Publication Server of Hochschule Darmstadt
Not a member yet
259 research outputs found
Sort by
Prüfmethodenentwicklung zur mechanischen Charakterisierung von Einzelgrasfasern
No full textIm Rahmen dieser Masterarbeit wird eine Prüfmethode zur mechanischen Charakterisierung von Grasfasern entwickelt. Ziel ist es, eine reproduzierbare und robuste Vorgehensweise zu er-arbeiten, mit der mechanische Eigenschaften wie Härte und Biegesteifigkeit erfasst werden können. Als Prüfgerät kommt ein Universal Surface Tester (UST) mit integrierter Nanoinden-tierung zum Einsatz. Neben der klassischen Härtemessung soll mit diesem Gerät auch ein Zwei-Punkt-Biegeversuch realisiert werden.
Im ersten Teil der Arbeit werden die optimalen Prüfparameter systematisch ermittelt. Für die Härtemessung können verschiedene Einflussfaktoren identifiziert und deren Auswirkungen auf die Messergebnisse quantifiziert werden. Im Versuchsteil zum Biegeverhalten stellt sich her-aus, dass ein Zwei-Punkt-Biegeversuch mit dem verwendeten Aufbau und Prüfgerät nicht zu-verlässig umsetzbar ist. Die komplexe Morphologie der Fasern – insbesondere Knotenpunkte, Krümmungen sowie der anisotrope und inhomogene Aufbau – führt zu unvorhersehbaren Bie-geverläufen. Daher kann für diesen Teil kein valider Prüfansatz etabliert werden.
Im zweiten Teil der Arbeit wird die entwickelte Prüfmethode zum Härteversuch angewendet. Es zeigt sich unter anderem, dass sowohl der Faserzustand (unbehandelt, getrocknet, wachsbe-schichtet) als auch die Messseite der Faser (glänzend/matt) Auswirkungen auf die Eindringtiefe haben.
Insgesamt zeigt die Arbeit, dass Grasfasern aufgrund ihres komplexen inneren Aufbaus und ihrer strukturellen Variabilität eine besondere Herausforderung für die mechanische Charak-terisierung darstellen. Dennoch konnte für die Härtemessung eine geeignete Prüfmethode ent-wickelt und der Einfluss zentraler Einflussgrößen systematisch analysiert werden
Process Anomaly Detection in Cyber–Physical Production Systems Based on Conditional Discrete-Time Dynamic Graphs
No full textVarious types of anomalies can arise in cyber–physical production systems, caused by either faulty devices or incorrect processes. Anomalies within individual devices can often be detected by applying machine learning techniques to the respective produced multivariate time series. While this data typically shows temporal and spatial changes and can therefore be efficiently utilized by models, detecting anomalies within the process is often more challenging, as process data usually only consists of events, binary signals, or changes in unique process states. Due to the low variance of data, existing anomaly detection methods struggle to detect anomalies effectively and accurately. To address this challenge, in this paper, we propose a novel concept for process anomaly detection based on conditional discrete-time dynamic graphs. Through the conditional connections of the graph, essential characteristics can be generated and utilized to effectively train machine learning models to detect anomalies in the process data. Identified anomalies can be related to the current graph, facilitating transparent and explainable detections. By evaluating the concept against process data from an industrial unit and achieving an F1-Score of 0.96 and 1 for the realized repetitive processes, the accuracy and effectiveness of the concept can be demonstrated
Lumos: Software for Multi-level Multi-reader Comparison of Cardiovascular Magnetic Resonance Late Gadolinium Enhancement Scar Quantification
No full textCardiovascular magnetic resonance imaging (CMR) offers state-of-the-art myocardial tissue differentiation. The CMR technique late gadolinium enhancement (LGE) currently provides the noninvasive gold standard for the detection of myocardial fibrosis. Typically, thresholding methods are used for fibrotic scar tissue quantification. A major challenge for standardized CMR assessment is large variations in the estimated scar for different methods. The aim was to improve quality assurance for LGE scar quantification, a multi-reader comparison tool “Lumos” was developed to support quality control for scar quantification methods. The thresholding methods and an exact rasterization approach were implemented, as well as a graphical user interface (GUI) with statistical and case-specific tabs. Twenty LGE cases were considered with half of them including artifacts and clinical results for eight scar quantification methods computed. Lumos was successfully implemented as a multi-level multi-reader comparison software, and differences between methods can be seen in the statistical results. Histograms visualize confounding effects of different methods. Connecting the statistical level with the case level allows for backtracking statistical differences to sources of differences in the threshold calculation. Being able to visualize the underlying groundwork for the different methods in the myocardial histogram gives the opportunity to identify causes for different thresholds. Lumos showed the differences in the clinical results between cases with artifacts and cases without artifacts. A video demonstration of Lumos is offered as supplementary material 1 . Lumos allows for a multi-reader comparison for LGE scar quantification that offers insights into the origin of reader differences
Wealth Taxation and Sustainable Development: Could Wealth Related Taxes Play a Role in Achieving the SDGs?
No full textThis paper examines the relationship between wealth taxation and Sustainable Development Goals (SDGs) in OECD member countries and analyzes the impacts of wealth (related) taxes on social, environmental, and economic goals for the period of 2000–2021. The results from panel data estimations utilizing fixed effects and Driscoll‐Kraay standard errors indicate that wealth taxes positively contribute to social goals (such as reducing inequalities) but negatively affect economic goals. In the data, we observe that wealth taxes are as successful as corporate income taxes in generating the necessary finance for governments. This underscores that wealth taxes hold significant revenue potential in tackling real‐world problems such as climate change. However, our empirical results do not show any meaningful impact of wealth taxes on environmental objectives. With their current forms, wealth taxes lead to opposing effects on SDGs in OECD countries. Developing effective implementation strategies for wealth taxes is, therefore, essential for promoting future economic activities toward environmental sustainability and well‐being
Neugier und Resilienz als Zukunftskompetenzen von Organisationen
Full text linklernOS ist eine Methode zur Selbstorganisation für Menschen, die im 21. Jahrhundert leben und arbeiten. Um heute erfolgreich zu sein, muss man ständig lernen, sich organisieren und weiterentwickeln. Niemand sonst ist für diesen Prozess verantwortlich (selbstgesteuertes, lebenslanges Lernen)
Trace-It
No full text“Trace-It” is a collaborative board game that aims at building capacity of traceability of chemicals in textile value chains. It has been developed in the project “Enable Digital Product Passports with Chemicals Traceability for a Circular Economy - ECHT”
New trends in applied machine intelligence
No full textThis article presents new trends and applications in generative artificial intelligence (AI) and knowledge-based AI. Foundations and applications of large language models (LLMs) are presented, such as classifying hate speech, easy-to-read language, and retrieval-augmented generation (RAG). The important aspect of user experience (UX) for AI systems is elaborated. Finally, AI solutions in different industry sectors are presented, in particular life sciences, the energy sector, and the manufacturing industry
Novel Azaborine-Based Inhibitors of Histone Deacetylases (HDACs)
No full textAromatic ring systems appear ubiquitously in active pharmaceutical substances, such as FDA-approved histone deacetylase inhibitors. However, these rings reduce the water solubility of the molecules, which is a disadvantage during application. To address this problem, azaborine rings may be substituted for conventional aromatic ring systems. These are obtained by replacing two adjacent carbon atoms with boron and nitrogen. Incorporating B–N analogs in place of aromatic rings not only enhances structural diversity but also provides a strategy to navigate around patent-protected scaffolds. We synthesized azaborines, which are isosteric to naphthalene and indole, and utilized them as capping units for HDAC inhibitors. These molecules were attached to various aliphatic and aromatic linkers with different zinc-binding units, used in established active compounds. Nearly half of the twenty-four molecules tested exhibited inhibitory activity against at least one of the enzymes HDAC1, HDAC4, or HDAC8, with three compounds displaying IC50 values in the nanomolar range. We have therefore demonstrated that azaborine building blocks can be successfully incorporated into HDACis, resulting in a highly active profile. Consequently, it should be feasible to develop active substances containing azaborine rings against other targets
Meta Automated Machine Learning: Effectivness, Efficiency and Usability
No full textMachine Learning (ML) is an exponentially growing technological sector fueled by digitalization and an ever-increasing demand for more ML-powered applications. This increasing demand results in a growing need for Artificial Intelligence (AI) experts, who remain in limited supply. However, the big economies worldwide already face a shortage of qualified personnel. Therefore, it is uncertain whether the current supply of AI experts can adequately meet the increasing demand for AI applications. Furthermore, this bottleneck may also affect innovations, as the private sector (startups, corporations) and the public research sector may start to compete for the finite pool of AI experts. Automated Machine Learning (AutoML) is a research domain that may provide a solution to this problem. The use of AutoML solutions, which automates the laborious data science workflow, enables AI experts to increase their efficiency. Furthermore, business domain experts may use AutoML solutions to access ML without requiring AI experts. However, in many cases, employing AutoML solutions requires AutoML, ML, and programming expertise — skills that business domain experts may not necessarily possess. Finally, selecting the best AutoML solution for a use case is not trivial. It requires manual investigation of its properties in technical documentation, source code and experimentation to identify its effectiveness for a use case. This thesis introduces Meta AutoML, a concept that addresses the limitations of individual AutoML solutions and enables both AI experts and business domain experts to generate effective ML models efficiently. Meta AutoML accomplishes this through the automation of the data science workflow using existing AutoML solutions. It introduces a meta-layer which administers the execution of the AutoML solutions and only displays the relevant information to the user. Therefore, the user is no longer required to possess technical expertise in ML, AutoML, and programming. Meta AutoML autonomously performs all the necessary data science workflows using the underlying AutoML solutions to find the most effective ML model. Furthermore, a unified AutoML interface is defined, that would standardize the functionalities and parametrization AutoML solutions offer. In addition, this thesis provides User Experience (UX) recommendations to ensure a good usability in AI systems. Systems which implement the Meta AutoML concept should implement these recommendations to ensure a good usability for both expert groups.
In a benchmark using 40 classification datasets, the Proof-of-Concept (PoC) Meta AutoML system Ontology-based Meta AutoML (OMA-ML) was evaluated, finding that it can generate top results in 29 out of the 40. However, the Meta AutoML process is highly inefficient, as in many cases, the user is only interested in one ML model, the best performing one. In an effort to increase the efficiency of the Meta AutoML process, two AI-based optimization approaches were evaluated. The first is the rule-based training strategy approach, which uses training strategies to optimize the individual data science workflow steps. Through the usage of the top-3 optimization strategy, the Meta AutoML training process can improve its training efficiency by up to 70% without reducing the best ML model prediction performance. The second approach is ML-based optimization, which aims to utilize ML models to predict the optimal training configuration parameter values for a dataset and ML task. Two ML-based approaches were evaluated; the first aimed to predict the best AutoML solutions for a training, and the second the optimal training runtime. However, neither ML-based approach could be used to predict an optimal training configuration. Finally, the usability aspect of OMA-ML was evaluated through a custom 4-stage usability evaluation methodology. Using this usability methodology, OMA-ML was evaluated by User Experience (UX) experts in an expert review, as well as AI and business domain experts through a usability study. Results show that while OMA-ML did not reach the target usability state yet, with each evaluation iteration, its usability improves. The results from the individual contributions show that the novel Meta AutoML can optimize its effectiveness, efficiency, and usability