Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters
Reset filters

Settings
Now showing 1 - 10 of 154
  • Publication
    Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems
    ( 2023)
    Rueden, Laura von
    ;
    Mayer, Sebastian
    ;
    Beckh, Katharina
    ;
    Georgiev, Bogdan
    ;
    Giesselbach, Sven
    ;
    Heese, Raoul
    ;
    Kirsch, Birgit
    ;
    Walczak, Michal
    ;
    Pfrommer, Julius
    ;
    Pick, Annika
    ;
    Ramamurthy, Rajkumar
    ;
    Garcke, Jochen
    ;
    Bauckhage, Christian
    ;
    Schuecker, Jannis
    Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
  • Publication
    Intelligent Assistants: Conceptual Dimensions, Contextual Model, and Design Trends
    ( 2022)
    Dhiman, Hitesh
    ;
    Wächter, Christoph
    ;
    Fellmann, Michael
    ;
    Röcker, Carsten
    Intelligent assistants are an increasingly commonplace class of information systems spanning a broad range of form and complexity. But what characterizes an intelligent assistant, and how do we design better assistants? In the paper, the authors contribute to scientific research in the domain of intelligent assistants in three steps, each building on the previous. First, they investigate the historical context of assistance as human work. By examining qualitative studies regarding the work of human assistants, the authors inductively derive concepts crucial to modeling the context of assistance. This analysis informs the second step, in which they develop a conceptual typology of intelligent assistants using 111 published articles. This typology explicates the characteristics (what or how) of intelligent assistants and their use context (who or which). In the third and final step, the authors utilize this typology to shed light on historical trends and patterns in design and evaluation of intelligent assistants, reflect on missed opportunities, and discuss avenues for further exploration.
  • Publication
    Sovereign Digital Consent through Privacy Impact Quantification and Dynamic Consent
    ( 2022)
    Appenzeller, Arno
    ;
    Hornung, Marina
    ;
    Kadow, Thomas
    ;
    Krempel, Erik
    ;
    Beyerer, Jürgen
    Digitization is becoming more and more important in the medical sector. Through electronic health records and the growing amount of digital data of patients available, big data research finds an increasing amount of use cases. The rising amount of data and the imposing privacy risks can be overwhelming for patients, so they can have the feeling of being out of control of their data. Several previous studies on digital consent have tried to solve this problem and empower the patient. However, there are no complete solution for the arising questions yet. This paper presents the concept of Sovereign Digital Consent by the combination of a consent privacy impact quantification and a technology for proactive sovereign consent. The privacy impact quantification supports the patient to comprehend the potential risk when sharing the data and considers the personal preferences regarding acceptance for a research project. The proactive dynamic consent implementation provides an implementation for fine granular digital consent, using medical data categorization terminology. This gives patients the ability to control their consent decisions dynamically and is research friendly through the automatic enforcement of the patients' consent decision. Both technologies are evaluated and implemented in a prototypical application. With the combination of those technologies, a promising step towards patient empowerment through Sovereign Digital Consent can be made.
  • Publication
    Reiteration theorem for R and L-spaces with the same parameter
    ( 2022)
    Doktorski, Leo
    ;
    Fernandez-Martinez, Pedro
    ;
    Signes, Teresa
    Let E,F,E0,E1 be rearrangement invariant spaces; let a,b,b0,b1 be slowly varying functions and 0<θ0,θ1<1. We characterize the interpolation spaces (Xâ¾Î¸0,b0,E0,a,FR,Xâ¾Î¸1,b1,E1,a,FL)η,b,E,0â¤Î·â¤1, when the parameters θ0 and θ1 are equal (under appropriate conditions on bi(t), i=0,1). This completes the study started in [11,12,22], which only considered the case θ0<θ1. As an application we recover and generalize interpolation identities for grand and small Lebesgue spaces given by [26].
  • Publication
    Confocal fluorescence microscopy with high-NA diffractive lens arrays
    ( 2022)
    Li, Zheng
    ;
    Taphanel, Miro
    ;
    Längle, Thomas
    ;
    Beyerer, Jürgen
    Traditionally, there is a trade-off between the numerical aperture and field of view for a microscope objective. Diffractive lens arrays (DLAs) with overlapping apertures are used to overcome such a problem. A spot array with an NA up to 0.83 and a pitch of 75 m is produced by the proposed DLA at a wavelength of 488 nm. By measurement of the fluorescence beads, the DLA-based confocal setup shows the capability of high-resolution measurement over an area of 3mm 3mm with a 2.5 0.07 NA objective. Further, the proposed fluorescence microscope is insensitive to optical aberrations, which has been demonstrated by imaging with a simple doublet lens.
  • Publication
    Validation of XAI Explanations for Multivariate Time Series Classification in the Maritime Domain
    ( 2022)
    Veerappa, Manjunatha
    ;
    Anneken, Mathias
    ;
    Burkart, Nadia
    ;
    Huber, Marco
    Due to the lack of explanation towards their internal mechanism, state-of-the-art deep learning-based classifiers are often considered as black-box models. For instance, in the maritime domain, models that classify the types of ships based on their trajectories and other features perform well, but give no further explanation for their predictions. To gain the trust of human operators responsible for critical decisions, the reason behind the classification is crucial. In this paper, we introduce explainable artificial intelligence (XAI) approaches to the task of classification of ship types. This supports decision-making by providing explanations in terms of the features contributing the most towards the prediction, along with their corresponding time intervals. In the case of the LIME explainer, we adapt the time-slice mapping technique (LimeforTime), while for Shapley additive explanations (SHAP) and path integrated gradient (PIG), we represent the relevance of each input variable to generate a heatmap as an explanation. In order to validate the XAI results, the existing perturbation and sequence analyses for classifiers of univariate time series data is employed for testing and evaluating the XAI explanations on multivariate time series. Furthermore, we introduce a novel evaluation technique to assess the quality of explanations yielded by the chosen XAI method.
  • Publication
    36P A point mutation replacing cysteine with arginine at position 382 (C382R) in the transmembrane domain of FGFR2 leads to response to FGF2-inhibitor pemigatinib in chemo-refractory intrahepatic cholangiocarcinoma
    ( 2022)
    Hempel, L.C.
    ;
    Lapa, C.
    ;
    Gaumann, A.
    ;
    Veloso de Oliveira, J.
    ;
    Scheiber, J.
    ;
    Philipp, Patrick
    ;
    Oyarzun Laura, Cristina
    ;
    Wesarg, Stefan
    ;
    Robert, S.
    ;
    Hempel, D.
    Background: To date, targeted tyrosine kinase inhibitors have been approved for FGFR2 and FGFR3 fusions (pemigatinib and erdafitinib, respectively), but the importance of FGFR2 mutations for transformation activity and as a druggable gene variant with response to different FGFR inhibitors is poorly understood. FGFR2 inhibitors present a mainstay of treatment for locally advanced or metastatic intrahepatic cholangiocellular carcinoma (iCCA). Methods: A 74-year-old male was diagnosed with iCCA in liver segments seven and eight with infiltration of the hepatic veins and inferior vena cava revealed a C382R mutation of the intramembrane domain of FGRR2 receptor. We performed an in-silico study to understand the potential mode-of-action of the mutant FGFR2 targets. Based on experimentally determined structures we then used a structure generated by AlphaFold2 as the variation in question is located at a position not determined well in the experiments. This revealed that the C382R mutation is located in the trans-membranal domain at a position crucial for signal transduction, both for activation and inhibition of downstream-signaling. The Molecular Tumor Board decided to start the treatment with 13.5 mg pemigatinib once daily for 14 days, followed by 7 days of free therapy interval resulting in a sustained partial response. The patient continues to be treated of 13.5 mg as described above. Results: In our case report, we were able to show that the patient in whom an C382R mutation was detected responded to the therapy with pemigatinib. This shows that real-world scenarios differ from the data of the approval studies, thereby illustrating how complex data on patients with FGFR mutations is. One of the main problems of large approval studies is that the functionality of the respective alterations is often disregarded. Conclusions: Our results suggest that respective mutation may be successfully targeted by FGFR-selective tyrosine-kinase inhibitors, demonstrating the importance of the functional characterization of mutations. Legal entity responsible for the study: Louisa Hempel. Funding: Has not received any funding. Disclosure: All authors have declared no conflicts of interest.
  • Publication
    Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events
    ( 2022)
    Kummerow, A.
    ;
    Monsalve, C.
    ;
    Bretschneider, P.
    The automated identification and localisation of grid disturbances is a major research area and key technology for the monitoring and control of future power systems. Current recognition systems rely on sufficient training data and are very error-prone to disturbance events, which are unseen during training. This study introduces a robust Siamese recurrent neural network using attention-based embedding functions to simultaneously identify and locate disturbances from synchrophasor data. Additionally, a novel double-sigmoid classifier is introduced for reliable differentiation between known and unknown disturbance types and locations. Different models are evaluated within an open-set classification problem for a generic power transmission system considering different unknown disturbance events. A detailed analysis of the results is provided and classification results are compared with a state-of-the-art open-set classifier.
  • Publication
    Mixture of Experts of Neural Networks and Kalman Filters for Optical Belt Sorting
    ( 2022)
    Thumm, Jakob
    ;
    Reith-Braun, Marcel
    ;
    Pfaff, Florian
    ;
    Hanebeck, Uwe D.
    ;
    Flitter, Merle
    ;
    Maier, Georg
    ;
    Gruna, Robin
    ;
    Längle, Thomas
    ;
    Bauer, Albert
    ;
    Kruggel-Emden, Harald
    In optical sorting of bulk material, the composition of particles may frequently change. State-of-the-art sorting approaches rely on tuning physical models of the particle motion. The aim of this work is to increase the prediction accuracy in complex, fast-changing sorting scenarios with data-driven approaches. We propose two neural network (NN) experts for accurate prediction of a priori known particle types. To handle the large variety of particle types that can occur in real-world sorting scenarios, we introduce a simple but effective mixture of experts approach that combines NNs with hand-crafted motion models. Our new method not only improves the prediction accuracy for bulk material consisting of many particle classes, but also proves to be very adaptive and robust to new particle types.
  • Publication
    Anwendungsszenarien für AR in der Produktion: Use Cases und Technologielösungen
    ( 2022)
    Deppe, Sahar
    ;
    Brünninghaus, Marc
    ;
    Voit, Michael
    ;
    Röcker, Carsten
    Mit der steigenden Leistungsfähigkeit von mobilen Computern und Anzeigegeräten hat sich die Nutzung von Augmented-Reality-Technologien in den letzten zehn Jahren verstärkt. Augmented Reality (AR) ist eine Technik, die es den Nutzern ermöglicht, mit ihrer physischen Umgebung durch die Überlagerung digitaler Informationen zu interagieren. Diese Technologie hebt bestimmte Merkmale der physischen Welt hervor, verbessert das Verständnis für diese Merkmale und bietet intelligente und zugängliche Einblicke. AR-Anwendungen haben das Potenzial, enorme Auswirkungen auf Branchen wie Produktion, Medizin, Forschung, Ausbildung und Unterhaltung zu bewirken. Der Fokus dieses Artikels liegt auf den AR-Anwendungen im Bereich der Produktion, die vor allem in den Bereichen Montage, Reparatur, Diagnose und Schulung eingesetzt werden. Außerdem werden die Effektivität und Effizienz von AR-Technologien in diesem Bereich anhand von vier dieser Anwendungen vorgestellt.