@article{PengLiuWangetal.2018, author = {Peng, Junjie and Liu, Danxu and Wang, Yingtao and Zeng, Ying and Cheng, Feng and Zhang, Wenqiang}, title = {Weight-based strategy for an I/O-intensive application at a cloud data center}, series = {Concurrency and computation : practice \& experience}, volume = {30}, journal = {Concurrency and computation : practice \& experience}, number = {19}, publisher = {Wiley}, address = {Hoboken}, issn = {1532-0626}, doi = {10.1002/cpe.4648}, pages = {14}, year = {2018}, abstract = {Applications with different characteristics in the cloud may have different resources preferences. However, traditional resource allocation and scheduling strategies rarely take into account the characteristics of applications. Considering that an I/O-intensive application is a typical type of application and that frequent I/O accesses, especially small files randomly accessing the disk, may lead to an inefficient use of resources and reduce the quality of service (QoS) of applications, a weight allocation strategy is proposed based on the available resources that a physical server can provide as well as the characteristics of the applications. Using the weight obtained, a resource allocation and scheduling strategy is presented based on the specific application characteristics in the data center. Extensive experiments show that the strategy is correct and can guarantee a high concurrency of I/O per second (IOPS) in a cloud data center with high QoS. Additionally, the strategy can efficiently improve the utilization of the disk and resources of the data center without affecting the service quality of applications.}, language = {en} } @article{SchaeferStede2021, author = {Sch{\"a}fer, Robin and Stede, Manfred}, title = {Argument mining on twitter}, series = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG}, volume = {63}, journal = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG}, number = {1}, publisher = {De Gruyter}, address = {Berlin}, issn = {1611-2776}, doi = {10.1515/itit-2020-0053}, pages = {45 -- 58}, year = {2021}, abstract = {In the last decade, the field of argument mining has grown notably. However, only relatively few studies have investigated argumentation in social media and specifically on Twitter. Here, we provide the, to our knowledge, first critical in-depth survey of the state of the art in tweet-based argument mining. We discuss approaches to modelling the structure of arguments in the context of tweet corpus annotation, and we review current progress in the task of detecting argument components and their relations in tweets. We also survey the intersection of argument mining and stance detection, before we conclude with an outlook.}, language = {en} } @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{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} } @phdthesis{Koehlmann2016, author = {K{\"o}hlmann, Wiebke}, title = {Zug{\"a}nglichkeit virtueller Klassenzimmer f{\"u}r Blinde}, publisher = {Logos}, address = {Berlin}, isbn = {978-3-8325-4273-3}, pages = {i-x, 310, i-clxxvi}, year = {2016}, abstract = {E-Learning-Anwendungen bieten Chancen f{\"u}r die gesetzlich vorgeschriebene Inklusion von Lernenden mit Beeintr{\"a}chtigungen. Die gleichberechtigte Teilhabe von blinden Lernenden an Veranstaltungen in virtuellen Klassenzimmern ist jedoch durch den synchronen, multimedialen Charakter und den hohen Informationsumfang dieser L{\"o}sungen kaum m{\"o}glich. Die vorliegende Arbeit untersucht die Zug{\"a}nglichkeit virtueller Klassenzimmer f{\"u}r blinde Nutzende, um eine m{\"o}glichst gleichberechtigte Teilhabe an synchronen, kollaborativen Lernszenarien zu erm{\"o}glichen. Im Rahmen einer Produktanalyse werden dazu virtuelle Klassenzimmer auf ihre Zug{\"a}nglichkeit und bestehende Barrieren untersucht und Richtlinien f{\"u}r die zug{\"a}ngliche Gestaltung von virtuellen Klassenzimmern definiert. Anschließend wird ein alternatives Benutzungskonzept zur Darstellung und Bedienung virtueller Klassenzimmer auf einem zweidimensionalen taktilen Braille-Display entwickelt, um eine m{\"o}glichst gleichberechtigte Teilhabe blinder Lernender an synchronen Lehrveranstaltungen zu erm{\"o}glichen. Nach einer ersten Evaluation mit blinden Probanden erfolgt die prototypische Umsetzung des Benutzungskonzepts f{\"u}r ein Open-Source-Klassenzimmer. Die abschließende Evaluation der prototypischen Umsetzung zeigt die Verbesserung der Zug{\"a}nglichkeit von virtuellen Klassenzimmern f{\"u}r blinde Lernende unter Verwendung eines taktilen Fl{\"a}chendisplays und best{\"a}tigt die Wirksamkeit der im Rahmen dieser Arbeit entwickelten Konzepte.}, language = {de} } @book{OPUS4-7534, title = {Process design for natural scientists}, series = {Communications in computer and information science ; 500}, journal = {Communications in computer and information science ; 500}, editor = {Lambrecht, Anna-Lena and Margaria, Tizian}, publisher = {Springer}, address = {Wiesbaden}, isbn = {978-3-662-45005-5}, pages = {X, 251}, year = {2014}, abstract = {This book presents an agile and model-driven approach to manage scientific workflows. The approach is based on the Extreme Model Driven Design (XMDD) paradigm and aims at simplifying and automating the complex data analysis processes carried out by scientists in their day-to-day work. Besides documenting the impact the workflow modeling might have on the work of natural scientists, this book serves three major purposes: 1. It acts as a primer for practitioners who are interested to learn how to think in terms of services and workflows when facing domain-specific scientific processes. 2. It provides interesting material for readers already familiar with this kind of tools, because it introduces systematically both the technologies used in each case study and the basic concepts behind them. 3. As the addressed thematic field becomes increasingly relevant for lectures in both computer science and experimental sciences, it also provides helpful material for teachers that plan similar courses.}, language = {en} } @phdthesis{Wust2015, author = {Wust, Johannes}, title = {Mixed workload managment for in-memory databases}, pages = {VIII, 167}, year = {2015}, language = {en} } @article{Teske2014, author = {Teske, Daniel}, title = {Geocoder accuracy ranking}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {161 -- 174}, year = {2014}, abstract = {Finding an address on a map is sometimes tricky: the chosen map application may be unfamiliar with the enclosed region. There are several geocoders on the market, they have different databases and algorithms to compute the query. Consequently, the geocoding results differ in their quality. Fortunately the geocoders provide a rich set of metadata. The workflow described in this paper compares this metadata with the aim to find out which geocoder is offering the best-fitting coordinate for a given address.}, language = {en} } @article{Sens2014, author = {Sens, Henriette}, title = {Web-Based map generalization tools put to the test: a jABC workflow}, series = {Process Design for Natural Scientists: an agile model-driven approach}, journal = {Process Design for Natural Scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {175 -- 185}, year = {2014}, abstract = {Geometric generalization is a fundamental concept in the digital mapping process. An increasing amount of spatial data is provided on the web as well as a range of tools to process it. This jABC workflow is used for the automatic testing of web-based generalization services like mapshaper.org by executing its functionality, overlaying both datasets before and after the transformation and displaying them visually in a .tif file. Mostly Web Services and command line tools are used to build an environment where ESRI shapefiles can be uploaded, processed through a chosen generalization service and finally visualized in Irfanview.}, language = {en} } @article{Noack2014, author = {Noack, Franziska}, title = {CREADED: Colored-Relief application for digital elevation data}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {186 -- 199}, year = {2014}, abstract = {In the geoinformatics field, remote sensing data is often used for analyzing the characteristics of the current investigation area. This includes DEMs, which are simple raster grids containing grey scales representing the respective elevation values. The project CREADED that is presented in this paper aims at making these monochrome raster images more significant and more intuitively interpretable. For this purpose, an executable interactive model for creating a colored and relief-shaded Digital Elevation Model (DEM) has been designed using the jABC framework. The process is based on standard jABC-SIBs and SIBs that provide specific GIS functions, which are available as Web services, command line tools and scripts.}, language = {en} } @article{Respondek2014, author = {Respondek, Tobias}, title = {A workflow for computing potential areas for wind turbines}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, pages = {200 -- 215}, year = {2014}, abstract = {This paper describes the implementation of a workflow model for service-oriented computing of potential areas for wind turbines in jABC. By implementing a re-executable model the manual effort of a multi-criteria site analysis can be reduced. The aim is to determine the shift of typical geoprocessing tools of geographic information systems (GIS) from the desktop to the web. The analysis is based on a vector data set and mainly uses web services of the "Center for Spatial Information Science and Systems" (CSISS). This paper discusses effort, benefits and problems associated with the use of the web services.}, language = {en} } @article{Scheele2014, author = {Scheele, Lasse}, title = {Location analysis for placing artificial reefs}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {216 -- 228}, year = {2014}, abstract = {Location analyses are among the most common tasks while working with spatial data and geographic information systems. Automating the most frequently used procedures is therefore an important aspect of improving their usability. In this context, this project aims to design and implement a workflow, providing some basic tools for a location analysis. For the implementation with jABC, the workflow was applied to the problem of finding a suitable location for placing an artificial reef. For this analysis three parameters (bathymetry, slope and grain size of the ground material) were taken into account, processed, and visualized with the The Generic Mapping Tools (GMT), which were integrated into the workflow as jETI-SIBs. The implemented workflow thereby showed that the approach to combine jABC with GMT resulted in an user-centric yet user-friendly tool with high-quality cartographic outputs.}, language = {en} } @article{Kind2014, author = {Kind, Josephine}, title = {Creation of topographic maps}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, pages = {229 -- 238}, year = {2014}, abstract = {Location analyses are among the most common tasks while working with spatial data and geographic information systems. Automating the most frequently used procedures is therefore an important aspect of improving their usability. In this context, this project aims to design and implement a workflow, providing some basic tools for a location analysis. For the implementation with jABC, the workflow was applied to the problem of finding a suitable location for placing an artificial reef. For this analysis three parameters (bathymetry, slope and grain size of the ground material) were taken into account, processed, and visualized with the The Generic Mapping Tools (GMT), which were integrated into the workflow as jETI-SIBs. The implemented workflow thereby showed that the approach to combine jABC with GMT resulted in an user-centric yet user-friendly tool with high-quality cartographic outputs.}, language = {en} } @article{Holler2014, author = {Holler, Robin}, title = {GraffDok - a graffiti documentation application}, series = {Process design for natural scientists: an agile model-driven approach}, journal = {Process design for natural scientists: an agile model-driven approach}, number = {500}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {239 -- 251}, year = {2014}, abstract = {GraffDok is an application helping to maintain an overview over sprayed images somewhere in a city. At the time of writing it aims at vandalism rather than at beautiful photographic graffiti in an underpass. Looking at hundreds of tags and scribbles on monuments, house walls, etc. it would be interesting to not only record them in writing but even make them accessible electronically, including images. GraffDok's workflow is simple and only requires an EXIF-GPS-tagged photograph of a graffito. It automatically determines its location by using reverse geocoding with the given GPS-coordinates and the Gisgraphy WebService. While asking the user for some more meta data, GraffDok analyses the image in parallel with this and tries to detect fore- and background - before extracting the drawing lines and make them stand alone. The command line based tool ImageMagick is used here as well as for accessing EXIF data. Any meta data is written to csv-files, which will stay easily accessible and can be integrated in TeX-files as well. The latter ones are converted to PDF at the end of the workflow, containing a table about all graffiti and a summary for each - including the generated characteristic graffiti pattern image.}, language = {en} } @article{Reso2014, author = {Reso, Judith}, title = {Protein Classification Workflow}, series = {Process Design for Natural Scientists: an agile model-driven approach}, journal = {Process Design for Natural Scientists: an agile model-driven approach}, number = {500}, editor = {Lambrecht, Anna-Lena and Margaria, Tiziana}, publisher = {Springer Verlag}, address = {Berlin}, isbn = {978-3-662-45005-5}, issn = {1865-0929}, pages = {65 -- 72}, year = {2014}, abstract = {The protein classification workflow described in this report enables users to get information about a novel protein sequence automatically. The information is derived by different bioinformatic analysis tools which calculate or predict features of a protein sequence. Also, databases are used to compare the novel sequence with known proteins.}, language = {en} }