Refine
Year of publication
- 2023 (260) (remove)
Institute
- Fachbereich Gestaltung (95)
- Fachbereich Medizintechnik und Technomathematik (40)
- Fachbereich Elektrotechnik und Informationstechnik (29)
- ECSM European Center for Sustainable Mobility (24)
- Fachbereich Luft- und Raumfahrttechnik (24)
- Fachbereich Wirtschaftswissenschaften (21)
- Fachbereich Chemie und Biotechnologie (18)
- Fachbereich Energietechnik (14)
- Fachbereich Maschinenbau und Mechatronik (12)
- INB - Institut für Nano- und Biotechnologien (12)
Document Type
- Bachelor Thesis (93)
- Article (79)
- Conference Proceeding (37)
- Part of a Book (23)
- Book (11)
- Patent (3)
- Habilitation (2)
- Master's Thesis (2)
- Preprint (2)
- Talk (2)
Keywords
- Corporate Design (6)
- Editorial (6)
- Illustration (6)
- Typografie (6)
- Nachhaltigkeit (5)
- Produktdesign (5)
- Fotografie (4)
- Publikation (4)
- Design (3)
- Erscheinungsbild (3)
Zugriffsart
- weltweit (100)
- campus (47)
- bezahl (32)
- fachbereichsweit (FB4) (12)
Umsatzbasierte Bußgelder – wie sonst nur aus dem Kartellrecht bekannt – waren einer der Gründe, warum die Datenschutz-Grundverordnung (DSGVO) vor ihrem Inkrafttreten für erhebliches Aufsehen sorgte. Die vielfach relevanteren Schadensersatzansprüche, die, wie bei „Dieselgate“, aufgrund der Vielzahl von betroffenen Personen und der aus Sicht von Rechtsdienstleistern bestehenden Skalierbarkeit mit weitaus höheren Einbußen für Unternehmen einhergehen können, blieben zunächst unbeachtet. Inzwischen ist der Schadensersatzanspruch gem. Art. 82 DSGVO die Vorschrift, die die meisten Vorlagen zum Europäischen Gerichtshof (EuGH) der letzten Jahre hervorgerufen hat. Am 4.5.2023 hat nun der EuGH (Urteil v. 4.5.2023 - Rs. C-300/21, NWB GAAAJ-41389) in einem Grundsatzurteil über zentrale Fragen rund um den Ersatz immaterieller Schäden als Folge von Datenschutzverstößen entschieden.
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.
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.
The work in modern open-pit and underground mines requires the transportation of large amounts of resources between fixed points. The navigation to these fixed points is a repetitive task that can be automated. The challenge in automating the navigation of vehicles commonly used in mines is the systemic properties of such vehicles. Many mining vehicles, such as the one we have used in the research for this paper, use steering systems with an articulated joint bending the vehicle’s drive axis to change its course and a hydraulic drive system to actuate axial drive components or the movements of tippers if available. To address the difficulties of controlling such a vehicle, we present a model-predictive approach for controlling the vehicle. While the control optimisation based on a parallel error minimisation of the predicted state has already been established in the past, we provide insight into the design and implementation of an MPC for an articulated mining vehicle and show the results of real-world experiments in an open-pit mine environment.
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.
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.
To fulfil the CO2 emission reduction targets of the European Union (EU), heavy-duty (HD) trucks need to operate 15% more efficiently by 2025 and 30% by 2030. Their electrification is necessary as conventional HD trucks are already optimized for the long-haul application. The resulting hybrid electric vehicle (HEV) truck gains most of the fuel saving potential by the recuperation of potential energy and its consecutive utilization. The key to utilizing the full potential of HEV-HD trucks is to maximize the amount of recuperated energy and ensure its intelligent usage while keeping the operating point of the internal combustion engine as efficient as possible. To achieve this goal, an intelligent energy management strategy (EMS) based on ECMS is developed for a parallel HEV-HD truck which uses predictive discharge of the battery and adaptive operating strategy regarding the height profile and the vehicle mass. The presented EMS can reproduce the global optimal operating strategy over long phases and lead to a fuel saving potential of up to 2% compared with a heuristic strategy. Furthermore, the fuel saving potential is correlated with the investigated boundary conditions to deepen the understanding of the impact of intelligent EMS for HEV-HD trucks.
Krebstherapie bei Kindern ist für alle Beteiligten eine emotional bedrückende Angelegenheit. Besonders die Strahlentherapie stellt Kinder aufgrund der Häufigkeit der Termine, der Isolation während der Bestrahlung und der Fixierung vor Herausforderungen. „nia“ ermöglicht es den Angehörigen, während der Behandlung einen physischen Kontakt zum Kind zu halten. Zwei miteinander verbundene Zwillingsgeräte registrieren die Bewegungen der Hände und übertragen die Berührung an das jeweils andere Gerät. Diese taktile Kommunikation sorgt für innere Ruhe und Verbundenheit. Vor der eigentlichen Therapie liegen die Geräte in einem Koffer, welcher ein Modell des Behandlungsraums beinhaltet. Mithilfe dessen werden die Kinder spielerisch auf die Bestrahlung vorbereitet. So sollen sich in Zukunft weniger Kinder ängstlich und allein einer Strahlentherapie stellen müssen.
In Deutschland verfügen mehr als 95 % aller Haushalte über einen Internetzugang und das Interesse an Smart Home Anwendungen steigt. Je vernetzter das Zuhause wird, desto mehr Devices müssen dort ihren Platz finden. WLAN Router wirken durch ihre technische Designsprache meist wie Fremdkörper im Raum, sodass oft versucht wird, sie zu verstecken. Das soll sich mit „Cobo“, dem smarten WLAN Router, ändern. Neben der Bereitstellung einer Internetanbindung wird er zum Hub für alle Smart Home Anwendungen. Als Herzstück des Zuhauses sorgt er für die Vernetzung aller Devices und schafft zudem eine Verbindung zwischen Technologie und Interior. Mit seinem minimalistischen Design und der gezielten Auswahl an Materialien und Farben fügt sich der intelligente Router in die eigenen vier Wände ein. „Cobo“ ist kein WLAN Router, der im Schuhregal versteckt werden muss, denn er wird zum Teil der Einrichtung.