While learning personalization offers great potential for learners, modern practices in higher education require a deeper consideration of domain models and learning contexts, to develop effective personalization algorithms. This paper introduces an innovative approach to higher education curriculum modelling that utilizes large language models (LLMs) for knowledge graph (KG) completion, with the goal of creating personalized learning-path recommendations. Our research focuses on modelling university subjects and linking their topics to corresponding domain models, enabling the integration of learning modules from different faculties and institutions in the student's learning path. Central to our approach is a collaborative process, where LLMs assist human experts in extracting high-quality, fine-grained topics from lecture materials. We develop a domain, curriculum, and user models for university modules and stakeholders. We implement this model to create the KG from two study modules: Embedded Systems and Development of Embedded Systems Using FPGA. The resulting KG structures the curriculum and links it to the domain models. We evaluate our approach through qualitative expert feedback and quantitative graph quality metrics. Domain experts validated the relevance and accuracy of the model, while the graph quality metrics measured the structural properties of our KG. Our results show that the LLM-assisted graph completion approach enhances the ability to connect related courses across disciplines to personalize the learning experience. Expert feedback also showed high acceptance of the proposed collaborative approach for concept extraction and classification.

In the era of personalized education, the provision of comprehensible explanations for learning recommendations is of great value to enhance the learner's understanding and engagement with the recommended learning content. Large language models (LLMs) and generative AI have recently opened new doors for generating human-like explanations, for and along learning recommendations. However, their precision is still far away from acceptable in a sensitive field like education. To harness the abilities of LLMs, while still ensuring a high level of precision towards the intent of the learners, this paper proposes an approach to utilize knowledge graphs (KG) as a source of factual context for LLM prompts, reducing the risk of model hallucinations, and safeguarding against wrong or imprecise information, while maintaining an application-intended learning context. We utilize the semantic relations in the knowledge graph to offer curated knowledge about learning recommendations. With domain-experts in the loop, we design the explanation as a textual template, which is filled and completed by the LLM. Domain experts were integrated in the prompt engineering phase as part of a study, to ensure that explanations include information that is relevant to the learner. We evaluate our approach quantitatively using Rouge-N and Rouge-L measures, as well as qualitatively with experts and learners. Our results show an enhanced recall and precision of the generated explanations compared to those generated solely by the GPT model, with a greatly reduced risk of generating imprecise information in the final learning explanation.

In emergencies, treatment needs to be fast, accu-rate and patient-specific. For instance, in emergency scenarios, obstacles like treatment environments and medical difficulties can lead to bad outcomes for patients. Additionally, a drastic change of health vitals can force paramedics to shift to a different treatment in the ongoing treatment of the patient in order to save a patient's life. The KIRETT (engl.: 'Artificial intelligence in rescue operations ‘) demonstrator is developed to provide a rescue operator with a wrist-worn device, enabling treatment recommendation (with the help of knowledge graph) with situation detection models to improve the emergency treatment of a patient. This paper aims to provide a qualitative evaluation of the 2-days testing in the KIRETT project with the focus of knowledge graphs, knowledge fusion, and user-experience-design (UX-design).

Modelling learning objects (LO) within their context enables the learner to advance from a basic, remembering-level, learning objective to a higher-order one, i.e., a level with an application- and analysis objective. While hierarchical data models are commonly used in digital learning platforms, using graph-based models enables representing the context of LOs in those platforms. This leads to a foundation for personalized recommendations of learning paths. In this paper, the transformation of hierarchical data models into knowledge graph (KG) models of LOs using text mining is introduced and evaluated. We utilize custom text mining pipelines to mine semantic relations between elements of an expert-curated hierarchical model. We evaluate the KG structure and relation extraction using graph quality-control metrics and the comparison of algorithmic semantic-similarities to expert-defined ones. The results show that the relations in the KG are semantically comparable to those defined by domain experts, and that the proposed KG improves representing and linking the contexts of LOs through increasing graph communities and betweenness centrality.

The growth of online job-posting repositories provided job-seekers with access to a large number of potential jobs. User assessment of recommended jobs becomes especially a tedious and time-consuming task with the overwhelming number of job recommendations. To enhance the job-seeker’s ability to evaluate the suitability of a recommended job, we propose an explainable job recommendation system, which matches the user to the most relevant jobs based on their profile. Then, the system explains to the user why each job-posting has been recommended to them. The proposed system uses a knowledge graph (KG) structure to model job-postings and user profiles in one homogeneous structure. Graph relations between the job-seekers and job-postings are mined through natural language processing (NLP) of the textual content from job-postings and user-profiles. Based on the graph structure itself and a customized named entity classifier, a human-readable explanation is generated for each recommendation and provided to the job-seeker. The explanation includes information about the matching factors that led the system to recommend a certain job-posting to the user. The proposed system is implemented and tested on a sample data-set of user profiles and job-postings from open online repositories. We use BELU and Rouge-L scores to show that the proposed systems generated relevant explanations for recommended jobs.

In recent years, the availability of modern technology increased drastically with the raising availability of integrated devices and applications, such as mobile phones, voice assistant systems smart home appliances and many more. This paved the way for the semiconductor industry to become one of the fastest growing industries. Knowing, planning, and stabilizing the yield of semiconductor manufacturing is highly important to meet the rising demand. One indication for potential root causes is the identification of defect patterns on wafers. Wafers are the base silicon layer on which sets of chips are manufactured. If a certain process damages chips, then this produces characteristic patterns of failing chips on the wafer, which are then investigated by engineers to isolate the root-cause. According to studies, human-expert based defect pattern recognition methods have a maximum accuracy of about 45%. To help engineers to improve recognition and root cause analysis of defect patterns, this paper introduces a novel process for analysis. For this, unsupervised machine learning and clustering techniques are utilized to identify and group unknown defect patterns. A tailored process is introduced, using autoencoders and an iterative classification, which is tested on a use case with a pre-known root cause.

The maintenance and repair of modern vehicles is a challenge for garages, as different causes of faults lead to similar symptoms in the highly complex vehicles these days. Existing processes for fault-diagnosis based on manufacturer service manuals and human experiences are often inadequate and result in high effort and wrong decisions. In addition to these service manuals which provide basic models for e.g., diagnostic terms, primary physical quantities, causal relationships, and plausibilities, nowadays, internet forums offer a comprehensive source of experiences for solutions to these challenges. This paper, therefore, presents methods for the extraction of knowledge from unstructured and informal contributions in internet forums with the goal to synthesize diagnostic graphs from the established knowledge base, which are part of a maintenance software to supports garages in the maintenance of vehicles by suggesting more efficient and target-oriented diagnostic and maintenance actions in real-time.

The society is in a state where learning has no limits and starts to overlap with technological developments. The recent advent of a connectivistic learning theory promises to shed light on how we learn in environments of interconnected knowledge and how the connectivity of concepts can guide the learning and conceptualization. This paper will have a look at a domain ontology-based approach to learning and assessment and investigate if the connectivity of the stored concepts, measured by a selected set of centrality measures, can provide a prediction of the assessment performance. The analysis will be conducted on a real world application with 247 students in the field of business informatics.