IGNITE
Individual Support in STEM Teaching (IGNITE) - The rapid expansion of educational programs and learning resources has led to significant overlap in content. This makes the development of coherent learning pathways more difficult and teachers face the challenge of responding to the diverse needs of students. This project presents a knowledge graph-based recommendation system that links learners' prior knowledge with curricular components, thereby enabling personalized course progressions and adaptive curriculum design. By utilizing structured semantic representations, the framework reduces redundancy, improves content coherence and promotes a more responsive educational environment.
Project description
Significant individual differences in students' knowledge and skills pose a challenge to meeting course requirements and achieving program-wide learning objectives. Offering courses that fully cover all missing knowledge is hardly practicable due to limited teaching capacities and credit constraints, while excessive repetition of already known content reduces the attractiveness of the curriculum. This problem is particularly relevant in the transition from different national and international Bachelor's degree courses to a Master's degree course.
The project addresses this challenge through personalized teaching within modularized courses, in which individual knowledge gaps are closed through a needs-based compilation of module elements foreach student. Knowledge graphs model both the students' competencies and the dependencies between the module elements, thereby enabling tools for generating optimized, individual learning and course progressions. The project will focus on various modular courses and carry out an experimental evaluation with students of computer science and digital health sciences
Focus of the project
- Personalized learning: generation of individual learning and course progressions based on students' prior knowledge and learning objectives
- Adaptive curriculum: Supporting teachers in adapting teaching content and reducing redundancies.
- Knowledge graphs: Using semantic representations to model competencies and content for coherent learning pathways.
Everything at a glance
-
Duration
01.04.2024 - 31.03.2026 (Completed) -
Research area
LLM and digital teaching -
Funding
Free space: 426.200,00€
Research methods & procedure
FRACTAL adopts a disruptive, cross‑layer methodology. The project uses cutting‑edge microelectronics, high‑performance processors and AI techniques to build a modular, open reference architecture for cognitive edge computing. A modular open reference architecture allows components to be selected and configured based on application needs and is visualised through the FRACTAL System configurator. Hardware advances include a Hierarchical Adaptive Time‑Triggered Multicore Architecture (HATMA) that enables adaptation while balancing safety, security, power and environmental scenarios; it leverages an Adaptive Time‑Triggered Network on Chip (ATTNoC) for scheduling adaptation. An AI‑based metascheduler supports dependable, time‑critical scheduling and run‑time adaptation. The software stack uses microservices and provides data ingestion, storage, orchestration and containerised ML model servers; this ensures the same open architecture across low‑, mid‑ and high‑end edge nodes. FRACTAL validated its methodology through eight real‑world use cases, demonstrating the modular architecture and edge AI capabilities across domains
Development of specialized AI models
We are developing modern AI models that are trained to recognize complex patterns in the electrical activity of the heart. We focus on five central topics: the evaluation of signal quality, precise heartbeat detection and the detailed analysis of rhythm, morphology and specific cardiological events.
Implementation of a cloud edge architecture
To make the analysis highly efficient, we use a combined computing strategy. This involves pre-processing the data directly on the mobile device (edge), while computationally intensive analyses are carried out in the cloud. This enables fast and in-depth monitoring of cardiac arrhythmias in real time.
Assessment of learning progress
Processes and algorithms will be developed to identify learning gaps, align FlexModules with accreditation requirements and create personalized assessment forms. These results will be incorporated into the best practice guide.
Pilot projects and evaluation
The project designs pilot projects in blended and flipped classroom formats, develops learning and evaluation platforms, obtains the necessary approvals, carries out the pilots, collects data and defines strategies for disseminating the results.
