand for education in Nigeria especially tertiary education has not been without its
challenges. Government–owned tertiary institutions as well as those privately owned do not possess the capacity
and manpower needed to accommodate the growing number of young school leavers hoping to secure admission
into tertiary institutions. [2] [3] [5] [13] posits that predicting and evaluating the academic performances of
students has for a long time now been an interesting and important area of research in many academic
disciplines. Evaluating students’ academic performances or achievement using the cumulative grade point
average (CGPA) as a pointer is a typical practice in several tertiary academic environments. A high percentage
of fresh students usually find themselves below the minimum grade point required at the end of their first year.
[1]. pointed out that having a thorough understanding of a student’s prior achievement or knowledge is
important and will go a long way in helping academic planners predict the future performance of such student.
[12] stressed the importance of predicting and evaluating the academic performances of students. In
his survey carried out in a privately-owned university in Nigeria, the percentages of students below the 2.5
CGPA at the end of the 2007/2008, 2008/2009 and 2009/2010 academic sessions were alarming. This
percentage gives a clear view of the declining nature of students’ academic performances in our tertiary
institutions. Thus predicting and evaluating students’ performances cannot be over-emphasized as it is a useful
tool for academic planners, educators and students alike, as it gives an actual understanding of students’
weaknesses and proffer solutions. The application of fuzzy logic in predicting and evaluating students’ academic
performances gives effective and attainable solutions as the knowledge of fuzzy logic is suitably required when
human evaluation is needed. Furthermore, research has shown that fuzzy logic is a more essential technique to
handle imprecision and uncertainty given that evaluating the prior knowledge or past achievements of students
with the aim of discovering the risk of students’ failure involves dealing with uncertain and imprecise data [5]
[8] [17] [21] . Therefore, this project aimed at implementing fuzzy logic in predicting students’ academic
performances as the fuzzy approach is likely to offer an alternative way of handling imprecise data, especially in
decision making.

II. Materials and Method

2.1 Overview of the System
The first step in the proposed model is the establishment of input and output variables. This task is
usually done by studying the problem domain. There is infinite number of potential candidates which should be
restricted to positive numbers. In this research, the key variables are defined. Input and outputs of proposed

DOI: 10.9790/0661-2401013642 www.iosrjournals.org 36 | Page

 A Fuzzy Based Logic System For Predicting Students Performance
model is given in Table 1 and whole structure of predicting student academic performance system developed in
the Matrix Laboratory (MATLAB) as shown in Fig 1.

Inputs variables Abbreviation Output variables Abbreviation

Computer science CSC
Mathematics MTH Performance P
Physics PHY
General studies GST
Chemistry CHM

Table 1: Input and output variables

Fig 1: Predicting Student Academic Performance Model using the Mamdani Method.

III. Design Specifications

The three main components of this are given below:
 User interface.
 Decision making inference engine.
 Database (storing the data and fuzzy rules).
A system administrator (or any user) will interact with the predicting student academic performance system
using MATLAB Fuzzy module. Inference engine gets commands from user by interface and evaluates these
with the help of a database in which rules are deposited.

3.1 Fuzzy sets and fuzzy number

The fuzzy set theory as introduced by Zadeh is a multi-value logic which permits intermediate values to
be defined between conventional ones like true/false, low/high, good/bad etc. In a classical set theory, an
element may either belong to set or not. In fuzzy set theory, an element has a degree of membership. A degree
of membership function can be described as an interval [0, 1]. In this study, a triangular fuzzy number (TFN)
was used for prediction computational efficiency. A TFN is shown simply as (a, m, b). “a, m, b” parameter
represents the smallest possible value (lower bound), mean value, the largest possible value (upper bound)
respectively. is a membership function

Fig 2: A triangular fuzzy number

DOI: 10.9790/0661-2401013642 www.iosrjournals.org 37 | Page

 A Fuzzy Based Logic System For Predicting Students Performance

Membership function of the TFN is presented as follows:

------------- (3.1)

3.2 Fuzzy Rule Based Model

The general architecture for a rule-based intelligent system and the components of a fuzzy rule-based
inference system are shown in this report. The main modules of a fuzzy rule-based system are fuzzification - or
fuzzifier module -, fuzzy rules, inference engine and defuzziier.
Step 1. Fuzzification module: It converts a crisp input of the domain of the input variable domain to a
grade by fuzzy set. Constructing a fuzzy logic membership functions play a crucial role for fuzzy rule-based
models. Triangular membership function was used in many fuzzy logics-based applications. In this study
triangular membership functions have been used.
Step 2. Defining fuzzy rules: Fuzzy rules consist of antecedent and consequent in the form of IF-
THEN statements. There are a number of rules, and they make a group which forms the basis for inference. The
following some fuzzy rules have been taken with the combination of linguistic variable values. Input and output
criteria of the model are “computer science (CSC)”, “Mathematics-(MTH)”, “physics (PHY) “General studies
(GST)”, “Chemistry (CHM)”, and “Performance (P)”.

3.3 Fuzzy parameters and their Membership Functions Design

Fig 3: Computer Science Courses Membership

Fig 4: Mathematics Courses Membership

DOI: 10.9790/0661-2401013642 www.iosrjournals.org 38 | Page

 A Fuzzy Based Logic System For Predicting Students Performance

Fig 5: Physics Courses Membership

Fig 6: General studies Courses Membership

3.4 Inference Engine and Defuzzification

The basic function of the inference engine is to compute level of belief in output fuzzy sets from the
levels of belief in the input fuzzy sets. The output is a single belief value for each output fuzzy set. In this stage,
the fuzzy operator is applied in order to gain a single number that represents the result of the antecedent for that
rule. The procedure of converting each aggregated fuzzy output set into a single crisp value is called
defuzzification. In the prediction of student academic performance system, to find the defuzzification value we
use the center of gravity method. The center of gravity equation can be written as follows:

----------- (3.2)

IV. Test and Results

The inference mechanism in the fuzzy logic controller resembles that of the human reasoning process.
This is where fuzzy logic technology is associated with artificial intelligence. Humans unconsciously use rules
in implementing their actions. Fuzzy rules consist of antecedent and consequent in the form of IF-THEN
statements. There are a number of rules, and they make a group which forms the basis for inference. The
following are some fuzzy rules that have been taken with the combination of linguistic variable values using the
software MATLAB.

DOI: 10.9790/0661-2401013642 www.iosrjournals.org 39 | Page

 A Fuzzy Based Logic System For Predicting Students Performance

Fig 7: Fuzzy rules dev0lop in MATLAB

Fig 8: Input variables Computer Science Courses (CSC), General Studies course (GST) vs. output variable
Performance (P).

It can be seen that computer science course (CSC) criteria is in x axis, General studies course (GST) criteria is in
y axis, and solution criteria Performance (P) is in z axis as shown in Figure 8.

Fig 9: Input variables Mathematics Courses (MTH), chemistry course (CHM) vs. output variable Performance
(P)
DOI: 10.9790/0661-2401013642 www.iosrjournals.org 40 | Page
 A Fuzzy Based Logic System For Predicting Students Performance

Fig 10: Input variables Physics Courses (PHY), Computer science course (CHM) vs. output variable
Performance(P).

As shown in Fig 9 Physics Course (PHY) criteria is in x axis, Computer Science course (CHM) criteria is in y
axis, and solution criteria Performance (P) is in z axis.
A 100-level student registered the following first semester courses on his/her portal, and when his final semester
examination result was out, and he went to check his performance. According to the proposed model, a sample
solution is given in Fig 11 When CSC=0.857, MTH=0.796, PHY=0.864, GST=0.638, CHM=0.489 model
output P=0.446. Output P=0.446 means that the student had a good performance. Using the CGPA scale of 5.0,
the student performance shows that he/she in first class (4.5) range approximately.

Fig 11: Fuzzy Rule Viewer for Predicting Student Academic Performance

V. Conclusion and Recommendations

In conclusion, a fuzzy logic system was developed for predicting the first semester performance of
students based on the following subjects: “Computer science" "Mathematics" "Physics" "Chemistry" and
"General studies". Based on our numerical experiments, we conclude that the MATLAB - trained fuzzy logic
system exhibits more consistent behavior and illustrate better classification results than the other classifiers.
Furthermore, we have shown the main features of our software tool to illustrate its functionalities and the
experimental set up process. Our tool is still under development but our first results shows it can be used to gain
DOI: 10.9790/0661-2401013642 www.iosrjournals.org 41 | Page
 A Fuzzy Based Logic System For Predicting Students Performance
considerable insights about student progress and recommend possible actions such as further study or additional
learning activities, resources and learning tasks.

References
[1]. Abruzzi, Kristen J.; Lenis, Cristina; Romero, Yansi V.; Maser, Kevin J.; Morote, Elsa -Sofia (2016). "Does Participation in
Extracurricular Activities Impact Student Achievement?". Journal for Leadership and Instruction. 15 n1: 21–26.
[2]. Alexander, A. W. (2010). “Student involvement: A developmental theory for higher education”. Journal of college student
personnel, Vol.25, No. 4, pp.297-308.
[3]. Ayán, M. N. R., & García, M. T. C. (2008). Prediction of University Students’ Academic Achievement by Linear and Logistic
Models. The Spanish Journal of Psychology, 11(01), 275–288.
[4]. Ayen, J. and Garcia, W. (2013). “Predicting student performance: an application of data mining methods with an educational web-
based system”. In Frontiers in education, 2013. FIE 2003 33rd annual (Vol. 1, pp. T2A-13). IEEE
[5]. Boules, K. and Gintis, W. G. (2014). Dropouts from higher education: Toward an empirical model. Interchange, Vol.2, No.3, pp.38-
62
[6]. Case, Mehdi. (2016). "Presenting a Model for Determining the Relationship Between Responded Educational Planning and
Perceived Class Evaluation on the Basis of Academic Involvement Mediation." JSR 2 (23): 64–78.
[7]. Clifton, R., Perry, R., Adams, C., & Roberts, L. (2004). Faculty environments, psychological dispositions and the academic
achievement of college students. Research in Higher Education, 45, 801-829.
[8]. Fredricks, J. A. (2011). Extracurricular Participation and Academic Outcomes: Testing the Over-Scheduling Hypothesis. Journal of
Youth and Adolescence, 41(3), 295–306. Fattahi, Z. 2005. "Review of the Opinions of the Scientific Board Members of Tehran
University of Medical Sciences About the Evaluation of the Professor in the Academic Year of 2002-2003." Hormozgan Medical
Journal 9: 59–66.
[9]. G. Gokmen, T. C. Akinci, M. Tektas, N. Onat. G. Kocyigit, N. Tektas, “Evaluation of Student Performance in Laboratory
Applications Using Fuzzy Logic”, Procedia Social and Behavioral Science, pp 902-909, 2010.
[10]. Golec, Adam, and Esra Kahya. (2007). "A Fuzzy Model for Competency-Based Employee Evaluation and Selection." Computers &
Industrial Engineering 52 (1): 143–61.
[11]. Guruprasad, Mamatha, R Sridhar, and S Balasubramanian. (2016). "Fuzzy Logic as a Tool for Evaluating the Appraisal
Performance of Faculty in Higher Education Institutions." In SHS Web of Conferences, EDP Sciences.
[12]. Jyothi, G, C Parvathi, P Srinivas, and Mr Sk Althaf. (2014). "Fuzzy Expert Model for Evaluation of Faculty Performance in
Technical Educational Institutions." International Journal of Engineering Research and Applications 4 (5): 41–50.
[13]. Kieffer, K., Reese, R., & Thompson, B. (2001). Statistical techniques employed in AERJ and ICP articles from 1988 to 1997: A
methodological review. Journal of Experimental Education, 69, 280-309.
[14]. Khademi Zare, Hassan, and Mohammad Bagher Fakhrzad. (2013). "Integration of Collaborative Management and Fuzzy Systems
for Evaluating Students' Educational Performance." Quarterly Journal of Research and Planning in Higher Education 19 (3): 23–
40.
[15]. Mamatha S. Upadhyay, “Fuzzy Logic Based on Performance of Students in College”, Journal of Computer Applications (JCA),
5(1), pp. 6-9, 2012.
[16]. Mirfakhradin, SH, Owlia, MS, & Jamali, R. (2009). "Reverse Engineering Quality Management in Higher Learning
Center." Quarterly Journal of Research and Planning in Higher Education 15: 131–57.
[17]. Mirza Mohamadi, MH 2010. "Design Algorithm Evaluation, Improvement Education Group Art and Architecture on Research
Program." Quarterly Journal of Research and Planning in Higher Education 17: 153–77.
[18]. Motamedi, Ahman, and Sadegh Rafie. (2001). "A Flexible Way to Evaluate Students' Performance Using Fuzzy Logic." In 11th
Iranian Fuzzy Systems Conference, http://www.civilica.com/Paper-ICFUZZYS11-ICFUZZYS11_099.html.
[19]. Mousavi, Shokufeh et al. 2014. "Evaluation of Faculty Members in the Psychology Group of Babol University of Medical Sciences:
Viewpoints of Internship Medical Students." Biannual Journal of Medical Education Development Centre (edc) Babol University of
Medical Sciences 2 (2): 37–42.
[20]. Saber, Reza. 2017. "Evaluation of the Art Education System in Primary School with Approaches to Major Areas and Content
Structure: A Study of Teachers, Principals and Experts' Views." Research in Curriculum Planning Vol 13 (. No 24): 75–86.
[21]. Zeegers, P. (2004). Student learning in higher education: A path analysis of academic achievement in science. Higher Education
Research and Development, 23, 35-56.

Manga, I, et. al. “A Fuzzy Based Logic System for Predicting Students Performance.” IOSR
Journal of Computer Engineering (IOSR-JCE), 24(1), 2022, pp. 36-42.

DOI: 10.9790/0661-2401013642 www.iosrjournals.org 42 | Page

View publication stats