@phdthesis{Draisbach2022,
  author    = {Draisbach, Uwe},
  title     = {Efficient duplicate detection and the impact of transitivity},
  doi       = {10.25932/publishup-57214},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-572140},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 150},
  year      = {2022},
  abstract  = {Duplicate detection describes the process of finding multiple representations of the same real-world entity in the absence of a unique identifier, and has many application areas, such as customer relationship management, genealogy and social sciences, or online shopping. Due to the increasing amount of data in recent years, the problem has become even more challenging on the one hand, but has led to a renaissance in duplicate detection research on the other hand. This thesis examines the effects and opportunities of transitive relationships on the duplicate detection process. Transitivity implies that if record pairs ⟨ri,rj⟩ and ⟨rj,rk⟩ are classified as duplicates, then also record pair ⟨ri,rk⟩ has to be a duplicate. However, this reasoning might contradict with the pairwise classification, which is usually based on the similarity of objects. An essential property of similarity, in contrast to equivalence, is that similarity is not necessarily transitive. First, we experimentally evaluate the effect of an increasing data volume on the threshold selection to classify whether a record pair is a duplicate or non-duplicate. Our experiments show that independently of the pair selection algorithm and the used similarity measure, selecting a suitable threshold becomes more difficult with an increasing number of records due to an increased probability of adding a false duplicate to an existing cluster. Thus, the best threshold changes with the dataset size, and a good threshold for a small (possibly sampled) dataset is not necessarily a good threshold for a larger (possibly complete) dataset. As data grows over time, earlier selected thresholds are no longer a suitable choice, and the problem becomes worse for datasets with larger clusters. Second, we present with the Duplicate Count Strategy (DCS) and its enhancement DCS++ two alternatives to the standard Sorted Neighborhood Method (SNM) for the selection of candidate record pairs. DCS adapts SNMs window size based on the number of detected duplicates and DCS++ uses transitive dependencies to save complex comparisons for finding duplicates in larger clusters. We prove that with a proper (domain- and data-independent!) threshold, DCS++ is more efficient than SNM without loss of effectiveness. Third, we tackle the problem of contradicting pairwise classifications. Usually, the transitive closure is used for pairwise classifications to obtain a transitively closed result set. However, the transitive closure disregards negative classifications. We present three new and several existing clustering algorithms and experimentally evaluate them on various datasets and under various algorithm configurations. The results show that the commonly used transitive closure is inferior to most other clustering algorithms, especially for the precision of results. In scenarios with larger clusters, our proposed EMCC algorithm is, together with Markov Clustering, the best performing clustering approach for duplicate detection, although its runtime is longer than Markov Clustering due to the subexponential time complexity. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.},
  language  = {en}
}
@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab134},
  pages     = {17},
  year      = {2021},
  abstract  = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.},
  language  = {en}
}
@article{KaitouaRablMarkl2020,
  author    = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker},
  title     = {A distributed data exchange engine for polystores},
  series = {Information technology : methods and applications of informatics and information technology},
  volume    = {62},
  journal   = {Information technology : methods and applications of informatics and information technology},
  number    = {3-4},
  publisher = {De Gruyter},
  address   = {Berlin},
  issn      = {1611-2776},
  doi       = {10.1515/itit-2019-0037},
  pages     = {145 -- 156},
  year      = {2020},
  abstract  = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.},
  language  = {en}
}
@misc{SukmanaTorkuraChengetal.2018,
  author    = {Sukmana, Muhammad Ihsan Haikal and Torkura, Kennedy A. and Cheng, Feng and Meinel, Christoph and Graupner, Hendrik},
  title     = {Unified logging system for monitoring multiple cloud storage providers in cloud storage broker},
  series = {32ND International Conference on Information Networking (ICOIN)},
  journal   = {32ND International Conference on Information Networking (ICOIN)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-2290-2},
  doi       = {10.1109/ICOIN.2018.8343081},
  pages     = {44 -- 49},
  year      = {2018},
  abstract  = {With the increasing demand for personal and enterprise data storage service, Cloud Storage Broker (CSB) provides cloud storage service using multiple Cloud Service Providers (CSPs) with guaranteed Quality of Service (QoS), such as data availability and security. However monitoring cloud storage usage in multiple CSPs has become a challenge for CSB due to lack of standardized logging format for cloud services that causes each CSP to implement its own format. In this paper we propose a unified logging system that can be used by CSB to monitor cloud storage usage across multiple CSPs. We gather cloud storage log files from three different CSPs and normalise these into our proposed log format that can be used for further analysis process. We show that our work enables a coherent view suitable for data navigation, monitoring, and analytics.},
  language  = {en}
}
@phdthesis{RobainaEstevez2017,
  author    = {Robaina Estevez, Semidan},
  title     = {Context-specific metabolic predictions},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-401365},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 158},
  year      = {2017},
  abstract  = {All life-sustaining processes are ultimately driven by thousands of biochemical reactions occurring in the cells: the metabolism. These reactions form an intricate network which produces all required chemical compounds, i.e., metabolites, from a set of input molecules. Cells regulate the activity through metabolic reactions in a context-specific way; only reactions that are required in a cellular context, e.g., cell type, developmental stage or environmental condition, are usually active, while the rest remain inactive. The context-specificity of metabolism can be captured by several kinds of experimental data, such as by gene and protein expression or metabolite profiles. In addition, these context-specific data can be assimilated into computational models of metabolism, which then provide context-specific metabolic predictions. This thesis is composed of three individual studies focussing on context-specific experimental data integration into computational models of metabolism. The first study presents an optimization-based method to obtain context-specific metabolic predictions, and offers the advantage of being fully automated, i.e., free of user defined parameters. The second study explores the effects of alternative optimal solutions arising during the generation of context-specific metabolic predictions. These alternative optimal solutions are metabolic model predictions that represent equally well the integrated data, but that can markedly differ. This study proposes algorithms to analyze the space of alternative solutions, as well as some ways to cope with their impact in the predictions. Finally, the third study investigates the metabolic specialization of the guard cells of the plant Arabidopsis thaliana, and compares it with that of a different cell type, the mesophyll cells. To this end, the computational methods developed in this thesis are applied to obtain metabolic predictions specific to guard cell and mesophyll cells. These cell-specific predictions are then compared to explore the differences in metabolic activity between the two cell types. In addition, the effects of alternative optima are taken into consideration when comparing the two cell types. The computational results indicate a major reorganization of the primary metabolism in guard cells. These results are supported by an independent 13C labelling experiment.},
  language  = {en}
}
@phdthesis{Bauckmann2013,
  author    = {Bauckmann, Jana},
  title     = {Dependency discovery for data integration},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66645},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Data integration aims to combine data of different sources and to provide users with a unified view on these data. This task is as challenging as valuable. In this thesis we propose algorithms for dependency discovery to provide necessary information for data integration. We focus on inclusion dependencies (INDs) in general and a special form named conditional inclusion dependencies (CINDs): (i) INDs enable the discovery of structure in a given schema. (ii) INDs and CINDs support the discovery of cross-references or links between schemas. An IND "A in B" simply states that all values of attribute A are included in the set of values of attribute B. We propose an algorithm that discovers all inclusion dependencies in a relational data source. The challenge of this task is the complexity of testing all attribute pairs and further of comparing all of each attribute pair's values. The complexity of existing approaches depends on the number of attribute pairs, while ours depends only on the number of attributes. Thus, our algorithm enables to profile entirely unknown data sources with large schemas by discovering all INDs. Further, we provide an approach to extract foreign keys from the identified INDs. We extend our IND discovery algorithm to also find three special types of INDs: (i) Composite INDs, such as "AB in CD", (ii) approximate INDs that allow a certain amount of values of A to be not included in B, and (iii) prefix and suffix INDs that represent special cross-references between schemas. Conditional inclusion dependencies are inclusion dependencies with a limited scope defined by conditions over several attributes. Only the matching part of the instance must adhere the dependency. We generalize the definition of CINDs distinguishing covering and completeness conditions and define quality measures for conditions. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. The challenge for this task is twofold: (i) Which (and how many) attributes should be used for the conditions? (ii) Which attribute values should be chosen for the conditions? Previous approaches rely on pre-selected condition attributes or can only discover conditions applying to quality thresholds of 100\%. Our approaches were motivated by two application domains: data integration in the life sciences and link discovery for linked open data. We show the efficiency and the benefits of our approaches for use cases in these domains.},
  language  = {en}
}
@article{PaascheEberle2011,
  author    = {Paasche, Hendrik and Eberle, Detlef},
  title     = {Automated compilation of pseudo-lithology maps from geophysical data sets a comparison of Gustafson-Kessel and fuzzy c-means cluster algorithms},
  series = {Exploration geophysics : the bulletin of the Australian Society of Exploration Geophysicists},
  volume    = {42},
  journal   = {Exploration geophysics : the bulletin of the Australian Society of Exploration Geophysicists},
  number    = {4},
  publisher = {CSIRO},
  address   = {Collingwood},
  issn      = {0812-3985},
  doi       = {10.1071/EG11014},
  pages     = {275 -- 285},
  year      = {2011},
  abstract  = {The fuzzy partitioning Gustafson-Kessel cluster algorithm is employed for rapid and objective integration of multi-parameter Earth-science related databases. We begin by evaluating the Gustafson-Kessel algorithm using the example of a synthetic study and compare the results to those obtained from the more widely employed fuzzy c-means algorithm. Since the Gustafson-Kessel algorithm goes beyond the potential of the fuzzy c-means algorithm by adapting the shape of the clusters to be detected and enabling a manual control of the cluster volume, we believe the results obtained from Gustafson-Kessel algorithm to be superior. Accordingly, a field database comprising airborne and ground-based geophysical data sets is analysed, which has previously been classified by means of the fuzzy c-means algorithm. This database is integrated using the Gustafson-Kessel algorithm thus minimising the amount of empirical data processing required before and after fuzzy c-means clustering. The resultant zonal geophysical map is more evenly clustered matching regional geology information available from the survey area. Even additional information about linear structures, e. g. as typically caused by the presence of dolerite dykes or faults, is visible in the zonal map obtained from Gustafson-Kessel cluster analysis.},
  language  = {en}
}
@book{BauckmannLeserNaumann2010,
  author    = {Bauckmann, Jana and Leser, Ulf and Naumann, Felix},
  title     = {Efficient and exact computation of inclusion dependencies for data integration},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-048-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41396},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {36},
  year      = {2010},
  abstract  = {Data obtained from foreign data sources often come with only superficial structural information, such as relation names and attribute names. Other types of metadata that are important for effective integration and meaningful querying of such data sets are missing. In particular, relationships among attributes, such as foreign keys, are crucial metadata for understanding the structure of an unknown database. The discovery of such relationships is difficult, because in principle for each pair of attributes in the database each pair of data values must be compared. A precondition for a foreign key is an inclusion dependency (IND) between the key and the foreign key attributes. We present with Spider an algorithm that efficiently finds all INDs in a given relational database. It leverages the sorting facilities of DBMS but performs the actual comparisons outside of the database to save computation. Spider analyzes very large databases up to an order of magnitude faster than previous approaches. We also evaluate in detail the effectiveness of several heuristics to reduce the number of necessary comparisons. Furthermore, we generalize Spider to find composite INDs covering multiple attributes, and partial INDs, which are true INDs for all but a certain number of values. This last type is particularly relevant when integrating dirty data as is often the case in the life sciences domain - our driving motivation.},
  language  = {en}
}