Modelling in Science Education and Learning - Vol. 14, Núm. 1 (2021)
Tabla de contenidos
- Aprender como una máquina: introduciendo la Inteligencia Artificial en la enseñanza secundaria
- Redes neuronales en el fútbol
- Introduciendo la Modelización Matemática Temprana en Educación Infantil: un marco para resolver problemas reales
- Taller móvil de medida de la contaminación
- E–aplan: una herramienta para la enseñanza de la planificación colaborativa de la producción agregada en ingeniería industrial
URI permanente para esta colecciónhttps://riunet.upv.es/handle/10251/161652
Examinar
Envíos recientes
Item type: Artículo , Access status: Abierto , E-aplan: a tool for teaching collaborative aggregate production planning in industrial engineering(Universitat Politècnica de València, 2021-01-27) Poler, R.; Andres, B.; Guzmán Ortiz, Eduardo; Departamento de Organización de Empresas; Centro de Investigación en Gestión e Ingeniería de Producción; Escuela Politécnica Superior de Alcoy; Generalitat Valenciana[EN] In this paper, we present a software tool entitled E-aplan Express (version 2018), with free access for educational and commercial use, to the modelling and resolution of aggregate production plans generating medium-long term production planning, based on a forecasted demand in that period. E-aplan tool models the aggregate production plan though a mixed integer linear programming model (MILP). The LP solver optimization engine generates the planning by adjusting all the optimization variables with the least possible error. Finally, it is presented an illustrative example that considers a collaborative aggregate production planning, in a two-echelon supply chain. Different scenarios are modelled in order to simultaneously consider the planning objectives of both enterprises of the network.Item type: Artículo , Access status: Abierto , Taller móvil de medida de la contaminación(Universitat Politècnica de València, 2021-01-27) Navarro LLopis, Asunción[EN] Using portable pollution measuring equipment, students investigate the air quality of their surrounding area, learn to handle with a large volume of data and establish cause-effect relationships, while becoming aware of the importance of modelling. The work is set within the service-learning methodological framework and favours the achievement of the Sustainable Development Goals promoted by the United Nations. With the implementation of the proposal, an increase in the critical thinking skills of students and their active participation in improving the living conditions of their community is observed.Item type: Artículo , Access status: Abierto , Introduciendo la Modelización Matemática Temprana en Educación Infantil: un marco para resolver problemas reales(Universitat Politècnica de València, 2021-01-27) Alsina, Angel; Salgado, María[EN] An Early Mathematical Modelling activity designed from a seven-phase modelling cycle is described and analysed: comprehension, structuring, mathematization, mathematical work, interpretation, validation, and exposition/presentation. The activity has been implemented in 19 4-5 years old children and has been analysed from the Rubric for the Evaluation of Mathematical Modelling Processes (REMMP), with specific indicators for Early Childhood Education. The results show that children are able to solve a real problem from a modelling cycle, creating a model based on the mathematical knowledge they mobilize. It is concluded that teachers interested in implementing modelling activities should rely on instruments that serve both to analyse student learning and to improve teaching practice.Item type: Artículo , Access status: Abierto , Redes neuronales en el fútbol(Universitat Politècnica de València, 2021-01-27) Sancho Barrios, Llorenç; Sanmartin Vich, Onofre; Roger de la Resurreccion, Carlos[EN] Machine learning provides the ability to examine massive datasets and discover patterns within the data without relying on a priori assumptions. Its application to the field of sport (which is experiencing rapid growth) is divided into predictive (training programmes, results...) and explanatory (injuries) models. In this report, which is part of a final project for a master’s degree course, we use unsupervised learning techniques (self-organised maps and clustering) to group players according to different statistics (passes, goals, fouls, etc.) and compare the results with their real playing positions. We also describe the tools used to implement and visualise the results, so that a reader can be inspired to carry out their own project.Item type: Artículo , Access status: Abierto , Aprender como una máquina: introduciendo la Inteligencia Artificial en la enseñanza secundaria(Universitat Politècnica de València, 2021-01-27) Calabuig, J. M.; García-Raffi, L. M.; Sánchez Pérez, Enrique Alfonso; Departamento de Matemática Aplicada; Instituto Universitario de Matemática Pura y Aplicada; Escuela Técnica Superior de Ingeniería de Caminos, Canales y Puertos; Escuela Técnica Superior de Ingeniería Industrial[EN] Artificial intelligence is present in the usual environment of all high school students. However, the general population—and students in particular—do not know how these algorithmic techniques work, which often have very simple mechanisms and can be explained at an elementary level in mathematics or technology classes in the Secondary Education. Possibly these contents will take many years to form part of the curricula of these subjects, but they can be introduced as part of the algebra contents that are explained in mathematics, or those related to the algorithms, in the computer lectures. Especially if they are proposed in the form of a game, in which different groups of students can compete, as we propose in this article. Thus, we present a very simple example of an algorithm of teaching of reinforcement (Machine Learning-Reinforcement Learning), that synthesizes in a playful activity the fundamental elements that constitute an algorithm of artificial intelligence.