open_access
Refine
Year
Publication Type
- Article (121)
- Report (34)
- Conference Proceeding (19)
- Book (11)
- Contribution to a Periodical (5)
- Other (5)
- Bachelor Thesis (3)
- Part of a Book (3)
- Working Paper (3)
- Part of Periodical (2)
Keywords
- PIV (4)
- renewable energy (4)
- wind turbine (4)
- Blockchain (3)
- Lüftungstechnik (3)
- Nachhaltigkeit (3)
- instationäre Lüftung (3)
- BBNE (2)
- Spreadsheet Energy System Model Generator (2)
- Third culture kids (2)
Faculty
AI-based chatbots as enabler for efficient external knowledge management in public administration
(2024)
This study addresses the pressing issue of staff shortages in German public administrations through the lens of digitalization, focusing on the potential of AI-based chatbots to solve this problem by replacing human labour. Employing a Design Science Research Process (DSRP) methodology, the research synthesizes theoretical foundations and regulatory frameworks to develop a robust chatbot concept. The artifact presented is a comprehensive architectural framework integrating user-centric design, linguistic processing, and regulatory compliance. The proposed artifact navigates complex federal structures and diverse IT infrastructures, promoting accessibility and inclusivity. Implications suggest enhanced efficiency and accessibility in public service delivery for potentially increasing citizen satisfaction and decreasing employee workload. The study underscores the importance of legal compliance and the evolving regulatory landscape in AI deployment. Future research will involve prototyping and evaluating the artifact's performance and applicability throughout the course of the DSRP, thus contributing to the advancement of digital transformation in public administrations.
This study presents a comprehensive evaluation of force sensors manufactured through conventional CNC machining, laser powder bed fusion (LPBF), and material extrusion (MEX) 3D printing methods. The study utilized a combination of finite element method (FEM) simulations, functional testing, durability assessments, and ultimate strength testing in order to assess the viability of additive manufacturing for sensing technology applications. The FEM simulations provided a preliminary framework for predictive analysis, closely aligning with experimental outcomes for LPBF and conventionally manufactured sensors. Nevertheless, discrepancies were observed in the performance of MEX-printed sensors during ultimate strength testing, necessitating the implementation of more comprehensive modeling approaches that take into account the distinctive material characteristics and failure mechanisms. Functional testing confirmed the operational capability of all sensors, thereby demonstrating their suitability for the intended application. Moreover, all sensors exhibited resilience during 50,000 cycles of cyclic testing, indicating reliability, durability, and satisfactory fatigue life performance. Notably, sensors produced via LPBF exhibited a significant increase in strength, nearly three times that of conventionally manufactured sensors. These findings suggest the potential for innovative sensor design and the expansion of their use into higher-loaded applications. Overall, while both LPBF and conventional methods demonstrated reliability and closely matched simulation predictions, further research is necessary to refine modeling approaches for MEX-printed sensors and fully unlock their potential in sensing technology applications. These findings indicate that additive manufacturing of metals may be a viable alternative for the fabrication of biomedical sensors.
Unter dem Titel „DO-IT-YOURHEALTH!” wurde im Rahmen des “Coburger Wegs” und hier im Modul ⅔ “Interdisziplinäre Projekte” eine online Gesundheitsförderung vom 15.11.2015 bis zum 11.12.2015 an der Hochschule Coburg durchgeführt. Diese richtete sich an alle Studierende mit dem Ziel, deren Gesundheitsbewusstsein in den Bereichen Ernährung, Bewegung und Innere Haltung zu stärken.
Imaging methods by the means of optical sensors are applied in diverse scientific areas such as medical research and diagnostics, aerodynamics, environmental analysis, or marine research. After a general introduction to the field, this review is focused on works published between 2012 and 2022. The covered topics include planar sensors (optrodes), nanoprobes, and sensitive coatings. Advanced sensor materials combined with imaging technologies enable the visualization of parameters which exhibit no intrinsic color or fluorescence, such as oxygen, pH, CO2, H2O2, Ca2+, or temperature. The progress on the development of multiple sensors and methods for referenced signal read out is also highlighted, as is the recent progress in device design and application formats using model systems in the lab or methods for measurements’ in the field.
Background
Artificial intelligence (AI) has the capability to analyze vast amounts of data and has been applied in various healthcare sectors. However, its effectiveness in aiding pharmacotherapy decision-making remains uncertain due to the intricate, patient-specific, and dynamic nature of this field.
Objective
This study sought to investigate the potential of AI in guiding pharmacotherapy decisions using clinical data such as diagnoses, laboratory results, and vital signs obtained from routine patient care.
Methods
Data of a previous study on medication therapy optimization was updated and adapted for the purpose of this study. Analysis was conducted using R software along with the tidymodels extension packages. The dataset was split into 74% for training and 26% for testing. Decision trees were selected as the primary model due to their simplicity, transparency, and interpretability. To prevent overfitting, bootstrapping techniques were employed, and hyperparameters were fine-tuned. Performance metrics such as areas under the curve and accuracies were computed.
Results
The study cohort comprised 101 elderly patients with multiple diagnoses and complex medication regimens. The AI model demonstrated prediction accuracies ranging from 38% to 100% for various cardiovascular drug classes. Laboratory data and vital signs could not be interpreted, as the effect and dependence were unclear for the model. The study revealed that the issue of AI lag time in responding to sudden changes could be addressed by manually adjusting decision trees, a task not feasible with neural networks.
Conclusion
In conclusion, the AI model exhibited promise in recommending appropriate medications for individual patients. While the study identified several obstacles during model development, most were successfully resolved. Future AI studies need to include the drug effect, not only the drug, if laboratory data is part of the decision. This could assist with interpreting their potential relationship. Human oversight and intervention remain essential for an AI-driven pharmacotherapy decision support system to ensure safe and effective patient care.