@phdthesis{Zieger2017,
  author    = {Zieger, Tobias},
  title     = {Self-adaptive data quality},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-410573},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 125},
  year      = {2017},
  abstract  = {Carrying out business processes successfully is closely linked to the quality of the data inventory in an organization. Lacks in data quality lead to problems: Incorrect address data prevents (timely) shipments to customers. Erroneous orders lead to returns and thus to unnecessary effort. Wrong pricing forces companies to miss out on revenues or to impair customer satisfaction. If orders or customer records cannot be retrieved, complaint management takes longer. Due to erroneous inventories, too few or too much supplies might be reordered. A special problem with data quality and the reason for many of the issues mentioned above are duplicates in databases. Duplicates are different representations of same real-world objects in a dataset. However, these representations differ from each other and are for that reason hard to match by a computer. Moreover, the number of required comparisons to find those duplicates grows with the square of the dataset size. To cleanse the data, these duplicates must be detected and removed. Duplicate detection is a very laborious process. To achieve satisfactory results, appropriate software must be created and configured (similarity measures, partitioning keys, thresholds, etc.). Both requires much manual effort and experience. This thesis addresses automation of parameter selection for duplicate detection and presents several novel approaches that eliminate the need for human experience in parts of the duplicate detection process. A pre-processing step is introduced that analyzes the datasets in question and classifies their attributes semantically. Not only do these annotations help understanding the respective datasets, but they also facilitate subsequent steps, for example, by selecting appropriate similarity measures or normalizing the data upfront. This approach works without schema information. Following that, we show a partitioning technique that strongly reduces the number of pair comparisons for the duplicate detection process. The approach automatically finds particularly suitable partitioning keys that simultaneously allow for effective and efficient duplicate retrieval. By means of a user study, we demonstrate that this technique finds partitioning keys that outperform expert suggestions and additionally does not need manual configuration. Furthermore, this approach can be applied independently of the attribute types. To measure the success of a duplicate detection process and to execute the described partitioning approach, a gold standard is required that provides information about the actual duplicates in a training dataset. This thesis presents a technique that uses existing duplicate detection results and crowdsourcing to create a near gold standard that can be used for the purposes above. Another part of the thesis describes and evaluates strategies how to reduce these crowdsourcing costs and to achieve a consensus with less effort.},
  language  = {en}
}
@phdthesis{Bamberg2014,
  author    = {Bamberg, Marlene},
  title     = {Planetary mapping tools applied to floor-fractured craters on Mars},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72104},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Planetary research is often user-based and requires considerable skill, time, and effort. Unfortunately, self-defined boundary conditions, definitions, and rules are often not documented or not easy to comprehend due to the complexity of research. This makes a comparison to other studies, or an extension of the already existing research, complicated. Comparisons are often distorted, because results rely on different, not well defined, or even unknown boundary conditions. The purpose of this research is to develop a standardized analysis method for planetary surfaces, which is adaptable to several research topics. The method provides a consistent quality of results. This also includes achieving reliable and comparable results and reducing the time and effort of conducting such studies. A standardized analysis method is provided by automated analysis tools that focus on statistical parameters. Specific key parameters and boundary conditions are defined for the tool application. The analysis relies on a database in which all key parameters are stored. These databases can be easily updated and adapted to various research questions. This increases the flexibility, reproducibility, and comparability of the research. However, the quality of the database and reliability of definitions directly influence the results. To ensure a high quality of results, the rules and definitions need to be well defined and based on previously conducted case studies. The tools then produce parameters, which are obtained by defined geostatistical techniques (measurements, calculations, classifications). The idea of an automated statistical analysis is tested to proof benefits but also potential problems of this method. In this study, I adapt automated tools for floor-fractured craters (FFCs) on Mars. These impact craters show a variety of surface features, occurring in different Martian environments, and having different fracturing origins. They provide a complex morphological and geological field of application. 433 FFCs are classified by the analysis tools due to their fracturing process. Spatial data, environmental context, and crater interior data are analyzed to distinguish between the processes involved in floor fracturing. Related geologic processes, such as glacial and fluvial activity, are too similar to be separately classified by the automated tools. Glacial and fluvial fracturing processes are merged together for the classification. The automated tools provide probability values for each origin model. To guarantee the quality and reliability of the results, classification tools need to achieve an origin probability above 50 \%. This analysis method shows that 15 \% of the FFCs are fractured by intrusive volcanism, 20 \% by tectonic activity, and 43 \% by water \& ice related processes. In total, 75 \% of the FFCs are classified to an origin type. This can be explained by a combination of origin models, superposition or erosion of key parameters, or an unknown fracturing model. Those features have to be manually analyzed in detail. Another possibility would be the improvement of key parameters and rules for the classification. This research shows that it is possible to conduct an automated statistical analysis of morphologic and geologic features based on analysis tools. Analysis tools provide additional information to the user and are therefore considered assistance systems.},
  language  = {en}
}