@inproceedings{MandekarJentschLutzetal.2021, author = {Mandekar, Swati and Jentsch, Lina and Lutz, Kai and Behbahani, Mehdi and Melnykowycz, Mark}, title = {Earable design analysis for sleep EEG measurements}, series = {UbiComp '21}, booktitle = {UbiComp '21}, doi = {10.1145/3460418.3479328}, pages = {171 -- 175}, year = {2021}, abstract = {Conventional EEG devices cannot be used in everyday life and hence, past decade research has been focused on Ear-EEG for mobile, at-home monitoring for various applications ranging from emotion detection to sleep monitoring. As the area available for electrode contact in the ear is limited, the electrode size and location play a vital role for an Ear-EEG system. In this investigation, we present a quantitative study of ear-electrodes with two electrode sizes at different locations in a wet and dry configuration. Electrode impedance scales inversely with size and ranges from 450 kΩ to 1.29 MΩ for dry and from 22 kΩ to 42 kΩ for wet contact at 10 Hz. For any size, the location in the ear canal with the lowest impedance is ELE (Left Ear Superior), presumably due to increased contact pressure caused by the outer-ear anatomy. The results can be used to optimize signal pickup and SNR for specific applications. We demonstrate this by recording sleep spindles during sleep onset with high quality (5.27 μVrms).}, language = {en} } @inproceedings{KloeserKohlKraftetal.2021, author = {Kl{\"o}ser, Lars and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Multi-attribute relation extraction (MARE): simplifying the application of relation extraction}, series = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, booktitle = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-526-5}, doi = {10.5220/0010559201480156}, pages = {148 -- 156}, year = {2021}, abstract = {Natural language understanding's relation extraction makes innovative and encouraging novel business concepts possible and facilitates new digitilized decision-making processes. Current approaches allow the extraction of relations with a fixed number of entities as attributes. Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems. We introduce multi-attribute relation extraction (MARE) as an assumption-less problem formulation with two approaches, facilitating an explicit mapping from business use cases to the data annotations. Avoiding elaborated annotation constraints simplifies the application of relation extraction approaches. The evaluation compares our models to current state-of-the-art event extraction and binary relation extraction methods. Our approaches show improvement compared to these on the extraction of general multi-attribute relations.}, language = {en} } @inproceedings{KohlSchmidtsKloeseretal.2021, author = {Kohl, Philipp and Schmidts, Oliver and Kl{\"o}ser, Lars and Werth, Henri and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {STAMP 4 NLP - an agile framework for rapid quality-driven NLP applications development}, series = {Quality of Information and Communications Technology. QUATIC 2021}, booktitle = {Quality of Information and Communications Technology. QUATIC 2021}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-85346-4}, doi = {10.1007/978-3-030-85347-1_12}, pages = {156 -- 166}, year = {2021}, abstract = {The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis. Building sophisticated NLP applications requires dealing with modern machine learning (ML) technologies, which impedes enterprises from establishing successful NLP projects. Our experience in applied NLP research projects shows that the continuous integration of research prototypes in production-like environments with quality assurance builds trust in the software and shows convenience and usefulness regarding the business goal. We introduce STAMP 4 NLP as an iterative and incremental process model for developing NLP applications. With STAMP 4 NLP, we merge software engineering principles with best practices from data science. Instantiating our process model allows efficiently creating prototypes by utilizing templates, conventions, and implementations, enabling developers and data scientists to focus on the business goals. Due to our iterative-incremental approach, businesses can deploy an enhanced version of the prototype to their software environment after every iteration, maximizing potential business value and trust early and avoiding the cost of successful yet never deployed experiments.}, language = {en} } @inproceedings{SchmidtsKraftWinkensetal.2021, author = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert}, title = {Catalog integration of heterogeneous and volatile product data}, series = {DATA 2020: Data Management Technologies and Applications}, booktitle = {DATA 2020: Data Management Technologies and Applications}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-83013-7}, doi = {10.1007/978-3-030-83014-4_7}, pages = {134 -- 153}, year = {2021}, abstract = {The integration of frequently changing, volatile product data from different manufacturers into a single catalog is a significant challenge for small and medium-sized e-commerce companies. They rely on timely integrating product data to present them aggregated in an online shop without knowing format specifications, concept understanding of manufacturers, and data quality. Furthermore, format, concepts, and data quality may change at any time. Consequently, integrating product catalogs into a single standardized catalog is often a laborious manual task. Current strategies to streamline or automate catalog integration use techniques based on machine learning, word vectorization, or semantic similarity. However, most approaches struggle with low-quality or real-world data. We propose Attribute Label Ranking (ALR) as a recommendation engine to simplify the integration process of previously unknown, proprietary tabular format into a standardized catalog for practitioners. We evaluate ALR by focusing on the impact of different neural network architectures, language features, and semantic similarity. Additionally, we consider metrics for industrial application and present the impact of ALR in production and its limitations.}, language = {en} } @inproceedings{BornheimGriegerBialonski2021, author = {Bornheim, Tobias and Grieger, Niklas and Bialonski, Stephan}, title = {FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning}, series = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, booktitle = {Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments : 17th Conference on Natural Language Processing KONVENS 2021}, publisher = {Heinrich Heine University}, address = {D{\"u}sseldorf}, doi = {10.48415/2021/fhw5-x128}, pages = {105 -- 111}, year = {2021}, language = {en} } @inproceedings{BurgethKleefeldZhangetal.2022, author = {Burgeth, Bernhard and Kleefeld, Andreas and Zhang, Eugene and Zhang, Yue}, title = {Towards Topological Analysis of Non-symmetric Tensor Fields via Complexification}, series = {Discrete Geometry and Mathematical Morphology}, booktitle = {Discrete Geometry and Mathematical Morphology}, editor = {Baudrier, {\´E}tienne and Naegel, Beno{\^i}t and Kr{\"a}henb{\"u}hl, Adrien and Tajine, Mohamed}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-19897-7}, doi = {10.1007/978-3-031-19897-7_5}, pages = {48 -- 59}, year = {2022}, abstract = {Fields of asymmetric tensors play an important role in many applications such as medical imaging (diffusion tensor magnetic resonance imaging), physics, and civil engineering (for example Cauchy-Green-deformation tensor, strain tensor with local rotations, etc.). However, such asymmetric tensors are usually symmetrized and then further processed. Using this procedure results in a loss of information. A new method for the processing of asymmetric tensor fields is proposed restricting our attention to tensors of second-order given by a 2x2 array or matrix with real entries. This is achieved by a transformation resulting in Hermitian matrices that have an eigendecomposition similar to symmetric matrices. With this new idea numerical results for real-world data arising from a deformation of an object by external forces are given. It is shown that the asymmetric part indeed contains valuable information.}, language = {en} } @inproceedings{BlaneckBornheimGriegeretal.2022, author = {Blaneck, Patrick Gustav and Bornheim, Tobias and Grieger, Niklas and Bialonski, Stephan}, title = {Automatic readability assessment of german sentences with transformer ensembles}, series = {Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text}, booktitle = {Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text}, publisher = {Association for Computational Linguistics}, address = {Potsdam}, doi = {10.48550/arXiv.2209.04299}, pages = {57 -- 62}, year = {2022}, abstract = {Reliable methods for automatic readability assessment have the potential to impact a variety of fields, ranging from machine translation to self-informed learning. Recently, large language models for the German language (such as GBERT and GPT-2-Wechsel) have become available, allowing to develop Deep Learning based approaches that promise to further improve automatic readability assessment. In this contribution, we studied the ability of ensembles of fine-tuned GBERT and GPT-2-Wechsel models to reliably predict the readability of German sentences. We combined these models with linguistic features and investigated the dependence of prediction performance on ensemble size and composition. Mixed ensembles of GBERT and GPT-2-Wechsel performed better than ensembles of the same size consisting of only GBERT or GPT-2-Wechsel models. Our models were evaluated in the GermEval 2022 Shared Task on Text Complexity Assessment on data of German sentences. On out-of-sample data, our best ensemble achieved a root mean squared error of 0:435.}, language = {en} } @inproceedings{BuesgenKloeserKohletal.2022, 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 = {Exploratory analysis of chat-based black market profiles with natural language processing}, series = {Proceedings of the 11th International Conference on Data Science, Technology and Applications}, booktitle = {Proceedings of the 11th International Conference on Data Science, Technology and Applications}, isbn = {978-989-758-583-8}, issn = {2184-285X}, doi = {10.5220/0011271400003269}, pages = {83 -- 94}, year = {2022}, abstract = {Messenger apps like WhatsApp or Telegram are an integral part of daily communication. Besides the various positive effects, those services extend the operating range of criminals. Open trading groups with many thousand participants emerged on Telegram. Law enforcement agencies monitor suspicious users in such chat rooms. This research shows that text analysis, based on natural language processing, facilitates this through a meaningful domain overview and detailed investigations. We crawled a corpus from such self-proclaimed black markets and annotated five attribute types products, money, payment methods, user names, and locations. Based on each message a user sends, we extract and group these attributes to build profiles. Then, we build features to cluster the profiles. Pretrained word vectors yield better unsupervised clustering results than current state-of-the-art transformer models. The result is a semantically meaningful high-level overview of the user landscape of black market chatrooms. Additionally, the extracted structured information serves as a foundation for further data exploration, for example, the most active users or preferred payment methods.}, language = {en} } @inproceedings{Maurer2022, author = {Maurer, Florian}, title = {Framework to provide a simulative comparison of different energy market designs}, series = {Energy Informatics}, volume = {5}, booktitle = {Energy Informatics}, number = {2, Article number: 12}, publisher = {Springer Nature}, issn = {2520-8942}, doi = {10.1186/s42162-022-00215-6}, pages = {18 -- 20}, year = {2022}, abstract = {Useful market simulations are key to the evaluation of diferent market designs existing of multiple market mechanisms or rules. Yet a simulation framework which has a comparison of diferent market mechanisms in mind was not found. The need to create an objective view on different sets of market rules while investigating meaningful agent strategies concludes that such a simulation framework is needed to advance the research on this subject. An overview of diferent existing market simulation models is given which also shows the research gap and the missing capabilities of those systems. Finally, a methodology is outlined how a novel market simulation which can answer the research questions can be developed.}, language = {en} } @inproceedings{WeldenSeverinsPoghossianetal.2022, author = {Welden, Melanie and Severins, Robin and Poghossian, Arshak and Wege, Christina and Siegert, Petra and Keusgen, Michael and Sch{\"o}ning, Michael Josef}, title = {Studying the immobilization of acetoin reductase with Tobacco mosaic virus particles on capacitive field-effect sensors}, series = {2022 IEEE International Symposium on Olfaction and Electronic Nose (ISOEN)}, booktitle = {2022 IEEE International Symposium on Olfaction and Electronic Nose (ISOEN)}, publisher = {IEEE}, isbn = {978-1-6654-5860-3 (Online)}, doi = {10.1109/ISOEN54820.2022.9789657}, pages = {4 Seiten}, year = {2022}, abstract = {A capacitive electrolyte-insulator-semiconductor (EISCAP) biosensor modified with Tobacco mosaic virus (TMV) particles for the detection of acetoin is presented. The enzyme acetoin reductase (AR) was immobilized on the surface of the EISCAP using TMV particles as nanoscaffolds. The study focused on the optimization of the TMV-assisted AR immobilization on the Ta 2 O 5 -gate EISCAP surface. The TMV-assisted acetoin EISCAPs were electrochemically characterized by means of leakage-current, capacitance-voltage, and constant-capacitance measurements. The TMV-modified transducer surface was studied via scanning electron microscopy.}, language = {en} }