Refine
Year of publication
- 2024 (6) (remove)
Document Type
- Report (2)
- Article (1)
- Other (1)
- Study Thesis (1)
- Working Paper (1)
Keywords
- Data Engineering (1)
- Data Science (1)
- Datensatz (1)
- Dunkelflaute (1)
- Explainable Artificial Intelligence (1)
- Government (1)
- KI (1)
- Künstliche Intelligenz (1)
- Langzeitspeicherung (1)
- Light Simulation, Ray Tracing, Optical Design, Registration/License Plate Illumination, Light Distribution, Luminance, Automotive, UNECE R4 (1)
Data engineering is an integral part of the data science process. It comprises tasks such as data ingestion, data transformation, and data quality assurance. In order to fulfill these tasks, schema inference is an important capability. Its goal is to detect the structure of a dataset and to derive metadata on hierarchies, data types, etc. Artificial intelligence (AI) has the potential to automate schema inference and thus increase the efficiency of the data science process. However, as government institutions are subject to special regulations, explainability of AI models can be a mandatory requirement. Goal of this research protocol is to plan a systematic review of literature on schema inference with explainable AI (XAI) for data engineering in government institutions. This second version includes adjustments resulting from the first iteration of the review.
Diese Studienarbeit untersucht den Stromverbrauch auf regionaler Ebene in Deutschland und vergleicht drei verschiedene Systemdesigns für erneuerbare Energien. Die Systeme basieren auf dem Einsatz von geotechnischen, chemischen und Batteriespeicher-technologien. Es werden reale Wetter- und Lastdaten für einen Zeitraum von drei Jahren vom 01.09.2020 bis zum 31.08.2023 verwendet.
Recent flood events (FE) in Germany have shown that the extent and impact of extreme flood events cannot be estimated solely based on numerical models. For analyzing the development of such an event and to develop and implement safety measures more efficiently, additional data must be collected during the event. Within the scope of this research, the possibilities of near real-time recording using an unmanned aerial vehicle (UAV) and data processing with the Structure from Motion (SfM) method were tested in a case study. Different recording parameter combinations were tested in the Laufer
Muehle area on the Aisch river in Germany. The focus of the investigations was the identification of a parameter combination that allows a short recording interval for aerial imagery. Based on these findings, the identification of changes in the study area by comparing multitemporal photography (flood prevention), as well as the recording of flooded areas during a FE should be possible. The accuracy analysis of the different parameter combinations between two point clouds as well as the process of change detection was done by a Multiscale Model to Model Cloud Comparison (M3C2) and
including ground control points. As a result, a parameter combination was identified which led to the desired results in the study area. The processes were transformed into fully automated and scripted workflows. The results serve as a basis for establishing a workflow for near real-time analyses in future studies.
The illumination of registration plates poses challenges for lighting technology. To achieve the wide and steep angles required for homogeneous illumination of the license plate, optics are needed to refract and reflect light. In this work, registration plate lamps with different components are designed. After the construction, the concepts are tested for their limits in terms of position and manufacturability. The
entire work is carried out at the company CREAT GmbH in Ingolstadt. All developments in the field of registration plate lighting are subject to the UNECE and country-specific regulations, which must be considered in the development of the lights.[1] Some vehicles currently available on the automotive market are measured to classify and compare the different lamp systems. From the average values, the lamps are designed. Adjustments are repeatedly made to the lighting device to achieve the most
homogeneous illumination of the registration plate. As soon as the lights meet the legal requirements, the geometric limits of the lighting device are defined in relation to the plate. As there are different polymers to produce optics, these are simulated with their refractive indices and tested for their effects on the light image.
Ein Einsatzfeld Künstlicher Intelligenz im Bereich der Sozialen Arbeit ist die automatische Inhaltsanalyse von Konversationen aus der psychosozialen Onlineberatung. Mögliche Anwendungen sind die statistische Untersuchung von Wirkzusammenhängen sowie die Entwicklung KI-basierter Dialog-und Unterstützungssysteme. Die Grundlage für das Training entsprechender Modelle sind aussagekräftige und realistische Trainingsdaten. Im Rahmen des Projektes GeCCo (German e-Counseling Conversation Dataset) wurde ein erster deutschsprachiger Datensatz für die Analyse psychosozialer Beratungskonversationen erstellt und veröffentlicht. Wesentlicher Bestandteil ist ein neu entwickeltes Kategoriensystem, das eine feingranulare inhaltliche Klassifikation in 40 Berater-und 28 Klienten-Kategorien ermöglicht. Basierend auf dem Datensatz konnten erfolgreich verschiedene Modelle mithilfe maschineller Lernverfahren trainiert und für die wissenschaftliche Nutzung bereitgestellt werden.