Conference Proceeding
Refine
Year of publication
- 2024 (9)
- 2023 (35)
- 2022 (46)
- 2021 (48)
- 2020 (46)
- 2019 (74)
- 2018 (64)
- 2017 (66)
- 2016 (66)
- 2015 (71)
- 2014 (51)
- 2013 (57)
- 2012 (59)
- 2011 (44)
- 2010 (48)
- 2009 (52)
- 2008 (37)
- 2007 (44)
- 2006 (60)
- 2005 (23)
- 2004 (22)
- 2003 (22)
- 2002 (25)
- 2001 (12)
- 2000 (12)
- 1999 (7)
- 1998 (8)
- 1997 (8)
- 1996 (4)
- 1995 (4)
- 1993 (6)
- 1992 (3)
- 1991 (2)
- 1990 (1)
- 1989 (3)
- 1988 (3)
- 1986 (1)
- 1985 (2)
- 1984 (3)
- 1983 (2)
- 1981 (2)
- 1980 (1)
- 1979 (1)
- 1978 (3)
- 1975 (2)
- 1973 (2)
Institute
- Fachbereich Elektrotechnik und Informationstechnik (234)
- Fachbereich Medizintechnik und Technomathematik (210)
- Fachbereich Luft- und Raumfahrttechnik (182)
- Fachbereich Energietechnik (177)
- IfB - Institut für Bioengineering (147)
- Solar-Institut Jülich (110)
- Fachbereich Maschinenbau und Mechatronik (107)
- Fachbereich Bauingenieurwesen (75)
- ECSM European Center for Sustainable Mobility (52)
- Fachbereich Wirtschaftswissenschaften (51)
Language
- English (1161) (remove)
Document Type
- Conference Proceeding (1161) (remove)
Keywords
- Biosensor (25)
- CAD (7)
- Finite-Elemente-Methode (7)
- civil engineering (7)
- Bauingenieurwesen (6)
- Blitzschutz (6)
- Enterprise Architecture (5)
- Clusterion (4)
- Energy storage (4)
- Gamification (4)
In collaborative research projects, both researchers and practitioners work together solving business-critical challenges. These projects often deal with ETL processes, in which humans extract information from non-machine-readable documents by hand. AI-based machine learning models can help to solve this problem.
Since machine learning approaches are not deterministic, their quality of output may decrease over time. This fact leads to an overall quality loss of the application which embeds machine learning models. Hence, the software qualities in development and production may differ.
Machine learning models are black boxes. That makes practitioners skeptical and increases the inhibition threshold for early productive use of research prototypes. Continuous monitoring of software quality in production offers an early response capability on quality loss and encourages the use of machine learning approaches. Furthermore, experts have to ensure that they integrate possible new inputs into the model training as quickly as possible.
In this paper, we introduce an architecture pattern with a reference implementation that extends the concept of Metrics Driven Research Collaboration with an automated software quality monitoring in productive use and a possibility to auto-generate new test data coming from processed documents in production.
Through automated monitoring of the software quality and auto-generated test data, this approach ensures that the software quality meets and keeps requested thresholds in productive use, even during further continuous deployment and changing input data.
Humic substances possess distinctive chemical features enabling their use in many advanced applications, including biomedical fields. No chemicals in nature have the same combination of specific chemical and biological properties as humic substances. Traditional medicine and modern research have demonstrated that humic substances from different sources possess immunomodulatory and anti-inflammatory properties, which makes them suitable for the prevention and treatment of chronic dermatoses, allergic rhinitis, atopic dermatitis, and other conditions characterized by inflammatory and allergic responses [1-4]. The use of humic compounds as agentswith antifungal and antiviral properties shows great potential [5-7].