@article{BaringhausGaigallThiele2018, author = {Baringhaus, Ludwig and Gaigall, Daniel and Thiele, Jan Philipp}, title = {Statistical inference for L²-distances to uniformity}, series = {Computational Statistics}, volume = {2018}, journal = {Computational Statistics}, number = {33}, publisher = {Springer}, address = {Berlin}, issn = {1613-9658}, doi = {10.1007/s00180-018-0820-0}, pages = {1863 -- 1896}, year = {2018}, abstract = {The paper deals with the asymptotic behaviour of estimators, statistical tests and confidence intervals for L²-distances to uniformity based on the empirical distribution function, the integrated empirical distribution function and the integrated empirical survival function. Approximations of power functions, confidence intervals for the L²-distances and statistical neighbourhood-of-uniformity validation tests are obtained as main applications. The finite sample behaviour of the procedures is illustrated by a simulation study.}, language = {en} } @inproceedings{MaurerMiskiwAcostaetal.2023, author = {Maurer, Florian and Miskiw, Kim K. and Acosta, Rebeca Ramirez and Harder, Nick and Sander, Volker and Lehnhoff, Sebastian}, title = {Market abstraction of energy markets and policies - application in an agent-based modeling toolbox}, series = {EI.A 2023: Energy Informatics}, booktitle = {EI.A 2023: Energy Informatics}, editor = {Jorgensen, Bo Norregaard and Pereira da Silva, Luiz Carlos and Ma, Zheng}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-48651-7 (Print)}, doi = {10.1007/978-3-031-48652-4_10}, pages = {139 -- 157}, year = {2023}, abstract = {In light of emerging challenges in energy systems, markets are prone to changing dynamics and market design. Simulation models are commonly used to understand the changing dynamics of future electricity markets. However, existing market models were often created with specific use cases in mind, which limits their flexibility and usability. This can impose challenges for using a single model to compare different market designs. This paper introduces a new method of defining market designs for energy market simulations. The proposed concept makes it easy to incorporate different market designs into electricity market models by using relevant parameters derived from analyzing existing simulation tools, morphological categorization and ontologies. These parameters are then used to derive a market abstraction and integrate it into an agent-based simulation framework, allowing for a unified analysis of diverse market designs. Furthermore, we showcase the usability of integrating new types of long-term contracts and over-the-counter trading. To validate this approach, two case studies are demonstrated: a pay-as-clear market and a pay-as-bid long-term market. These examples demonstrate the capabilities of the proposed framework.}, language = {en} } @inproceedings{BuesgenKloeserKohletal.2023, author = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {From cracked accounts to fake IDs: user profiling on German telegram black market channels}, series = {Data Management Technologies and Applications}, booktitle = {Data Management Technologies and Applications}, editor = {Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37889-8 (Print)}, doi = {10.1007/978-3-031-37890-4_9}, pages = {176 -- 202}, year = {2023}, abstract = {Messenger apps like WhatsApp and Telegram are frequently used for everyday communication, but they can also be utilized as a platform for illegal activity. Telegram allows public groups with up to 200.000 participants. Criminals use these public groups for trading illegal commodities and services, which becomes a concern for law enforcement agencies, who manually monitor suspicious activity in these chat rooms. This research demonstrates how natural language processing (NLP) can assist in analyzing these chat rooms, providing an explorative overview of the domain and facilitating purposeful analyses of user behavior. We provide a publicly available corpus of annotated text messages with entities and relations from four self-proclaimed black market chat rooms. Our pipeline approach aggregates the extracted product attributes from user messages to profiles and uses these with their sold products as features for clustering. The extracted structured information is the foundation for further data exploration, such as identifying the top vendors or fine-granular price analyses. Our evaluation shows that pretrained word vectors perform better for unsupervised clustering than state-of-the-art transformer models, while the latter is still superior for sequence labeling.}, language = {en} } @inproceedings{KohlFreyerKraemeretal.2023, author = {Kohl, Philipp and Freyer, Nils and Kr{\"a}mer, Yoka and Werth, Henri and Wolf, Steffen and Kraft, Bodo and Meinecke, Matthias and Z{\"u}ndorf, Albert}, title = {ALE: a simulation-based active learning evaluation framework for the parameter-driven comparison of query strategies for NLP}, series = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science}, booktitle = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {978-3-031-39059-3}, pages = {235 -- 253}, year = {2023}, abstract = {Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data points to annotators they annotate next instead of a subsequent or random sample. This method is supposed to save annotation effort while maintaining model performance. However, practitioners face many AL strategies for different tasks and need an empirical basis to choose between them. Surveys categorize AL strategies into taxonomies without performance indications. Presentations of novel AL strategies compare the performance to a small subset of strategies. Our contribution addresses the empirical basis by introducing a reproducible active learning evaluation (ALE) framework for the comparative evaluation of AL strategies in NLP. The framework allows the implementation of AL strategies with low effort and a fair data-driven comparison through defining and tracking experiment parameters (e.g., initial dataset size, number of data points per query step, and the budget). ALE helps practitioners to make more informed decisions, and researchers can focus on developing new, effective AL strategies and deriving best practices for specific use cases. With best practices, practitioners can lower their annotation costs. We present a case study to illustrate how to use the framework.}, language = {en} } @inproceedings{KloeserBuesgenKohletal.2023, author = {Kl{\"o}ser, Lars and B{\"u}sgen, Andr{\´e} and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Explaining relation classification models with semantic extents}, series = {DeLTA 2023: Deep Learning Theory and Applications}, booktitle = {DeLTA 2023: Deep Learning Theory and Applications}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {10.1007/978-3-031-39059-3_13}, pages = {189 -- 208}, year = {2023}, abstract = {In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly accurate on scientific benchmarks. A lack of explainability is currently a complicating factor in many real-world applications. Comprehensible systems are necessary to prevent biased, counterintuitive, or harmful decisions. We introduce semantic extents, a concept to analyze decision patterns for the relation classification task. Semantic extents are the most influential parts of texts concerning classification decisions. Our definition allows similar procedures to determine semantic extents for humans and models. We provide an annotation tool and a software framework to determine semantic extents for humans and models conveniently and reproducibly. Comparing both reveals that models tend to learn shortcut patterns from data. These patterns are hard to detect with current interpretability methods, such as input reductions. Our approach can help detect and eliminate spurious decision patterns during model development. Semantic extents can increase the reliability and security of natural language processing systems. Semantic extents are an essential step in enabling applications in critical areas like healthcare or finance. Moreover, our work opens new research directions for developing methods to explain deep learning models.}, language = {en} } @incollection{BaierBraunerBrillowskietal.2023, author = {Baier, Ralph and Brauner, Philipp and Brillowski, Florian and Dammers, Hannah and Liehner, Luca and P{\"u}tz, Sebastian and Schneider, Sebastian and Schollemann, Alexander and Steuer-Dankert, Linda and Vervier, Luisa and Gries, Thomas and Leicht-Scholten, Carmen and Mertens, Alexander and Nagel, Saskia K. and Schuh, G{\"u}nther and Ziefle, Martina and Nitsch, Verena}, title = {Human-centered work design for the internet of production}, series = {Internet of production - fundamentals, applications and proceedings}, booktitle = {Internet of production - fundamentals, applications and proceedings}, editor = {Brecher, Christian and Schuh, G{\"u}nther and van der Alst, Wil and Jarke, Matthias and Piller, Frank T. and Padberg, Melanie}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-98062-7}, doi = {10.1007/978-3-030-98062-7_19-1}, pages = {1 -- 23}, year = {2023}, abstract = {Like all preceding transformations of the manufacturing industry, the large-scale usage of production data will reshape the role of humans within the sociotechnical production ecosystem. To ensure that this transformation creates work systems in which employees are empowered, productive, healthy, and motivated, the transformation must be guided by principles of and research on human-centered work design. Specifically, measures must be taken at all levels of work design, ranging from (1) the work tasks to (2) the working conditions to (3) the organizational level and (4) the supra-organizational level. We present selected research across all four levels that showcase the opportunities and requirements that surface when striving for human-centered work design for the Internet of Production (IoP). (1) On the work task level, we illustrate the user-centered design of human-robot collaboration (HRC) and process planning in the composite industry as well as user-centered design factors for cognitive assistance systems. (2) On the working conditions level, we present a newly developed framework for the classification of HRC workplaces. (3) Moving to the organizational level, we show how corporate data can be used to facilitate best practice sharing in production networks, and we discuss the implications of the IoP for new leadership models. Finally, (4) on the supra-organizational level, we examine overarching ethical dimensions, investigating, e.g., how the new work contexts affect our understanding of responsibility and normative values such as autonomy and privacy. Overall, these interdisciplinary research perspectives highlight the importance and necessary scope of considering the human factor in the IoP.}, language = {en} } @article{ElsenKraissKrumbiegeletal.1999, author = {Elsen, Ingo and Kraiss, Karl-Friedrich and Krumbiegel, Dirk and Walter, Peter and Wickel, Jochen}, title = {Visual information retrieval for 3D product identification: a midterm report}, series = {KI - K{\"u}nstliche Intelligenz}, volume = {13}, journal = {KI - K{\"u}nstliche Intelligenz}, number = {1}, publisher = {Springer}, address = {Berlin}, issn = {1610-1987}, pages = {64 -- 67}, year = {1999}, language = {en} } @incollection{EggertZaehlWolfetal.2023, author = {Eggert, Mathias and Z{\"a}hl, Philipp M. and Wolf, Martin R. and Haase, Martin}, title = {Applying leaderboards for quality improvement in software development projects}, series = {Software Engineering for Games in Serious Contexts}, booktitle = {Software Engineering for Games in Serious Contexts}, editor = {Cooper, Kendra M.L. and Bucchiarone, Antonio}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-33337-8 (Print)}, doi = {10.1007/978-3-031-33338-5_11}, pages = {243 -- 263}, year = {2023}, abstract = {Software development projects often fail because of insufficient code quality. It is now well documented that the task of testing software, for example, is perceived as uninteresting and rather boring, leading to poor software quality and major challenges to software development companies. One promising approach to increase the motivation for considering software quality is the use of gamification. Initial research works already investigated the effects of gamification on software developers and come to promising. Nevertheless, a lack of results from field experiments exists, which motivates the chapter at hand. By conducting a gamification experiment with five student software projects and by interviewing the project members, the chapter provides insights into the changing programming behavior of information systems students when confronted with a leaderboard. The results reveal a motivational effect as well as a reduction of code smells.}, language = {en} } @inproceedings{ZaehlTheisWolfetal.2023, author = {Z{\"a}hl, Philipp M. and Theis, Sabine and Wolf, Martin and K{\"o}hler, Klemens}, title = {Teamwork in software development and what personality has to do with it - an overview}, series = {Virtual, Augmented and Mixed Reality}, booktitle = {Virtual, Augmented and Mixed Reality}, editor = {Chen, Jessie Y. C. and Fragomeni, Gino}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-35633-9 (Print)}, doi = {10.1007/978-3-031-35634-6_10}, pages = {130 -- 153}, year = {2023}, abstract = {Due to the increasing complexity of software projects, software development is becoming more and more dependent on teams. The quality of this teamwork can vary depending on the team composition, as teams are always a combination of different skills and personality types. This paper aims to answer the question of how to describe a software development team and what influence the personality of the team members has on the team dynamics. For this purpose, a systematic literature review (n=48) and a literature search with the AI research assistant Elicit (n=20) were conducted. Result: A person's personality significantly shapes his or her thinking and actions, which in turn influences his or her behavior in software development teams. It has been shown that team performance and satisfaction can be strongly influenced by personality. The quality of communication and the likelihood of conflict can also be attributed to personality.}, language = {en} } @inproceedings{ViehmannLimpertHofmannetal.2023, author = {Viehmann, Tarik and Limpert, Nicolas and Hofmann, Till and Henning, Mike and Ferrein, Alexander and Lakemeyer, Gerhard}, title = {Winning the RoboCup logistics league with visual servoing and centralized goal reasoning}, series = {RoboCup 2022}, booktitle = {RoboCup 2022}, editor = {Eguchi, Amy and Lau, Nuno and Paetzel-Pr{\"u}smann, Maike and Wanichanon, Thanapat}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-28468-7 (Print)}, doi = {https://doi.org/10.1007/978-3-031-28469-4_25}, pages = {300 -- 312}, year = {2023}, abstract = {The RoboCup Logistics League (RCLL) is a robotics competition in a production logistics scenario in the context of a Smart Factory. In the competition, a team of three robots needs to assemble products to fulfill various orders that are requested online during the game. This year, the Carologistics team was able to win the competition with a new approach to multi-agent coordination as well as significant changes to the robot's perception unit and a pragmatic network setup using the cellular network instead of WiFi. In this paper, we describe the major components of our approach with a focus on the changes compared to the last physical competition in 2019.}, language = {en} }