@article{AyzelHeistermann2021, author = {Ayzel, Georgy and Heistermann, Maik}, title = {The effect of calibration data length on the performance of a conceptual hydrological model versus LSTM and GRU}, series = {Computers \& geosciences : an international journal devoted to the publication of papers on all aspects of geocomputation and to the distribution of computer programs and test data sets ; an official journal of the International Association for Mathematical Geology}, volume = {149}, journal = {Computers \& geosciences : an international journal devoted to the publication of papers on all aspects of geocomputation and to the distribution of computer programs and test data sets ; an official journal of the International Association for Mathematical Geology}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0098-3004}, doi = {10.1016/j.cageo.2021.104708}, pages = {12}, year = {2021}, abstract = {We systematically explore the effect of calibration data length on the performance of a conceptual hydrological model, GR4H, in comparison to two Artificial Neural Network (ANN) architectures: Long Short-Term Memory Networks (LSTM) and Gated Recurrent Units (GRU), which have just recently been introduced to the field of hydrology. We implemented a case study for six river basins across the contiguous United States, with 25 years of meteorological and discharge data. Nine years were reserved for independent validation; two years were used as a warm-up period, one year for each of the calibration and validation periods, respectively; from the remaining 14 years, we sampled increasing amounts of data for model calibration, and found pronounced differences in model performance. While GR4H required less data to converge, LSTM and GRU caught up at a remarkable rate, considering their number of parameters. Also, LSTM and GRU exhibited the higher calibration instability in comparison to GR4H. These findings confirm the potential of modern deep-learning architectures in rainfall runoff modelling, but also highlight the noticeable differences between them in regard to the effect of calibration data length.}, language = {en} } @article{KossmannHalfpapJankriftetal.2020, author = {Kossmann, Jan and Halfpap, Stefan and Jankrift, Marcel and Schlosser, Rainer}, title = {Magic mirror in my hand, which is the best in the land?}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {11}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3407790.3407832}, pages = {2382 -- 2395}, year = {2020}, abstract = {Indexes are essential for the efficient processing of database workloads. Proposed solutions for the relevant and challenging index selection problem range from metadata-based simple heuristics, over sophisticated multi-step algorithms, to approaches that yield optimal results. The main challenges are (i) to accurately determine the effect of an index on the workload cost while considering the interaction of indexes and (ii) a large number of possible combinations resulting from workloads containing many queries and massive schemata with possibly thousands of attributes.
In this work, we describe and analyze eight index selection algorithms that are based on different concepts and compare them along different dimensions, such as solution quality, runtime, multi-column support, solution granularity, and complexity. In particular, we analyze the solutions of the algorithms for the challenging analytical Join Order, TPC-H, and TPC-DS benchmarks. Afterward, we assess strengths and weaknesses, infer insights for index selection in general and each approach individually, before we give recommendations on when to use which approach.}, language = {en} } @article{KayaFreitag2022, author = {Kaya, Adem and Freitag, Melina A.}, title = {Conditioning analysis for discrete Helmholtz problems}, series = {Computers and mathematics with applications : an international journal}, volume = {118}, journal = {Computers and mathematics with applications : an international journal}, publisher = {Elsevier Science}, address = {Amsterdam}, issn = {0898-1221}, doi = {10.1016/j.camwa.2022.05.016}, pages = {171 -- 182}, year = {2022}, abstract = {In this paper, we examine conditioning of the discretization of the Helmholtz problem. Although the discrete Helmholtz problem has been studied from different perspectives, to the best of our knowledge, there is no conditioning analysis for it. We aim to fill this gap in the literature. We propose a novel method in 1D to observe the near-zero eigenvalues of a symmetric indefinite matrix. Standard classification of ill-conditioning based on the matrix condition number is not true for the discrete Helmholtz problem. We relate the ill-conditioning of the discretization of the Helmholtz problem with the condition number of the matrix. We carry out analytical conditioning analysis in 1D and extend our observations to 2D with numerical observations. We examine several discretizations. We find different regions in which the condition number of the problem shows different characteristics. We also explain the general behavior of the solutions in these regions.}, language = {en} } @article{MattisBeckmannReinetal.2022, author = {Mattis, Toni and Beckmann, Tom and Rein, Patrick and Hirschfeld, Robert}, title = {First-class concepts}, series = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science}, volume = {21}, journal = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science}, number = {2}, publisher = {ETH Z{\"u}rich, Department of Computer Science}, address = {Z{\"u}rich}, issn = {1660-1769}, doi = {10.5381/jot.2022.21.2.a6}, pages = {1 -- 15}, year = {2022}, abstract = {Ideally, programs are partitioned into independently maintainable and understandable modules. As a system grows, its architecture gradually loses the capability to accommodate new concepts in a modular way. While refactoring is expensive and not always possible, and the programming language might lack dedicated primary language constructs to express certain cross-cutting concerns, programmers are still able to explain and delineate convoluted concepts through secondary means: code comments, use of whitespace and arrangement of code, documentation, or communicating tacit knowledge.
Secondary constructs are easy to change and provide high flexibility in communicating cross-cutting concerns and other concepts among programmers. However, such secondary constructs usually have no reified representation that can be explored and manipulated as first-class entities through the programming environment.
In this exploratory work, we discuss novel ways to express a wide range of concepts, including cross-cutting concerns, patterns, and lifecycle artifacts independently of the dominant decomposition imposed by an existing architecture. We propose the representation of concepts as first-class objects inside the programming environment that retain the capability to change as easily as code comments. We explore new tools that allow programmers to view, navigate, and change programs based on conceptual perspectives. In a small case study, we demonstrate how such views can be created and how the programming experience changes from draining programmers' attention by stretching it across multiple modules toward focusing it on cohesively presented concepts. Our designs are geared toward facilitating multiple secondary perspectives on a system to co-exist in symbiosis with the original architecture, hence making it easier to explore, understand, and explain complex contexts and narratives that are hard or impossible to express using primary modularity constructs.}, language = {en} } @article{KoumarelasJiangNaumann2020, author = {Koumarelas, Ioannis and Jiang, Lan and Naumann, Felix}, title = {Data preparation for duplicate detection}, series = {Journal of data and information quality : (JDIQ)}, volume = {12}, journal = {Journal of data and information quality : (JDIQ)}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3377878}, pages = {24}, year = {2020}, abstract = {Data errors represent a major issue in most application workflows. Before any important task can take place, a certain data quality has to be guaranteed by eliminating a number of different errors that may appear in data. Typically, most of these errors are fixed with data preparation methods, such as whitespace removal. However, the particular error of duplicate records, where multiple records refer to the same entity, is usually eliminated independently with specialized techniques. Our work is the first to bring these two areas together by applying data preparation operations under a systematic approach prior to performing duplicate detection.
Our process workflow can be summarized as follows: It begins with the user providing as input a sample of the gold standard, the actual dataset, and optionally some constraints to domain-specific data preparations, such as address normalization. The preparation selection operates in two consecutive phases. First, to vastly reduce the search space of ineffective data preparations, decisions are made based on the improvement or worsening of pair similarities. Second, using the remaining data preparations an iterative leave-one-out classification process removes preparations one by one and determines the redundant preparations based on the achieved area under the precision-recall curve (AUC-PR). Using this workflow, we manage to improve the results of duplicate detection up to 19\% in AUC-PR.}, language = {en} } @article{KossmannSchlosser2020, author = {Kossmann, Jan and Schlosser, Rainer}, title = {Self-driving database systems}, series = {Distributed and parallel databases}, volume = {38}, journal = {Distributed and parallel databases}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {0926-8782}, doi = {10.1007/s10619-020-07288-w}, pages = {795 -- 817}, year = {2020}, abstract = {Challenges for self-driving database systems, which tune their physical design and configuration autonomously, are manifold: Such systems have to anticipate future workloads, find robust configurations efficiently, and incorporate knowledge gained by previous actions into later decisions. We present a component-based framework for self-driving database systems that enables database integration and development of self-managing functionality with low overhead by relying on separation of concerns. By keeping the components of the framework reusable and exchangeable, experiments are simplified, which promotes further research in that area. Moreover, to optimize multiple mutually dependent features, e.g., index selection and compression configurations, we propose a linear programming (LP) based algorithm to derive an efficient tuning order automatically. Afterwards, we demonstrate the applicability and scalability of our approach with reproducible examples.}, language = {en} } @article{SchneiderWenigPapenbrock2021, author = {Schneider, Johannes and Wenig, Phillip and Papenbrock, Thorsten}, title = {Distributed detection of sequential anomalies in univariate time series}, series = {The VLDB journal : the international journal on very large data bases}, volume = {30}, journal = {The VLDB journal : the international journal on very large data bases}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1066-8888}, doi = {10.1007/s00778-021-00657-6}, pages = {579 -- 602}, year = {2021}, abstract = {The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to find all sequential anomalies possibly fast on potentially very large time series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.}, language = {en} } @article{Kleemann2021, author = {Kleemann, Steven}, title = {Cyber warfare and the "humanization" of international humanitarian law}, series = {International journal of cyber warfare and terrorism}, volume = {11}, journal = {International journal of cyber warfare and terrorism}, number = {2}, publisher = {IGI Global}, address = {Hershey}, isbn = {978-1-7998-6177-5}, issn = {1947-3435}, doi = {10.4018/IJCWT.2021040101}, pages = {1 -- 11}, year = {2021}, abstract = {Cyber warfare is a timely and relevant issue and one of the most controversial in international humanitarian law (IHL). The aim of IHL is to set rules and limits in terms of means and methods of warfare. In this context, a key question arises: Has digital warfare rules or limits, and if so, how are these applicable? Traditional principles, developed over a long period, are facing a new dimension of challenges due to the rise of cyber warfare. This paper argues that to overcome this new issue, it is critical that new humanity-oriented approaches is developed with regard to cyber warfare. The challenge is to establish a legal regime for cyber-attacks, successfully addressing human rights norms and standards. While clarifying this from a legal perspective, the authors can redesign the sensitive equilibrium between humanity and military necessity, weighing the humanitarian aims of IHL and the protection of civilians-in combination with international human rights law and other relevant legal regimes-in a different manner than before.}, language = {en} } @book{MeyerSmirnovWeske2011, author = {Meyer, Andreas and Smirnov, Sergey and Weske, Mathias}, title = {Data in business processes}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-144-8}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53046}, publisher = {Universit{\"a}t Potsdam}, pages = {40}, year = {2011}, abstract = {Process and data are equally important for business process management. Process data is especially relevant in the context of automated business processes, process controlling, and representation of organizations' core assets. One can discover many process modeling languages, each having a specific set of data modeling capabilities and the level of data awareness. The level of data awareness and data modeling capabilities vary significantly from one language to another. This paper evaluates several process modeling languages with respect to the role of data. To find a common ground for comparison, we develop a framework, which systematically organizes process- and data-related aspects of the modeling languages elaborating on the data aspects. Once the framework is in place, we compare twelve process modeling languages against it. We generalize the results of the comparison and identify clusters of similar languages with respect to data awareness.}, language = {de} } @phdthesis{Kluth2011, author = {Kluth, Stephan}, title = {Quantitative modeling and analysis with FMC-QE}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-52987}, school = {Universit{\"a}t Potsdam}, year = {2011}, abstract = {The modeling and evaluation calculus FMC-QE, the Fundamental Modeling Concepts for Quanti-tative Evaluation [1], extends the Fundamental Modeling Concepts (FMC) for performance modeling and prediction. In this new methodology, the hierarchical service requests are in the main focus, because they are the origin of every service provisioning process. Similar to physics, these service requests are a tuple of value and unit, which enables hierarchical service request transformations at the hierarchical borders and therefore the hierarchical modeling. Through reducing the model complexity of the models by decomposing the system in different hierarchical views, the distinction between operational and control states and the calculation of the performance values on the assumption of the steady state, FMC-QE has a scalable applica-bility on complex systems. According to FMC, the system is modeled in a 3-dimensional hierarchical representation space, where system performance parameters are described in three arbitrarily fine-grained hierarchi-cal bipartite diagrams. The hierarchical service request structures are modeled in Entity Relationship Diagrams. The static server structures, divided into logical and real servers, are de-scribed as Block Diagrams. The dynamic behavior and the control structures are specified as Petri Nets, more precisely Colored Time Augmented Petri Nets. From the structures and pa-rameters of the performance model, a hierarchical set of equations is derived. The calculation of the performance values is done on the assumption of stationary processes and is based on fundamental laws of the performance analysis: Little's Law and the Forced Traffic Flow Law. Little's Law is used within the different hierarchical levels (horizontal) and the Forced Traffic Flow Law is the key to the dependencies among the hierarchical levels (vertical). This calculation is suitable for complex models and allows a fast (re-)calculation of different performance scenarios in order to support development and configuration decisions. Within the Research Group Zorn at the Hasso Plattner Institute, the work is embedded in a broader research in the development of FMC-QE. While this work is concentrated on the theoretical background, description and definition of the methodology as well as the extension and validation of the applicability, other topics are in the development of an FMC-QE modeling and evaluation tool and the usage of FMC-QE in the design of an adaptive transport layer in order to fulfill Quality of Service and Service Level Agreements in volatile service based environments. This thesis contains a state-of-the-art, the description of FMC-QE as well as extensions of FMC-QE in representative general models and case studies. In the state-of-the-art part of the thesis in chapter 2, an overview on existing Queueing Theory and Time Augmented Petri Net models and other quantitative modeling and evaluation languages and methodologies is given. Also other hierarchical quantitative modeling frameworks will be considered. The description of FMC-QE in chapter 3 consists of a summary of the foundations of FMC-QE, basic definitions, the graphical notations, the FMC-QE Calculus and the modeling of open queueing networks as an introductory example. The extensions of FMC-QE in chapter 4 consist of the integration of the summation method in order to support the handling of closed networks and the modeling of multiclass and semaphore scenarios. Furthermore, FMC-QE is compared to other performance modeling and evaluation approaches. In the case study part in chapter 5, proof-of-concept examples, like the modeling of a service based search portal, a service based SAP NetWeaver application and the Axis2 Web service framework will be provided. Finally, conclusions are given by a summary of contributions and an outlook on future work in chapter 6. [1] Werner Zorn. FMC-QE - A New Approach in Quantitative Modeling. In Hamid R. Arabnia, editor, Procee-dings of the International Conference on Modeling, Simulation and Visualization Methods (MSV 2007) within WorldComp '07, pages 280 - 287, Las Vegas, NV, USA, June 2007. CSREA Press. ISBN 1-60132-029-9.}, language = {en} }