@inproceedings{FreyerThewesMeinecke2023, author = {Freyer, Nils and Thewes, Dustin and Meinecke, Matthias}, title = {GUIDO: a hybrid approach to guideline discovery \& ordering from natural language texts}, series = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1}, booktitle = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1}, editor = {Gusikhin, Oleg and Hammoudi, Slimane and Cuzzocrea, Alfredo}, isbn = {978-989-758-664-4}, issn = {2184-285X}, doi = {10.5220/0012084400003541}, pages = {335 -- 342}, year = {2023}, abstract = {Extracting workflow nets from textual descriptions can be used to simplify guidelines or formalize textual descriptions of formal processes like business processes and algorithms. The task of manually extracting processes, however, requires domain expertise and effort. While automatic process model extraction is desirable, annotating texts with formalized process models is expensive. Therefore, there are only a few machine-learning-based extraction approaches. Rule-based approaches, in turn, require domain specificity to work well and can rarely distinguish relevant and irrelevant information in textual descriptions. In this paper, we present GUIDO, a hybrid approach to the process model extraction task that first, classifies sentences regarding their relevance to the process model, using a BERT-based sentence classifier, and second, extracts a process model from the sentences classified as relevant, using dependency parsing. The presented approach achieves significantly better resul ts than a pure rule-based approach. GUIDO achieves an average behavioral similarity score of 0.93. Still, in comparison to purely machine-learning-based approaches, the annotation costs stay low.}, language = {en} } @inproceedings{SchulteSchwagerNoureldinetal.2023, author = {Schulte, Jonas and Schwager, Christian and Noureldin, Kareem and May, Martin and Teixeira Boura, Cristiano Jos{\´e} and Herrmann, Ulf}, title = {Gradient controlled startup procedure of a molten-salt power-to-heat energy storage plant based on dynamic process simulation}, series = {SolarPACES: Solar Power \& Chemical Energy Systems}, booktitle = {SolarPACES: Solar Power \& Chemical Energy Systems}, number = {2815 / 1}, publisher = {AIP conference proceedings / American Institute of Physics}, address = {Melville, NY}, isbn = {978-0-7354-4623-6}, issn = {1551-7616 (online)}, doi = {10.1063/5.0148741}, pages = {9 Seiten}, year = {2023}, abstract = {The integration of high temperature thermal energy storages into existing conventional power plants can help to reduce the CO2 emissions of those plants and lead to lower capital expenditures for building energy storage systems, due to the use of synergy effects [1]. One possibility to implement that, is a molten salt storage system with a powerful power-to-heat unit. This paper presents two possible control concepts for the startup of the charging system of such a facility. The procedures are implemented in a detailed dynamic process model. The performance and safety regarding the film temperatures at heat transmitting surfaces are investigated in the process simulations. To improve the accuracy in predicting the film temperatures, CFD simulations of the electrical heater are carried out and the results are merged with the dynamic model. The results show that both investigated control concepts are safe regarding the temperature limits. The gradient controlled startup performed better than the temperature-controlled startup. Nevertheless, there are several uncertainties that need to be investigated further.}, 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{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 = {Deep Learning Theory and Applications}, booktitle = {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} } @inproceedings{LahrsKrisamHerrmann2023, author = {Lahrs, Lennart and Krisam, Pierre and Herrmann, Ulf}, title = {Envisioning a collaborative energy system planning platform for the energy transition at the district level}, series = {ECOS 2023. The 36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems}, booktitle = {ECOS 2023. The 36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems}, publisher = {Procedings of ECOS 2023}, doi = {10.52202/069564-0284}, pages = {3163 -- 3170}, year = {2023}, abstract = {Residential and commercial buildings account for more than one-third of global energy-related greenhouse gas emissions. Integrated multi-energy systems at the district level are a promising way to reduce greenhouse gas emissions by exploiting economies of scale and synergies between energy sources. Planning district energy systems comes with many challenges in an ever-changing environment. Computational modelling established itself as the state-of-the-art method for district energy system planning. Unfortunately, it is still cumbersome to combine standalone models to generate insights that surpass their original purpose. Ideally, planning processes could be solved by using modular tools that easily incorporate the variety of competing and complementing computational models. Our contribution is a vision for a collaborative development and application platform for multi-energy system planning tools at the district level. We present challenges of district energy system planning identified in the literature and evaluate whether this platform can help to overcome these challenges. Further, we propose a toolkit that represents the core technical elements of the platform. Lastly, we discuss community management and its relevance for the success of projects with collaboration and knowledge sharing at their core.}, language = {en} } @inproceedings{AlhaskirTschescheLinkeetal.2023, author = {Alhaskir, Mohamed and Tschesche, Matteo and Linke, Florian and Schriewer, Elisabeth and Weber, Yvonne and Wolking, Stefan and R{\"o}hrig, Rainer and Koch, Henner and Kutafina, Ekaterina}, title = {ECG matching: an approach to synchronize ECG datasets for data quality comparisons}, series = {Proceedings of the 68th Annual Meeting of the German Association of Medical Informatics, Biometry, and Epidemiology e.V. (gmds) 2023}, volume = {307}, booktitle = {Proceedings of the 68th Annual Meeting of the German Association of Medical Informatics, Biometry, and Epidemiology e.V. (gmds) 2023}, editor = {R{\"o}hrig, Rainer and Grabe, Niels and Haag, Martin and H{\"u}bner, Ursula and Sax, Ulrich and Schmidt, Carsten Oliver and Sedlmayr, Martin and Zapf, Antonia}, publisher = {IOS Press}, isbn = {978-1-64368-428-4 (Print)}, doi = {10.3233/SHTI230718}, pages = {225 -- 232}, year = {2023}, abstract = {Clinical assessment of newly developed sensors is important for ensuring their validity. Comparing recordings of emerging electrocardiography (ECG) systems to a reference ECG system requires accurate synchronization of data from both devices. Current methods can be inefficient and prone to errors. To address this issue, three algorithms are presented to synchronize two ECG time series from different recording systems: Binned R-peak Correlation, R-R Interval Correlation, and Average R-peak Distance. These algorithms reduce ECG data to their cyclic features, mitigating inefficiencies and minimizing discrepancies between different recording systems. We evaluate the performance of these algorithms using high-quality data and then assess their robustness after manipulating the R-peaks. Our results show that R-R Interval Correlation was the most efficient, whereas the Average R-peak Distance and Binned R-peak Correlation were more robust against noisy data.}, language = {en} } @inproceedings{NethSchubaBrodkorbetal.2023, author = {Neth, Jannik and Schuba, Marko and Brodkorb, Karsten and Neugebauer, Georg and H{\"o}ner, Tim and Hack, Sacha}, title = {Digital forensics triage app for android}, series = {ARES '23: Proceedings of the 18th International Conference on Availability, Reliability and Security}, booktitle = {ARES '23: Proceedings of the 18th International Conference on Availability, Reliability and Security}, publisher = {ACM}, isbn = {9798400707728}, doi = {10.1145/3600160.3605017}, pages = {6 Seiten}, year = {2023}, abstract = {Digital forensics of smartphones is of utmost importance in many criminal cases. As modern smartphones store chats, photos, videos etc. that can be relevant for investigations and as they can have storage capacities of hundreds of gigabytes, they are a primary target for forensic investigators. However, it is exactly this large amount of data that is causing problems: extracting and examining the data from multiple phones seized in the context of a case is taking more and more time. This bears the risk of wasting a lot of time with irrelevant phones while there is not enough time left to analyze a phone which is worth examination. Forensic triage can help in this case: Such a triage is a preselection step based on a subset of data and is performed before fully extracting all the data from the smartphone. Triage can accelerate subsequent investigations and is especially useful in cases where time is essential. The aim of this paper is to determine which and how much data from an Android smartphone can be made directly accessible to the forensic investigator - without tedious investigations. For this purpose, an app has been developed that can be used with extremely limited storage of data in the handset and which outputs the extracted data immediately to the forensic workstation in a human- and machine-readable format.}, language = {en} } @inproceedings{GrundAltherr2023, author = {Grund, Raphael M. and Altherr, Lena}, title = {Development of an open source energy disaggregation tool for the home automation platform Home Assistant}, series = {Tagungsband AALE 2023 : mit Automatisierung gegen den Klimawandel}, booktitle = {Tagungsband AALE 2023 : mit Automatisierung gegen den Klimawandel}, editor = {Reiff-Stephan, J{\"o}rg and J{\"a}kel, Jens and Schwarz, Andr{\´e}}, publisher = {le-tex publishing services GmbH}, address = {Leipzig}, isbn = {978-3-910103-01-6}, doi = {10.33968/2023.02}, pages = {11 -- 20}, year = {2023}, abstract = {In order to reduce energy consumption of homes, it is important to make transparent which devices consume how much energy. However, power consumption is often only monitored aggregated at the house energy meter. Disaggregating this power consumption into the contributions of individual devices can be achieved using Machine Learning. Our work aims at making state of the art disaggregation algorithms accessibe for users of the open source home automation platform Home Assistant.}, language = {en} } @inproceedings{TischbeinKeanVertgewalletal.2023, author = {Tischbein, Franziska and Kean, Kilian and Vertgewall, Chris Martin and Ulbig, Andreas and Altherr, Lena}, title = {Determination of the topology of low-voltage distribution grids using cluster methods}, series = {27th International Conference on Electricity Distribution (CIRED 2023)}, booktitle = {27th International Conference on Electricity Distribution (CIRED 2023)}, publisher = {IEEE}, isbn = {978-1-83953-855-1}, doi = {10.1049/icp.2023.0478}, pages = {1 -- 5}, year = {2023}, abstract = {Due to the decarbonization of the energy sector, the electric distribution grids are undergoing a major transformation, which is expected to increase the load on the operating resources due to new electrical loads and distributed energy resources. Therefore, grid operators need to gradually move to active grid management in order to ensure safe and reliable grid operation. However, this requires knowledge of key grid variables, such as node voltages, which is why the mass integration of measurement technology (smart meters) is necessary. Another problem is the fact that a large part of the topology of the distribution grids is not sufficiently digitized and models are partly faulty, which means that active grid operation management today has to be carried out largely blindly. It is therefore part of current research to develop methods for determining unknown grid topologies based on measurement data. In this paper, different clustering algorithms are presented and their performance of topology detection of low voltage grids is compared. Furthermore, the influence of measurement uncertainties is investigated in the form of a sensitivity analysis.}, language = {en} } @inproceedings{StarkBartelDitscheetal.2023, author = {Stark, Ralf and Bartel, Sebastian and Ditsche, Florian and Esch, Thomas}, title = {Design study of a 30kN LOX/LCH4 aerospike rocket engine for lunar lander application}, series = {Aerospace Europe Conference 2023 - 10th EUCASS - 9th CEAS}, booktitle = {Aerospace Europe Conference 2023 - 10th EUCASS - 9th CEAS}, pages = {9 Seiten}, year = {2023}, abstract = {Based on lunar lander concept EL3, various LOX/CH4 aerospike engines were studied. A distinction was made between single and cluster configurations as well as ideal and non-ideal contour concepts. It could be shown that non-ideal aerospike engines promise a significant payload gain.}, language = {en} }