Creating Adaptive Curricular Sequences based on Student Profiles and Teaching Materials using the NSGA-III Algorithm

• Bernadete Aquino Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-6206-7003
• Jairo Souza Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-0911-7980
• Luciana Brugiolo Gonçalves Universidade Federal de Juiz de Fora https://orcid.org/0000-0001-8947-1607
• Stênio Sã Rosário Furtado Soares Universidade Federal de Juiz de Fora https://orcid.org/0000-0003-3479-442X

DOI: https://doi.org/10.5753/cbie.sbie.2020.902

Abstract

Adaptive Curriculum Sequencing (ACS) problem has been treated in the literature with metaheuristic approaches and with techniques that reduce it to a mono-objective optimization problem. The objectives used are mostly conflicting, that is, an improvement in one of these objectives does not necessarily result in the improvement of the others. Thus, the objective of this article is to propose a new approach to ACS based on many objectives optimization using the NSGA-III algorithm. Although it is still an unexplored solution, it proved to be adequate for the problem, according to experiments carried out in the laboratory.

Keywords: Adaptive Curriculum Sequencing, NSGA-III, Intelligent Tutoring Systems

References

Acampora, G., Gaeta, M., and Loia, V. (2011). Hierarchical optimization of personalizedexperiences for e-learning systems through evolutionary models.Neural Computingand Applications, 20(5):641–657.


Al-Muhaideb, S. and Menai, M. E. B. (2011). Evolutionary computation approaches tothe curriculum sequencing problem.Natural Computing, 10.


Anschau, D., Marchi, J., and Rizzon, E. (2017). Smart its: um sistema tutor inteligentepara flexibilização e adaptação de currículos.Brazilian Symposium on Computers inEducation (Simpósio Brasileiro de Informática na Educação - SBIE), 28(1):1347.


Azuma, R. M. (2011). Otimização multiobjetivo em problema de estoque e roteamentogerenciados pelo fornecedor. Master’s thesis, Universidade Estadual De Campinas.


Barrére, E., Souza, J., and Machado, M. (2017). Geração de sequências curricularesadaptativas baseada em computação evolucionária: Estado da arte e tendências.Bra-zilian Symposium on Computers in Education (Simpósio Brasileiro de Informática naEducação - SBIE), 28(1):1137.


Cao, X., Xu, J., De Clercq, D., Wang, Y., and TAO, Y. (2019). Many-objective optimization of technology implementation in the industrial symbiosis system based on amodified nsga-iii.Journal of Cleaner Production, 245:118810.


Christudas, B., Kirubakaran, E., and Thangaiah, P. (2018). An evolutionary approachfor personalization of content delivery in e-learning systems based on learner behaviorforcing compatibility of learning materials.Telematics and Informatics, page 520–533.


Deb, K. and Jain, H. (2014). An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part i: Solving problemswith box constraints.IEEE Transactions on Evolutionary Computation, 18(4).


Dwivedi, P., Kant, V., and Bharadwaj, K. (2018). Learning path recommendation based onmodified variable length genetic algorithm.Education and Information Technologies.


Gonçalves, A., Vivas, A., Assis, L., Pitangui, C., and Dorça, F. (2016). Avanços na modelagem automática e dinâmica de estilos de aprendizagem de estudantes em sistemas adaptativos e inteligentes para educação: uma análise experimental.Brazilian Sympo-sium on Computers in Education (Simpósio Brasileiro de Informática na Educação -SBIE), 27(1):1006.


Jain, H. and Deb, K. (2014). An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part ii: Handling cons-traints and extending to an adaptive approach.IEEE Transactions on EvolutionaryComputation, 18(4):602–622.


Kamsa, I., Elouahbi, R., and Khoukhi, F. (2018). The combination between the individualfactors and the collective experience for ultimate optimization learning path using antcolony algorithm.Engineering and Information Technology, 8:1198–1208.


Li, M., Zhen, L., and Yao, X. (2017). How to read many-objective solution sets in parallelcoordinates.IEEE Computational Intelligence Magazine, 12.


Machado, M., Barrere, E., and Souza, J. (2019). Solving the adaptive curriculum sequencing problem with prey-predator algorithm.International Journal of DistanceEducation Technologies, 17:71–93.


Machado, M., Barrére, E., and Souza, J. (2018). Uma abordagem evolutiva para o problema de sequenciamento curricular adaptativo.Brazilian Symposium on Computersin Education (Simpósio Brasileiro de Informática na Educação - SBIE), 29(1):1243.


Sani, S. and Aris, T. N. M. (2014). Computational intelligence approaches for student/tutor modelling: A review. In2014 5th International Conference on IntelligentSystems, Modelling and Simulation, pages 72–76.


Shmelev, V., Karpova, M., and Dukhanov, A. (2015). An approach of learning path sequencing based on revised bloom’s taxonomy and domain ontologies with the use ofgenetic algorithms.Procedia Computer Science, page 711–719.


Vanitha, V. and Krishnan, P. (2019). A modified ant colony algorithm for personalized learning path construction.Journal of Intelligent & Fuzzy Systems, 37:1–16.


Vanitha, V., Krishnan, P., and R., E. (2019). Collaborative optimization algorithm forlearning path construction in e-learning.Computers & Electrical Engineering, 77.


Zhou, B., Liu, B., Yang, D., Cao, J., and Littler, T. (2020). Multi-objective optimal operation of coastal hydro-electrical energy system with seawater reverse osmosis desalination based on constrained nsga-iii.Energy Conversion and Management, 207:112533