Fig 1.
The full paper overall structure.
Fig 2.
A simple Multi-Layer Perceptron (MLP).
Fig 3.
Framework diagram of performance prediction model.
Fig 4.
Process of Elastic Grey Wolf Optimization algorithm (EGWO) training MLP.
Fig 5.
Weights and biases assignments of the Multi-Layer Perceptron (MLP) with two layers.
Fig 6.
Proportions of two Portuguese schools.
Table 1.
Attribute information for student performance data set.
Table 2.
List of parameter setting used algorithms-MLP.
Fig 7.
Results of variable importance.
Fig 8.
Students’ own various characteristics.
(a) Proportion of students’ sex, (b) Proportion of students’ home address type, (c) Proportion of students’ receiving family education support.
Fig 9.
Study time and family guardian of the students.
(a) Proportion of students’ study time, (b) Proportion of students’ guardian.
Fig 10.
(a) Job proportion of students’ mother, (b) Job proportion of students’ father.
Table 3.
The training error of the Mathematics (Mat.) subject achievement prediction.
Table 4.
The test error of the Mathematics (Mat.) subject achievement prediction.
Table 5.
Results for RM ANOVA on RANKS of the Mathematics (Mat.) subject achievement prediction.
Table 6.
The training error for the Portuguese (Por.) subject achievement prediction.
Table 7.
The test error for the Portuguese (Por.) subject achievement prediction.
Table 8.
Results for RM ANOVA on RANKS of the Portuguese (Por.) subject achievement prediction.