@inproceedings{MaurerSejdijaSander2024,
  author    = {Maurer, Florian and Sejdija, Jonathan and Sander, Volker},
  title     = {Decentralized energy data storages through an Open Energy Database Server},
  doi       = {10.5281/zenodo.10607895},
  pages     = {5 Seiten},
  year      = {2024},
  abstract  = {In the research domain of energy informatics, the importance of open datais rising rapidly. This can be seen as various new public datasets are created andpublished. Unfortunately, in many cases, the data is not available under a permissivelicense corresponding to the FAIR principles, often lacking accessibility or reusability.Furthermore, the source format often differs from the desired data format or does notmeet the demands to be queried in an efficient way. To solve this on a small scale atoolbox for ETL-processes is provided to create a local energy data server with openaccess data from different valuable sources in a structured format. So while the sourcesitself do not fully comply with the FAIR principles, the provided unique toolbox allows foran efficient processing of the data as if the FAIR principles would be met. The energydata server currently includes information of power systems, weather data, networkfrequency data, European energy and gas data for demand and generation and more.However, a solution to the core problem - missing alignment to the FAIR principles - isstill needed for the National Research Data Infrastructure.},
  language  = {en}
}
@article{KohlKraemerFohryetal.2024,
  author    = {Kohl, Philipp and Kr{\"a}mer, Yoka and Fohry, Claudia and Kraft, Bodo},
  title     = {Scoping review of active learning strategies and their evaluation environments for entity recognition tasks},
  series = {Deep learning theory and applications},
  journal   = {Deep learning theory and applications},
  editor    = {Fred, Ana and Hadjali, Allel and Gusikhin, Oleg and Sansone, Carlo},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-031-66694-0 (online ISBN)},
  doi       = {10.1007/978-3-031-66694-0_6},
  pages     = {84 -- 106},
  year      = {2024},
  abstract  = {We conducted a scoping review for active learning in the domain of natural language processing (NLP), which we summarize in accordance with the PRISMA-ScR guidelines as follows: Objective: Identify active learning strategies that were proposed for entity recognition and their evaluation environments (datasets, metrics, hardware, execution time). Design: We used Scopus and ACM as our search engines. We compared the results with two literature surveys to assess the search quality. We included peer-reviewed English publications introducing or comparing active learning strategies for entity recognition. Results: We analyzed 62 relevant papers and identified 106 active learning strategies. We grouped them into three categories: exploitation-based (60x), exploration-based (14x), and hybrid strategies (32x). We found that all studies used the F1-score as an evaluation metric. Information about hardware (6x) and execution time (13x) was only occasionally included. The 62 papers used 57 different datasets to evaluate their respective strategies. Most datasets contained newspaper articles or biomedical/medical data. Our analysis revealed that 26 out of 57 datasets are publicly accessible. Conclusion: Numerous active learning strategies have been identified, along with significant open questions that still need to be addressed. Researchers and practitioners face difficulties when making data-driven decisions about which active learning strategy to adopt. Conducting comprehensive empirical comparisons using the evaluation environment proposed in this study could help establish best practices in the domain.},
  language  = {en}
}