@article{RoehrigSalzwedelLinckEleftheriadisetal.2015,
  author    = {R{\"o}hrig, Bernd and Salzwedel, Annett and Linck-Eleftheriadis, Sigrid and V{\"o}ller, Heinz and Nosper, Manfred},
  title     = {Outcome Based Center Comparisons in Inpatient Cardiac Rehabilitation Results from the EVA-Reha (R) Cardiology Project},
  series = {Die Rehabilitation : Zeitschrift f{\"u}r Praxis und Forschung in der Rehabilitation},
  volume    = {54},
  journal   = {Die Rehabilitation : Zeitschrift f{\"u}r Praxis und Forschung in der Rehabilitation},
  number    = {1},
  publisher = {Thieme},
  address   = {Stuttgart},
  issn      = {0034-3536},
  doi       = {10.1055/s-0034-1395556},
  pages     = {45 -- 52},
  year      = {2015},
  abstract  = {Background: So far, for center comparisons in inpatient cardiac rehabilitation (CR), the objective outcome quality was neglected because of challenges in quantifying the overall success of CR. In this article, a multifactorial benchmark model measuring the individual rehabilitation success is presented. Methods: In 21 rehabilitation centers, 5 123 patients were consecutively enrolled between 01/2010 and 12/2012 in the prospective multicenter registry EVA-Reha (R) Cardiology. Changes in 13 indicators in the areas cardiovascular risk factors, physical performance and subjective health during rehabilitation were evaluated according to levels of severity. Changes were only rated for patients who needed a medical intervention. Additionally, the changes had to be clinically relevant. Therefore Minimal Important Differences (MID) were predefined. Ratings were combined to a single score, the multiple outcome criterion (MEK). Results: The MEK was determined for all patients (71.7 +/- 7.4 years, 76.9 \% men) and consisted of an average of 5.6 indicators. After risk adjustment for sociodemographic and clinical baseline parameters, MEK was used for center ranking. In addition, individual results of indicators were compared with means of all study sites. Conclusion: With the method presented here, the outcome quality can be quantified and outcome-based comparisons of providers can be made.},
  language  = {de}
}
@article{WaitelonisJuergesSack2019,
  author    = {Waitelonis, J{\"o}rg and J{\"u}rges, Henrik and Sack, Harald},
  title     = {Remixing entity linking evaluation datasets for focused benchmarking},
  series = {Semantic Web},
  volume    = {10},
  journal   = {Semantic Web},
  number    = {2},
  publisher = {IOS Press},
  address   = {Amsterdam},
  issn      = {1570-0844},
  doi       = {10.3233/SW-180334},
  pages     = {385 -- 412},
  year      = {2019},
  abstract  = {In recent years, named entity linking (NEL) tools were primarily developed in terms of a general approach, whereas today numerous tools are focusing on specific domains such as e.g. the mapping of persons and organizations only, or the annotation of locations or events in microposts. However, the available benchmark datasets necessary for the evaluation of NEL tools do not reflect this focalizing trend. We have analyzed the evaluation process applied in the NEL benchmarking framework GERBIL [in: Proceedings of the 24th International Conference on World Wide Web (WWW'15), International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 2015, pp. 1133-1143, Semantic Web 9(5) (2018), 605-625] and all its benchmark datasets. Based on these insights we have extended the GERBIL framework to enable a more fine grained evaluation and in depth analysis of the available benchmark datasets with respect to different emphases. This paper presents the implementation of an adaptive filter for arbitrary entities and customized benchmark creation as well as the automated determination of typical NEL benchmark dataset properties, such as the extent of content-related ambiguity and diversity. These properties are integrated on different levels, which also enables to tailor customized new datasets out of the existing ones by remixing documents based on desired emphases. Besides a new system library to enrich provided NIF [in: International Semantic Web Conference (ISWC'13), Lecture Notes in Computer Science, Vol. 8219, Springer, Berlin, Heidelberg, 2013, pp. 98-113] datasets with statistical information, best practices for dataset remixing are presented, and an in depth analysis of the performance of entity linking systems on special focus datasets is presented.},
  language  = {en}
}
@phdthesis{Hesse2022,
  author    = {Hesse, G{\"u}nter},
  title     = {A benchmark for enterprise stream processing architectures},
  doi       = {10.25932/publishup-56600},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566000},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 148},
  year      = {2022},
  abstract  = {Data stream processing systems (DSPSs) are a key enabler to integrate continuously generated data, such as sensor measurements, into enterprise applications. DSPSs allow to steadily analyze information from data streams, e.g., to monitor manufacturing processes and enable fast reactions to anomalous behavior. Moreover, DSPSs continuously filter, sample, and aggregate incoming streams of data, which reduces the data size, and thus data storage costs. The growing volumes of generated data have increased the demand for high-performance DSPSs, leading to a higher interest in these systems and to the development of new DSPSs. While having more DSPSs is favorable for users as it allows choosing the system that satisfies their requirements the most, it also introduces the challenge of identifying the most suitable DSPS regarding current needs as well as future demands. Having a solution to this challenge is important because replacements of DSPSs require the costly re-writing of applications if no abstraction layer is used for application development. However, quantifying performance differences between DSPSs is a difficult task. Existing benchmarks fail to integrate all core functionalities of DSPSs and lack tool support, which hinders objective result comparisons. Moreover, no current benchmark covers the combination of streaming data with existing structured business data, which is particularly relevant for companies. This thesis proposes a performance benchmark for enterprise stream processing called ESPBench. With enterprise stream processing, we refer to the combination of streaming and structured business data. Our benchmark design represents real-world scenarios and allows for an objective result comparison as well as scaling of data. The defined benchmark query set covers all core functionalities of DSPSs. The benchmark toolkit automates the entire benchmark process and provides important features, such as query result validation and a configurable data ingestion rate. To validate ESPBench and to ease the use of the benchmark, we propose an example implementation of the ESPBench queries leveraging the Apache Beam software development kit (SDK). The Apache Beam SDK is an abstraction layer designed for developing stream processing applications that is applied in academia as well as enterprise contexts. It allows to run the defined applications on any of the supported DSPSs. The performance impact of Apache Beam is studied in this dissertation as well. The results show that there is a significant influence that differs among DSPSs and stream processing applications. For validating ESPBench, we use the example implementation of the ESPBench queries developed using the Apache Beam SDK. We benchmark the implemented queries executed on three modern DSPSs: Apache Flink, Apache Spark Streaming, and Hazelcast Jet. The results of the study prove the functioning of ESPBench and its toolkit. ESPBench is capable of quantifying performance characteristics of DSPSs and of unveiling differences among systems. The benchmark proposed in this thesis covers all requirements to be applied in enterprise stream processing settings, and thus represents an improvement over the current state-of-the-art.},
  language  = {en}
}