TY - CHAP A1 - Klöser, Lars A1 - Kohl, Philipp A1 - Kraft, Bodo A1 - Zündorf, Albert T1 - Multi-attribute relation extraction (MARE): simplifying the application of relation extraction T2 - Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1 N2 - 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. Y1 - 2021 SN - 978-989-758-526-5 U6 - https://doi.org/10.5220/0010559201480156 N1 - 2nd International Conference on Deep Learning Theory and Applications, DeLTA2021, July 7-9, 2021 SP - 148 EP - 156 PB - SciTePress CY - Setúbal ER - TY - CHAP A1 - Kohl, Philipp A1 - Schmidts, Oliver A1 - Klöser, Lars A1 - Werth, Henri A1 - Kraft, Bodo A1 - Zündorf, Albert T1 - STAMP 4 NLP – an agile framework for rapid quality-driven NLP applications development T2 - Quality of Information and Communications Technology. QUATIC 2021 N2 - 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. KW - Machine learning KW - Process model KW - Natural language processing Y1 - 2021 SN - 978-3-030-85346-4 SN - 978-3-030-85347-1 U6 - https://doi.org/10.1007/978-3-030-85347-1_12 N1 - International Conference on the Quality of Information and Communications Technology, QUATIC 2021, 8-11 September, Algarve, Portugal SP - 156 EP - 166 PB - Springer CY - Cham ER - TY - CHAP A1 - Schmidts, Oliver A1 - Kraft, Bodo A1 - Winkens, Marvin A1 - Zündorf, Albert T1 - Catalog integration of heterogeneous and volatile product data T2 - DATA 2020: Data Management Technologies and Applications N2 - 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. Y1 - 2021 SN - 978-3-030-83013-7 U6 - https://doi.org/10.1007/978-3-030-83014-4_7 N1 - International Conference on Data Management Technologies and Applications, DATA 2020, 7-9 July SP - 134 EP - 153 PB - Springer CY - Cham ER - TY - JOUR A1 - Jildeh, Zaid B. A1 - Wagner, Patrick H. A1 - Schöning, Michael Josef T1 - Sterilization of Objects, Products, and Packaging Surfaces and Their Characterization in Different Fields of Industry: The Status in 2020 JF - physica status solidi (a) applications and materials science N2 - The treatment method to deactivate viable microorganisms from objects or products is termed sterilization. There are multiple forms of sterilization, each intended to be applied for a specific target, which depends on—but not limited to—the thermal, physical, and chemical stability of that target. Herein, an overview on the currently used sterilization processes in the global market is provided. Different sterilization techniques are grouped under a category that describes the method of treatment: radiation (gamma, electron beam, X-ray, and ultraviolet), thermal (dry and moist heat), and chemical (ethylene oxide, ozone, chlorine dioxide, and hydrogen peroxide). For each sterilization process, the typical process parameters as defined by regulations and the mode of antimicrobial activity are summarized. Finally, the recommended microorganisms that are used as biological indicators to validate sterilization processes in accordance with the rules that are established by various regulatory agencies are summarized. KW - bioburdens KW - sterility tests KW - sterilization efficacy KW - sterilization methods KW - validation methods Y1 - 2021 U6 - https://doi.org/10.1002/pssa.202000732 SN - 1862-6319 N1 - Corresponding author: Michael J. Schöning VL - 218 IS - 13 PB - Wiley-VCH CY - Weinheim ER - TY - THES A1 - Bayer, Robin T1 - Development of a novel in-vitro vascular model for determination of physiological and pathophysiological mechanobiology Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:38-362212 N1 - Dissertation, Universität zu Köln, 2021 PB - Universität zu Köln CY - Köln ER - TY - JOUR A1 - Molinnus, Denise A1 - Drinic, Aleksander A1 - Iken, Heiko A1 - Kröger, Nadja A1 - Zinser, Max A1 - Smeets, Ralf A1 - Köpf, Marius A1 - Kopp, Alexander A1 - Schöning, Michael Josef T1 - Towards a flexible electrochemical biosensor fabricated from biocompatible Bombyx mori silk JF - Biosensors and Bioelectronics Y1 - 2021 U6 - https://doi.org/10.1016/j.bios.2021.113204 SN - 0956-5663 VL - 183 IS - Art. 113204 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Yoshinobu, Tatsuo A1 - Schöning, Michael Josef T1 - Light-addressable potentiometric sensors (LAPS) for cell monitoring and biosensing JF - Current Opinion in Electrochemistry Y1 - 2021 U6 - https://doi.org/10.1016/j.coelec.2021.100727 SN - 2451-9103 IS - In Press, Journal Pre-proof PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Jablonski, Melanie A1 - Münstermann, Felix A1 - Nork, Jasmina A1 - Molinnus, Denise A1 - Muschallik, Lukas A1 - Bongaerts, Johannes A1 - Wagner, Torsten A1 - Keusgen, Michael A1 - Siegert, Petra A1 - Schöning, Michael Josef T1 - Capacitive field‐effect biosensor applied for the detection of acetoin in alcoholic beverages and fermentation broths JF - physica status solidi (a) applications and materials science N2 - An acetoin biosensor based on a capacitive electrolyte–insulator–semiconductor (EIS) structure modified with the enzyme acetoin reductase, also known as butane-2,3-diol dehydrogenase (Bacillus clausii DSM 8716ᵀ), is applied for acetoin detection in beer, red wine, and fermentation broth samples for the first time. The EIS sensor consists of an Al/p-Si/SiO₂/Ta₂O₅ layer structure with immobilized acetoin reductase on top of the Ta₂O₅ transducer layer by means of crosslinking via glutaraldehyde. The unmodified and enzyme-modified sensors are electrochemically characterized by means of leakage current, capacitance–voltage, and constant capacitance methods, respectively. KW - acetoin KW - acetoin reductase KW - alcoholic beverages KW - biosensors KW - capacitive field-effect sensors Y1 - 2021 U6 - https://doi.org/10.1002/pssa.202000765 SN - 1862-6319 N1 - Corresponding author: Melanie Jablonski VL - 218 IS - 13 PB - Wiley-VCH CY - Weinheim ER - TY - JOUR A1 - Wert, Stefan A1 - Iken, Heiko A1 - Schöning, Michael Josef A1 - Matysik, Frank-Michael T1 - Development of a temperature‐pulse enhanced electrochemical glucose biosensor and characterization of its stability via scanning electrochemical microscopy JF - Electroanalysis N2 - Glucose oxidase (GOx) is an enzyme frequently used in glucose biosensors. As increased temperatures can enhance the performance of electrochemical sensors, we investigated the impact of temperature pulses on GOx that was drop-coated on flattened Pt microwires. The wires were heated by an alternating current. The sensitivity towards glucose and the temperature stability of GOx was investigated by amperometry. An up to 22-fold increase of sensitivity was observed. Spatially resolved enzyme activity changes were investigated via scanning electrochemical microscopy. The application of short (<100 ms) heat pulses was associated with less thermal inactivation of the immobilized GOx than long-term heating. Y1 - 2021 U6 - https://doi.org/10.1002/elan.202100089 SN - 1521-4109 IS - Early View PB - Wiley-VCH CY - Weinheim ER - TY - JOUR A1 - Waldvogel, Janice A1 - Ritzmann, Ramona A1 - Freyler, Kathrin A1 - Helm, Michael A1 - Monti, Elena A1 - Albracht, Kirsten A1 - Stäudle, Benjamin A1 - Gollhofer, Albert A1 - Narici, Marco T1 - The Anticipation of Gravity in Human Ballistic Movement JF - Frontiers in Physiology N2 - Stretch-shortening type actions are characterized by lengthening of the pre-activated muscle-tendon unit (MTU) in the eccentric phase immediately followed by muscle shortening. Under 1 g, pre-activity before and muscle activity after ground contact, scale muscle stiffness, which is crucial for the recoil properties of the MTU in the subsequent push-off. This study aimed to examine the neuro-mechanical coupling of the stretch-shortening cycle in response to gravity levels ranging from 0.1 to 2 g. During parabolic flights, 17 subjects performed drop jumps while electromyography (EMG) of the lower limb muscles was combined with ultrasound images of the gastrocnemius medialis, 2D kinematics and kinetics to depict changes in energy management and performance. Neuro-mechanical coupling in 1 g was characterized by high magnitudes of pre-activity and eccentric muscle activity allowing an isometric muscle behavior during ground contact. EMG during pre-activity and the concentric phase systematically increased from 0.1 to 1 g. Below 1 g the EMG in the eccentric phase was diminished, leading to muscle lengthening and reduced MTU stretches. Kinetic energy at take-off and performance were decreased compared to 1 g. Above 1 g, reduced EMG in the eccentric phase was accompanied by large MTU and muscle stretch, increased joint flexion amplitudes, energy loss and reduced performance. The energy outcome function established by linear mixed model reveals that the central nervous system regulates the extensor muscles phase- and load-specifically. In conclusion, neuro-mechanical coupling appears to be optimized in 1 g. Below 1 g, the energy outcome is compromised by reduced muscle stiffness. Above 1 g, loading progressively induces muscle lengthening, thus facilitating energy dissipation. Y1 - 2021 U6 - https://doi.org/10.3389/fphys.2021.614060 SN - 1664-042X PB - Frontiers CY - Lausanne ER -