In modular educational systems, students have a certain degree of freedom to choose their own subjects. Usually, the choices a student is allowed to make are subject to constraints, such like choosing courses from given pools of electives. This pedagogical concept is already practiced in certain parts of Europe, like in the German Gymnasium and is being increasingly adopted in other countries (i.e. in Austria with the "modulare Oberstufe"). However implementing such a course election system in practice is a major challenge for educational institutions, that can only be solved using advanced optimization algorithms and AI techniques. In this applied research project we investigate algorithms for solving different variants of this problem efficiently and help schools and educational institutions implement this concept in practice.

Course scheduling for modular educational system
Department of Science & Technology
Project Description
- Further Information
- Status: Ongoing
- Project ID : 1609
-
Sponsor
:
Land NÖ
- Project Leader
- Dr. Rubén Ruiz TorrubianoSenior Lecturer Institute Digitalisation and Informatics
Dr. Rubén Ruiz Torrubiano
Senior Lecturer Institute Digitalisation and Informatics
Institute Digitalisation and Informatics
- Combinatorial optimization
- Machine learning / data mining
- Systems architecture
- UnternehmensführungBachelor of Arts in Business / full-time
- InformaticsBachelor of Science in Engineering / full-time
- Digital Business Innovation and TransformationMaster of Arts in Business / part-time
-
Kursplanung in modularen Schulsystemen
Project Leader, Department of Science & Technology
-
BRfit für Künstliche Intelligenz
Department of Business
-
Dataskop – Sensor-Based Data Economy in Niederösterreich
Department of Science & Technology
Dhungana, D., Haselböck, A., Ruiz-Torrubiano, R., Wallner, S. (2022): Variability of safety risks in production environments. In Alexander Felfernig et. al. (Hrsg.), SPLC '22: Proceedings of the 26th ACM International Systems and Software Product Line Conference (178-187). Graz, Austria: Association for Computing Machinery.
Doi: https://doi.org/10.1145/3546932.3547074Ruiz-Torrubiano, R., Suárez, A. (2015): A memetic algorithm for cardinality-constrained portfolio optimization with transaction costs. Applied Soft Computing, 36: 125-142.
Doi: https://doi.org/10.1016/j.asoc.2015.06.053Ruiz-Torrubiano, R., Suarez, A. (2011): The TransRAR crossover operator for genetic algorithms with set encoding. In Ruiz-Torrubiano, R., Suarez, A. (Hrsg.), Proceedings of the 13th annual conference on Genetic and evolutionary computation (489-496). New York: Association for Computing Machinery.
Doi: https://doi.org/10.1145/2001576.2001644Ruiz-Torrubiano, R., Suarez, A. (2010): Hybrid approaches and dimensionality reduction for portfolio selection with cardinality constraints. IEEE Computational Intelligence Magazine, 5(2): 92-107.
Doi: https://doi.org/10.1109/MCI.2010.936308Ruiz-Torrubiano, R., García-Moratilla, S., Suárez, A. (2010): Optimization problems with cardinality constraints. In Ruiz-Torrubiano, R., García-Moratilla, S., Suárez, A. (Hrsg.), Optimization problems with cardinality constraints (105-130). Berlin Heidelberg: Springer.
Doi: https://doi.org/10.1007/978-3-642-12775-5_5Ruiz-Torrubiano, R., Suárez, A. (2009): A hybrid optimization approach to index tracking. Annals of Operations Research, 166(1): 57-71.
Doi: https://doi.org./10.1007/s10479-008-0404-4Ruiz-Torrubiano, R., Suárez, A. (2007): Use of heuristic rules in evolutionary methods for the selection of optimal investment portfolios. In IEEE (Hrsg.), IEEE. Singapore: IEEE.
Doi: https://doi.org/10.1109/CEC.2007.4424474Moral-Escudero, R., Ruiz-Torrubiano, R., Suárez, A. (2006): Selection of optimal investment portfolios with cardinality constraints. In Moral-Escudero, R., Ruiz-Torrubiano, R., Suárez, A. (Hrsg.), 2006 IEEE International Conference on Evolutionary Computation (2382-2388). New York: IEEE.
Doi: https://doi.org/10.1109/CEC.2006.1688603Hernández-Lobato, D., Hernández-Lobato, J., Ruiz-Torrubiano, R., Valle, A. (2006): Pruning adaptive boosting ensembles by means of a genetic algorithm. In Hernández-Lobato, D., Hernández-Lobato, J., Ruiz-Torrubiano, R., Valle, A. (Hrsg.), International Conference on Intelligent Data Engineering and Automated Learning (322-329). Berlin Heidelberg: Springer.
Doi: https://doi.org/10.1007/11875581_39