Conference Proceeding
Refine
Year of publication
Institute
- Fachbereich Elektrotechnik und Informationstechnik (302)
- Fachbereich Energietechnik (259)
- Fachbereich Medizintechnik und Technomathematik (243)
- Fachbereich Maschinenbau und Mechatronik (209)
- Fachbereich Luft- und Raumfahrttechnik (208)
- Solar-Institut Jülich (167)
- IfB - Institut für Bioengineering (152)
- Fachbereich Bauingenieurwesen (139)
- Fachbereich Wirtschaftswissenschaften (73)
- ECSM European Center for Sustainable Mobility (62)
Language
- English (1170)
- German (477)
- Italian (1)
- Multiple languages (1)
- Spanish (1)
Document Type
- Conference Proceeding (1650) (remove)
Keywords
- Biosensor (25)
- Blitzschutz (15)
- CAD (11)
- Finite-Elemente-Methode (11)
- civil engineering (11)
- Bauingenieurwesen (10)
- Lightning protection (9)
- Einspielen <Werkstoff> (6)
- Telekommunikationsmarkt (6)
- shakedown analysis (6)
Nowadays, the most employed devices for recoding videos or capturing images are undoubtedly the smartphones. Our work investigates the application of source camera identification on mobile phones. We present a dataset entirely collected by mobile phones. The dataset contains both still images and videos collected by 67 different smartphones. Part of the images consists in photos of uniform backgrounds, especially collected for the computation of the RSPN. Identifying the source camera given a video is particularly challenging due to the strong video compression. The experiments reported in this paper, show the large variation in performance when testing an highly accurate technique on still images and videos.
Modern implementations of driver assistance systems are evolving from a pure driver assistance to a independently acting automation system. Still these systems are not covering the full vehicle usage range, also called operational design domain, which require the human driver as fall-back mechanism. Transition of control and potential minimum risk manoeuvres are currently research topics and will bridge the gap until full autonomous vehicles are available. The authors showed in a demonstration that the transition of control mechanisms can be further improved by usage of communication technology. Receiving the incident type and position information by usage of standardised vehicle to everything (V2X) messages can improve the driver safety and comfort level. The connected and automated vehicle’s software framework can take this information to plan areas where the driver should take back control by initiating a transition of control which can be followed by a minimum risk manoeuvre in case of an unresponsive driver. This transition of control has been implemented in a test vehicle and was presented to the public during the IEEE IV2022 (IEEE Intelligent Vehicle Symposium) in Aachen, Germany.
Industrie 4.0 stellt viele Herausforderungen an produzierende Unternehmen und ihre Beschäf-tigten. Innovative und effektive Trainingsstrategien sind erforderlich, um mit den sich schnell verändernden Produktionsumgebungen und neuen Fertigungstechnologien Schritt halten zu können. Virtual Reality (VR) bietet neue Möglichkeiten für On-the-Job, On-Demand- und Off-Premise-Schulungen. Diese Arbeit stellt ein neues VR Schulungssystem vor, welches sich flexible an unterschiedliche Trainingsobjekte auf Grundlage von Rezepten und CAD Modellen anpassen lässt. Das Konzept basiert auf gerichteten azyklischen Graphen und einem Level-system. Es ermöglicht eine benutzerindividuelle Lerngeschwindigkeit mittels visueller Ele-mente. Das Konzept wurde für einen mechanischen Anwendungsfall mit Industriekomponen-ten implementiert und in der Industrie 4.0-Modellfabrik der FH Aachen umgesetzt.
Digital twins are seen as one of the key technologies of Industry 4.0. Although many research groups focus on digital twins and create meaningful outputs, the technology has not yet reached a broad application in the industry. The main reasons for this imbalance are the complexity of the topic, the lack of specialists, and the unawareness of the twin opportunities. The project "Digital Twin Academy" aims to overcome these barriers by focusing on three actions: Building a digital twin community for discussion and exchange, offering multi-stage training for various knowledge levels, and implementing realworld use cases for deeper insights and guidance. In this work, we focus on creating a flexible learning platform that allows the user to select a training path adjusted to personal knowledge and needs. Therefore, a mix of basic and advanced modules is created and expanded by individual feedback options. The usage of personas supports the selection of the appropriate modules.
The development of protype applications with sensors and actuators in the automation industry requires tools that are independent of manufacturer, and are flexible enough to be modified or extended for any specific requirements. Currently, developing prototypes with industrial sensors and actuators is not straightforward. First of all, the exchange of information depends on the industrial protocol that these devices have. Second, a specific configuration and installation is done based on the hardware that is used, such as automation controllers or industrial gateways. This means that the development for a specific industrial protocol, highly depends on the hardware and the software that vendors provide. In this work we propose a rapid-prototyping framework based on Arduino to solve this problem. For this project we have focused to work with the IO-Link protocol. The framework consists of an Arduino shield that acts as the physical layer, and a software that implements the IO-Link Master protocol. The main advantage of such framework is that an application with industrial devices can be rapid-prototyped with ease as its vendor independent, open-source and can be ported easily to other Arduino compatible boards. In comparison, a typical approach requires proprietary hardware, is not easy to port to another system and is closed-source.
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.