Logo des Repositoriums

Auflistung nach Schlagwort "Data Analysis"

1 - 4 von 4
  • Konferenzbeitrag
    Comparison of Classifiers for Eye-Tracking Data
    (INFORMATIK 2024, 2024) Landes, Jennifer; Köppl, Sonja; Klettke, Meike
    This paper delves into the initial stages of data analysis, focusing on the classification of eye-tracking data. Six machine learning algorithms, namely XGBoost, Random Forest, Naive Bayes, Logistic Regression, Gradient Boosting Machines, and Neural Networks, were employed to predict cheating behavior based on a dataset comprising records from 25 students. Their performance was evaluated using metrics such as accuracy, precision, recall, F1 score, confusion matrix, and feature importance. Results indicate that Random Forest and its optimized version exhibit balanced performance, making them promising candidates for cheating prediction. The overarching research project investigates academic misconduct in the realm of online assessments, seeking to comprehend the behaviors and methodologies involved. An eye-tracking experiment was conducted to gain deeper insights into the timing and mannerisms of students engaging in academic misconduct.
  • Textdokument
    Identifying a Trial Population for Clinical Studies on Diabetes Drug Testing with Neural Networks
    (SKILL 2021, 2021) Löhr, Tim
    This project aims to model an end-to-end workflow of implementing different Artificial Intelligence (AI) tools for a clinical environment. A possible use case, such as the selection process of patients for a novel treatment, will be conducted by estimating the hospitalization time with a Neural Network on an Electronic Health Record (EHR) of diabetes. Then, Explainable AI (XAI) methods are computed for models trained with a Random Forest to evaluate the predictions. The diabetes readmission EHR dataset from the University of California, Irvine (UCI) Diabetes is used for this project. The trial population is selected by predicting the expected days for a person being hospitalized. An arbitrary boundary is set for choosing whether or not a patient shall be included into the trial. If so, a clear explanation of how the prediction is calculated and additional possible risk factors will be given in order to make the workflow explainable. This project shows that given a proper explanatory approach, AI can be a useful tool for the modern clinical environment. The workflow finally reveals that AI can be a beneficial support tool for doctors in the patient selection process.
  • Zeitschriftenartikel
    Standardisierung der europaweiten Berichterstattung im Rahmen der Messung der Gesamtenergieeffizienz von Gebäuden
    (Wirtschaftsinformatik: Vol. 49, No. 5, 2007) Gräning, André; Kienegger, Harald
    KernpunkteEs besteht keine technische Rahmenvorgabe zur Unterstützung der Berichterstattung im Rahmen der Messung der Energieeffizienz von Gebäuden.Durch die Vorgabe der Europäischen Union entsteht Handlungsbedarf zur Standardisierung der Berichterstattung.Mit XBRL besteht bereits ein Kommunikationsstandard, der im Rahmen der Finanzberichterstattung eingesetzt wird.Anhand unterschiedlicher Kriterien wird untersucht, ob sich XBRL auch auf die Energieeffizienzberichterstattung in Rahmen der Vorgaben der Europäischen Union übertragen lässt.AbstractThe introduction of the European Directive on the Energy Performance of Buildings is a further step taken by the European Union (EU) in order to harmonise the legislation within the 27 member states. However, achieving a high level of legal standardisation, each member country is left alone as far as technical harmonisation is being considered. But this situation leads to different implementations of the directive across the member states and it complicates the comparability across the EU. A supporting approach can be observed in the Basel II and International Financial Reporting Standards (IFRS) implementation of the EU by the Committee of European Banking Supervisors (CEBS) using the eXtensible Business Reporting Language (XBRL). The use of XBRL, being constructed mainly for business reporting data, can be also considered in various other areas. The paper presents an approach to use XBRL as a mean of standardisation for the reporting concerning the energy performance of buildings. The paper addresses the issue of such an approach and can be generalised and applied in other domains.
  • Konferenzbeitrag
    Virtuous, multi-level integration of research and education within the project “European Digital Dynamic Mapping” (EDDY)
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Rettig, Rasmus; Weltz, Maximilian
    Project- and Problem-Based Learning has been subject to research and implementation in engineering and computer science curricula for about the last 20 years. However, the projects and problems focused on in education have hardly been questioned for their relevance and effect. Considering current global and financial challenges, the authors propose to revise project- and problem-based approaches in education in the context of relevance and excellence in applied research. Besides coping with current cost-cutting, existing control mechanisms could ensure both relevance and excellence. Example projects based on more than 10 years of hands-on experience in Project-Based Learning in the context of externally funded research, for various classroom situations are included.