Options
Akronym
GENERATING
Projekt Titel
Development and Implementation of an Adaptive Exercise Generator for Engineering Courses based on Artificial Intelligence
Förderkennzeichen
16DHB4007
Aktenzeichen
945.02-804
Startdatum
March 1, 2021
Enddatum
February 29, 2024
Loading...
Förderorganisation
Projektträger
Projektleitung
The project GENERATING aims to develop an artificial intelligence (AI) based adaptive task generator for technical and engineering courses at the Hamburg University of Technology. The project is jointly conducted by the Institute of Technical Logistics, Institute of Maritime Logistics, Center for Teaching and Learning and the IT department of the TUHH.
Personalized supervision is a proven way to improve learning progress and conceptual knowledge of students. With respect to the increasing amount of students, the use of task generators which create exercises automatically became increasingly popular in the last years.
A prototype of an automated exercise generator will be implemented in the existing learning management system (LMS) of the TUHH and will be applied in two teaching modules. The task generator will focus on technical and engineering tasks. The students learning behaviour, as well as their results will be evaluated by KI-based algorithms and will be compared to competence profiles. Based on this assessments, personalized feedback and individualized new exercises will be given to the students, to further improve their learning curve.
Personalized supervision is a proven way to improve learning progress and conceptual knowledge of students. With respect to the increasing amount of students, the use of task generators which create exercises automatically became increasingly popular in the last years.
A prototype of an automated exercise generator will be implemented in the existing learning management system (LMS) of the TUHH and will be applied in two teaching modules. The task generator will focus on technical and engineering tasks. The students learning behaviour, as well as their results will be evaluated by KI-based algorithms and will be compared to competence profiles. Based on this assessments, personalized feedback and individualized new exercises will be given to the students, to further improve their learning curve.