International Journal of Cognitive Research in Science, Engineering and Education (IJCRSEE)

IJCRSEE Editorial Team; Marija Mojsilović; Muzafer Saračević; Selver Pepić; Suad Bećirović; Milica Tufegdžić

doi:10.23947/2334-8496-2025-13-3-603-623

Authors

Marija Mojsilović Academy of Professional Studies Sumadija Department in Trstenik, Trstenik, Serbia https://orcid.org/0009-0004-6818-2450
Muzafer Saračević University of Novi Pazar, Department of Economics and Computer Sciences, Novi Pazar, Serbia https://orcid.org/0000-0003-2577-7927
Selver Pepić Academy of Professional Studies Sumadija Department in Trstenik, Trstenik, Serbia; University of Novi Pazar, Department of Economics and Computer Sciences, Novi Pazar, Serbia https://orcid.org/0009-0007-9139-4891
Suad Bećirović University of Novi Pazar, Department of Economics and Computer Sciences, Novi Pazar, Serbia https://orcid.org/0000-0002-9704-5664
Milica Tufegdžić Academy of Professional Studies Sumadija Department in Trstenik, Trstenik, Serbia https://orcid.org/0000-0003-3856-1498

DOI:

https://doi.org/10.23947/2334-8496-2025-13-3-603-623

Keywords:

Teaching quality, Professional studies, Fuzzy logic, Anfis, Soft computing

Abstract

This research aims to examine the impact of the quality of teaching on the success of vocational students, focusing on professional-applicative subjects in the field of information technology, as well as on general education subjects. The quality of teaching was analyzed through six factors: comprehensibility of the teaching content, applicability of the material, quality of the teaching material, teacher’s commitment, working atmosphere and objectivity of assessment. The academic success of students is represented by the course grade. An adaptive neuro-fuzzy system, ANFIS, was used to model the relationship between the aforementioned factors and academic achievement, which combines the advantages of fuzzy logic and neural networks. Data were collected through a structured questionnaire with a Likert scale, and the model was trained and evaluated using soft computing techniques. The results show that the quality of the teaching material, the dedication of teachers and the working atmosphere have the greatest influence on the success of students. These factors were singled out as the most significant predictors of success within the ANFIS model. The findings indicate the need for a systematic approach to improving the quality of teaching in professional studies and confirm the usefulness of artificial intelligence in the analysis of educational data.

Downloads

Download data is not yet available.

References

Abdi, H., Valentin, D., & Edelman, B. (1999), Neural networks (No. 124). Sage. https://methods.sagepub.com/book/mono/neural-networks/toc DOI: https://doi.org/10.4135/9781412985277

Anđelković B., (2006). Istraživanje i razvoj novih metoda za proračun steznih sklopova primenom neuronskih mreža i fazi logike [Research and development of new methods for the calculation of clamping circuits using neural networks and fuzzy logic], (Doctoral dissertation), Mašinski fakultetet Niš.

Adamović, V. M. (2018). Predviđanje indikatora za upravljanje čvrstim otpadom na nacionalnom nivou primenom veštačkih neuronskih mreža [Prediction of indicators for solid waste management at the national level using artificial neural networks], (Doctoral dissertation, University of Belgrade (Serbia)). https://www.proquest.com/openview/196aec169b9652cf2882b4b37e865d29/1?pq-origsite=gscholar&cbl=2026366&diss=y

Baker, R. S., Martin, T., & Rossi, L. M. (2016). Educational data mining and learning analytics. The Wiley handbook of cognition and assessment: Frameworks, methodologies, and applications, 379-396. https://doi.org/10.1002/9781118956588.ch16 DOI: https://doi.org/10.1002/9781118956588.ch16

Buchaniec, S., Gnatowski, M., & Brus, G. (2021). Integration of classical mathematical modeling with an artificial neural network for the problems with limited dataset. Energies, 14(16), 5127. https://www.mdpi.com/1996-1073/14/16/5127 DOI: https://doi.org/10.3390/en14165127

Buragohain, M., & Mahanta, C. (2008). A novel approach for ANFIS modelling based on full factorial design. Applied soft computing, 8(1), 609-625. https://doi.org/10.1016/j.asoc.2007.03.010 DOI: https://doi.org/10.1016/j.asoc.2007.03.010

Bakri, R., Rahma, A. N., Suryani, I., & Sari, Y. (2020), Penerapan Logika Fuzzy Dalam Menentukan Jumlah Peserta Bpjs Kesehatan Menggunakan Fuzzy Inference System Sugeno. Jurnal Lebesgue: Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika, 1(3), 182-192. https://pdfs.semanticscholar.org/8a3c/05006756cdaf9623b143bb6679418f0cd60a.pdf DOI: https://doi.org/10.46306/lb.v1i3.38

Celikyilmaz, A., & Türksen, I. B. (2009). Modeling uncertainty with fuzzy logic. Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-89924-2 DOI: https://doi.org/10.1007/978-3-540-89924-2

Chong, D. J. S., Chan, Y. J., Arumugasamy, S. K., Yazdi, S. K., & Lim, J. W. (2023). Optimisation and performance evaluation of response surface methodology (RSM), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) in the prediction of biogas production from palm oil mill effluent (POME). Energy, 266, 126449. https://doi.org/10.1016/j.energy.2022.126449

Ćalasan, M., Aleem, S. H. A., & Zobaa, A. F. (2020). On the root mean square error (RMSE) calculation for parameter estimation of photovoltaic models: A novel exact analytical solution based on Lambert W function. Energy conversion and management, 210, 112716. https://doi.org/10.1016/j.enconman.2020.112716 DOI: https://doi.org/10.1016/j.enconman.2020.112716

Chong, D. J. S., Chan, Y. J., Arumugasamy, S. K., Yazdi, S. K., & Lim, J. W. (2023). Optimisation and performance evaluation of response surface methodology (RSM), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) in the prediction of biogas production from palm oil mill effluent (POME). Energy, 266, 126449. https://doi.org/10.1016/j.energy.2022.126449 DOI: https://doi.org/10.1016/j.energy.2022.126449

Fountas, Z. (2011). Spiking neural networks for human-like avatar control in a simulated environment. Computing Science of Imperial College London, 1-60. https://www.doc.ic.ac.uk/teaching/distinguished-projects/2011/z.fountas.pdf

Haykin, S. (1998), Neural networks: a comprehensive foundation. Prentice Hall PTR. https://dl.acm.org/doi/abs/10.5555/541500

Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685. https://doi.org/10.1109/21.256541 DOI: https://doi.org/10.1109/21.256541

Ligia, E., Iskandar, K., Surajaya, I. K., Bayasut, M., Jayanagara, O., & Mizuno, K. (2024). Cultural clash: Investigating how entrepreneural characteristics and culture diffusion affect international interns’ competency. Aptisi Transactions on Technopreneurship (ATT), 6(2), 182-198. https://att.aptisi.or.id/index.php/att/article/view/398 DOI: https://doi.org/10.34306/att.v6i2.398

Mojsilović, M., Pepić, S., Popović, G., Saračević, M., & Karabašević, D. (2025). Application of Soft Computing Techniques in the Analysis of Educational Data Using Fuzzy Logic. Mathematics, 13(13), 2096. https://doi.org/10.3390/math13132096 DOI: https://doi.org/10.3390/math13132096

Mehrotra, K., Mohan, C. K., & Ranka, S. (1997). Elements of artificial neural networks. MIT press. https://direct.mit.edu/books/monograph/3932/Elements-of-Artificial-Neural-Networks DOI: https://doi.org/10.7551/mitpress/2687.001.0001

Mojsilović, M., Cvejić, R., Pepić, S., Karabašević, D., Saračević, M., & Stanujkić, D. (2023). Statistical evaluation of the achievements of professional students by combination of the random forest algorithm and the ANFIS method. Heliyon, 9(11). https://pubmed.ncbi.nlm.nih.gov/38027614/ DOI: https://doi.org/10.1016/j.heliyon.2023.e21768

Milovanović, M. B. (2018). Upravljanje dinamičkim sistemima primenom adaptivnih ortogonalnih neuronskih mreža [Management of dynamic systems using adaptive orthogonal neural networks]. Univerzitet u Nišu. https://nardus.mpn.gov.rs/bitstream/id/52334/Disertacija.pdf

Razeghi, S. A. (2022). Razvoj modela upravljanja cirkulacijom u postupku bušenja korišćenjem neuro fazi sistema zaključivanja [Development of a circulation control model in the drilling process using a neuro fuzzy inference system]. Univerzitet u Beogradu. https://www.proquest.com/openview/d737bf260854749c1c9f56d7b97fedf4/1?pq-origsite=gscholar&cbl=2026366&diss=y

Shanmuganathan, S. (2016). Artificial neural network modelling: An introduction (pp. 1-14). Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-319-28495-8_1 DOI: https://doi.org/10.1007/978-3-319-28495-8_1

Stevens, C. F. (1979). The neuron. Scientific American, 241(3), 54-65. https://www.jstor.org/stable/24965287 DOI: https://doi.org/10.1038/scientificamerican0979-54

Villar, A., & de Andrade, C. R. V. (2024). Supervised machine learning algorithms for predicting student dropout and academic success: a comparative study. Discover Artificial Intelligence, 4(1), 2. https://link.springer.com/article/10.1007/s44163-023-00079-z DOI: https://doi.org/10.1007/s44163-023-00079-z

Zhao, H., & Zhang, F. (2025). A Tree Soft Set Framework for Evaluating Teaching Quality in University Physics Programs: Enhancing Precision and Decision-Making. Neutrosophic Sets and Systems, 80(1), 5. https://digitalrepository.unm.edu/nss_journal/vol80/iss1/5/

Zogopoulos, K., Gioti, L., Raptis, N., & Karatzas, A. (2025). Teaching soft skills to students through artificial intelligence. IOSR Journal of Research & Method in Education, 15(1), 23-33. https://www.iosrjournals.org/iosr-jrme.html