A Hybrid Fuzzy–Neural Decision-Support Framework for Graduate Learning Outcome Attainment Evaluation in a Computer Science Program

Suendri; Ratni Sirait; Ilka Zufria

doi:10.15408/jti.v19i2.54389

Authors

Suendri Universitas Islam Negeri Sumatera Utara, Medan, Indonesia https://orcid.org/0000-0003-2736-646X
Ratni Sirait Universitas Islam Negeri Sumatera Utara, Medan, Indonesia
Ilka Zufria Universitas Islam Negeri Sumatera Utara, Medan, Indonesia

DOI:

https://doi.org/10.15408/jti.v19i2.54389

Keywords:

graduate learning outcomes, fuzzy logic, neural network, outcome-based education, educational assessment, hybrid artificial intelligence, decision support, human-in-the-loop

Abstract

A passing threshold of 70 assigns different attainment labels to students scoring 71.0 and 66.5, although both are close enough to warrant review. This study develops a fuzzy-neural decision-support framework for graduate learning outcome assessment in an undergraduate Computer Science program. Weighted course learning outcome scores determine the reference status. Fuzzy rules provide category memberships and a soft score, with cases within five points of 70 referred to a human reviewer. A single-layer perceptron produces a separate estimate from normalized course scores. Four anonymized records and one partial-profile scenario illustrate the calculations. The fuzzy results retain all reference classifications. Two of the four complete records are referred for review; including the additional scenario gives three referrals among five cases. The referral set is unchanged at half-widths of 5, 7, and 10. After one training pass, the perceptron misclassifies the partial-profile scenario even when the assumed missing score is supplied. The weighted calculation gives the reference status using either the available scores or the assumed complete profile. These results document the referral procedure and the limits of the neural prototype. The design keeps its estimate separate from the official status and leaves borderline decisions to a reviewer. Predictive performance and the consistency of human review require evaluation on larger datasets.

Author Biography

Suendri, Universitas Islam Negeri Sumatera Utara, Medan, Indonesia

Dosen Universitas Islam Negeri Sumatera Utara

References

[1] M. Z. Zamir, M. I. Abid, M. R. Fazal, M. A. A. R. Qazi, and M. Kamran, “Switching to outcome-based education (OBE) system: A paradigm shift in engineering education,” IEEE Transactions on Education, vol. 65, no. 4, 2022.

[2] R. Mufanti, D. Carter, and N. England, “Outcomes-based education in Indonesian higher education: Reporting on the understanding, challenges and support available to teachers,” Social Sciences & Humanities Open, vol. 9, 2024.

[3] B. Kushari and L. Septiadi, “A learning outcome assessment information system to facilitate outcome-based education (OBE) implementation,” Jurnal Pendidikan Teknologi dan Kejuruan, vol. 28, no. 2, pp. 238–250, 2022, doi: 10.21831/jptk.v28i2.42339.

[4] A. Aziz, M. A. U. Golap, and M. M. A. Hashem, “Student’s academic performance evaluation method using fuzzy logic system,” in Proc. 2019 1st Int. Conf. on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019, pp. 1–6, doi: 10.1109/ICASERT.2019.8934464.

[5] A. Krouska, C. Troussas, and C. Sgouropoulou, “Fuzzy logic for refining the evaluation of learners’ performance in online engineering education,” European Journal of Engineering and Technology Research, vol. 4, no. 6, pp. 50–56, 2019.

[6] N. U. Jan, S. Naqvi, and Q. Ali, “Using fuzzy logic for monitoring students’ academic performance in higher education,” Engineering Proceedings, vol. 46, no. 1, art. 21, 2023, doi: 10.3390/engproc2023046021.

[7] E. T. Lau, L. Sun, and Q. Yang, “Modelling, prediction and classification of student academic performance using artificial neural networks,” SN Applied Sciences, vol. 1, no. 9, art. 982, 2019, doi: 10.1007/s42452-019-0884-7.

[8] Y. Baashar et al., “Toward predicting student’s academic performance using artificial neural networks (ANNs),” Applied Sciences, vol. 12, no. 3, art. 1289, 2022, doi: 10.3390/app12031289.

[9] M. Nachouki and M. Abou Naaj, “Analysis of the factors affecting student performance using a neuro-fuzzy approach,” Education Sciences, vol. 13, no. 3, art. 313, 2023, doi: 10.3390/educsci13030313.

[10] W. D. Yuniarti, S. Hartati, S. Priyatna, and H. D. Surjono, “Learner assessment system in e-learning with OBE approach: Activity performance, ability level and recommendation,” HighTech and Innovation Journal, vol. 5, no. 3, pp. 572–602, 2024.

[11] I. G. S. M. Diyasa, I. N. D. P. Putra, N. K. I. M. Mandenni, M. R. M. Ariefwan, and R. L. Aryananda, “Implementation of innovation in integrated evaluation and learning system using outcome-based education ecosystem,” International Journal of Entrepreneurship and Business Development, vol. 6, 2023.

[12] T. Sasipraba et al., “Assessment tools and rubrics for evaluating the capstone projects in outcome based education,” Procedia Computer Science, vol. 172, pp. 296–301, 2020, doi: 10.1016/j.procs.2020.05.047.

[13] A. Aziz and M. M. A. Hashem, “Fuzzy logic-based assessment of students learning outcome in implementing outcome-based education,” in Proc. Int. Conf. on Big Data, IoT, and Machine Learning, 2022.

[14] A. Ozdemir and K. F. Balbal, “Fuzzy logic based performance analysis of educational mobile game for engineering students,” Computer Applications in Engineering Education, vol. 28, no. 6, pp. 1536–1548, 2020.

[15] T. A. Ajoi, S. S. Gran, A. Kanyan, and S. F. Lajim, “An enhanced systematic student performance evaluation based on fuzzy logic approach for selection of best student award,” Asian Journal of University Education, vol. 16, no. 4, pp. 10–20, 2021.

[16] M. Yağcı, “Educational data mining: Prediction of students’ academic performance using machine learning algorithms,” Smart Learning Environments, vol. 9, art. 11, 2022, doi: 10.1186/s40561-022-00192-z.

[17] N. Ahmad, N. Hassan, H. Jaafar, and N. I. M. Enzai, “Students’ performance prediction using artificial neural network,” IOP Conference Series: Materials Science and Engineering, vol. 1176, art. 012020, 2021, doi: 10.1088/1757-899X/1176/1/012020.

[18] P. J. Loresco and N. Pilueta, “An adaptive neuro-fuzzy framework for monitoring student outcomes with individualized dashboard in outcome-based education,” in Proc. TENCON 2024 – 2024 IEEE Region 10 Conference (TENCON), 2024, pp. 1286–1289, doi: 10.1109/TENCON61640.2024.10903009.

[19] H. Naccache and R. Hleiss, “Reducing classification risk in developmental performance assessment using fuzzy logic: evidence from preservice mathematics teacher education,” Frontiers in Education, vol. 11, art. 1840093, 2026, doi: 10.3389/feduc.2026.1840093.

[20] T. A. Tuan, N. D. Tho, N. H. Nghia, and D. T. T. Loan, “A systematic review and meta-analysis of fuzzy logic for students’ performance assessment,” International Journal of Engineering Trends and Technology, vol. 73, no. 9, pp. 155–174, 2025, doi: 10.14445/22315381/IJETT-V73I9P114.

[21] W. Khan et al., “Auto-assessment of assessment: a human-in-the-loop AI framework addressing policy gaps in academic assessment,” PLOS ONE, vol. 21, no. 4, art. e0346815, 2026, doi: 10.1371/journal.pone.0346815.

[22] D. C. Fajardo-Ramos, A. Chiappe, and J. Mella-Norambuena, “Human-in-the-loop assessment with AI: implications for teacher education in Ibero-American universities,” Frontiers in Education, vol. 10, art. 1710992, 2025, doi: 10.3389/feduc.2025.1710992.

[23] G. Türkmen, “The review of studies on explainable artificial intelligence in educational research,” Journal of Educational Computing Research, vol. 63, no. 2, pp. 277–310, 2025, doi: 10.1177/07356331241310915.

[24] S. Gunasekara and M. Saarela, “Explainable AI in education: techniques and qualitative assessment,” Applied Sciences, vol. 15, no. 3, art. 1239, 2025, doi: 10.3390/app15031239.

[25] A. Shabbir, T. Rehman, M. Salman, S. Rizvi, and N. Saaludin, “Unmasking the impact of teaching workload on learning outcome attainment in outcome-based engineering education: a multi-level analysis of CLO and PLO achievement,” Education Sciences, vol. 16, no. 9, art. 1473, 2026, doi: 10.3390/educsci16091473.

[26] P. Lasunon, “Triangular fuzzy grading method and its software,” in Proc. 2019 5th Int. Conf. on Engineering, Applied Sciences and Technology (ICEAST), 2019.

[27] N. A. Namli and O. Senkal, “Using the fuzzy logic in assessing the programming performance of students,” International Journal of Assessment Tools in Education, pp. 701–712, 2018.

[28] G. Zheng et al., “SAPPNet: Students’ academic performance prediction during COVID-19 using neural network,” Scientific Reports, vol. 14, art. 24605, 2024, doi: 10.1038/s41598-024-75242-2.

[29] H. Khosravi et al., “Explainable artificial intelligence in education,” Computers and Education: Artificial Intelligence, vol. 3, art. 100074, 2022, doi: 10.1016/j.caeai.2022.100074.