Conference Proceeding
Refine
Year of publication
- 2023 (37) (remove)
Institute
- Fachbereich Elektrotechnik und Informationstechnik (17)
- ECSM European Center for Sustainable Mobility (10)
- Fachbereich Luft- und Raumfahrttechnik (6)
- Fachbereich Energietechnik (5)
- Fachbereich Medizintechnik und Technomathematik (4)
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (4)
- Fachbereich Wirtschaftswissenschaften (3)
- Kommission für Forschung und Entwicklung (3)
- Solar-Institut Jülich (3)
- Nowum-Energy (2)
Has Fulltext
- no (37)
Document Type
- Conference Proceeding (37) (remove)
Keywords
- Natural language processing (3)
- Associated liquids (2)
- Future Skills (2)
- Information extraction (2)
- Interdisciplinarity (2)
- Power plants (2)
- Sustainability (2)
- Active learning (1)
- Agent-based simulation (1)
- Agile development (1)
The RoboCup Logistics League (RCLL) is a robotics competition in a production logistics scenario in the context of a Smart Factory. In the competition, a team of three robots needs to assemble products to fulfill various orders that are requested online during the game. This year, the Carologistics team was able to win the competition with a new approach to multi-agent coordination as well as significant changes to the robot’s perception unit and a pragmatic network setup using the cellular network instead of WiFi. In this paper, we describe the major components of our approach with a focus on the changes compared to the last physical competition in 2019.
Due to the increasing complexity of software projects, software development is becoming more and more dependent on teams. The quality of this teamwork can vary depending on the team composition, as teams are always a combination of different skills and personality types. This paper aims to answer the question of how to describe a software development team and what influence the personality of the team members has on the team dynamics. For this purpose, a systematic literature review (n=48) and a literature search with the AI research assistant Elicit (n=20) were conducted. Result: A person’s personality significantly shapes his or her thinking and actions, which in turn influences his or her behavior in software development teams. It has been shown that team performance and satisfaction can be strongly influenced by personality. The quality of communication and the likelihood of conflict can also be attributed to personality.
This paper presents an approach for reducing the cognitive load for humans working in quality control (QC) for production processes that adhere to the 6σ -methodology. While 100% QC requires every part to be inspected, this task can be reduced when a human-in-the-loop QC process gets supported by an anomaly detection system that only presents those parts for manual inspection that have a significant likelihood of being defective. This approach shows good results when applied to image-based QC for metal textile products.
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.
KNX is a protocol for smart building automation, e.g., for automated heating, air conditioning, or lighting. This paper analyses and evaluates state-of-the-art KNX devices from manufacturers Merten, Gira and Siemens with respect to security. On the one hand, it is investigated if publicly known vulnerabilities like insecure storage of passwords in software, unencrypted communication, or denialof-service attacks, can be reproduced in new devices. On the other hand, the security is analyzed in general, leading to the discovery of a previously unknown and high risk vulnerability related to so-called BCU (authentication) keys.
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.
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.