Settings

Now showing1 - 4 of 4
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Finding the perfect MRI sequence for your patient : towards an optimisation workflow for MRI-sequences
    (IEEE, 2024-08-08)
    Plump, Christina
    ;
    Hoinkiss, Daniel C.
    ;
    Huber, Jörn
    ;
    Berger, Bernhard Johannes
    ;
    Günther, Matthias
    Magnetic Resonance Imaging (MRI) is an essential tool for medical diagnosis. At the same time, its usage requires profound expert knowledge to determine the ideal MR sequence and protocol to be run. Until now, the contrast and quality of the resulting image have relied mainly on the radiologist's expertise. When confronted with clinical requirements and patient information, the radiologist chooses suitable sequence protocols for the examination. We propose a workflow that supports medical personnel in finding the optimal sequence for a given diagnostic task. To that end, we combine evolutionary algorithms for the optimisation, machine learning techniques for training a surrogate optimisation function from simulated MRI data, and domain-specific languages to allow non-programmers to formulate their requirements and constraints semi-formally. In this paper, we focus on the efficient usage of real-world application-motivated adaptions of the used evolutionary algorithm and evaluate their effects on four real-life sequence examples. We show that it is essential to use an adaption for the surrogate model to obtain realistic solutions and use correlation information about the search space to stay in feasible areas of the search space and thus improve optimisation quality. These findings are a first step in automating the entire MRI-sequence optimisation flow, which is necessary to allow a more widespread usage of this essential medical diagnostic technique.
    Publicationtype: Conference Paper
      19
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Machine learning for SAST: a lightweight and adaptable approach
    (Springer, 2024-01-11)
    Hüther, Lorenz
    ;
    Sohr, Karsten
    ;
    Berger, Bernhard Johannes
    ;
    Rothe, Hendrik
    ;
    Edelkamp, Stefan
    In this paper, we summarize a novel method for machine learning-based static application security testing (SAST), which was devised as part of a larger study funded by Germany’s Federal Office for Information Security (BSI). SAST describes the practice of applying static analysis techniques to program code on the premise of detecting security-critical software defects early during the development process. In the past, this was done by using rule-based approaches, where the program code is checked against a set of rules that define some pattern, representative of a defect. Recently, an increasing influx of publications can be observed that discuss the application of machine learning methods to this problem. Our method poses a lightweight approach to this concept, comprising two main contributions: Firstly, we present a novel control-flow based embedding method for program code. Embedding the code into a metric space is a necessity in order to apply machine learning techniques to the problem of SAST. Secondly, we describe how this method can be applied to generate expressive, yet simple, models of some unwanted behavior. We have implemented these methods in a prototype for the C and C++ programming languages. Using tenfold cross-validation, we show that our prototype is capable of effectively predicting the location and type of software defects in previously unseen code.
    Publicationtype: Conference Paper
      21
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    GLRP: Guided by Layer-wise Relevance Propagation - Selecting Crucial Neurons in Artificial Neural Networks
    (2023-06)
    Bahnsen, Fin Hendrik
    ;
    Bernhard Johannes Berger
    ;
    Fey, Görschwin
    Artificial neural networks (ANN) are used in critical application domains like autonomous driving or medicine. As a result of an attack or due to faults in the hardware, an ANN might make wrong predictions which might lead to a dangerous malfunction.Using layer-wise relevance propagation, we identify crucial neurons in trained ANNs. Hardening techniques, independent of our approach, can then be used to protect crucial neurons. Mathematically as well as with empirical experiments, we show that hardening the crucial neurons reduces or even eliminates the number of wrong predictions made by the ANN.
    Publicationtype: Conference Paper
      23
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    EVOAL : a domain-specific language-based approach to optimisation
    (IEEE, 2023)
    Berger, Bernhard Johannes
    ;
    Plump, Christina
    ;
    Drechsler, Rolf
    Adapting optimisation algorithms, such as evolutionary algorithms, to a problem is a necessity. The required collection and exchange of domain information is an important but tedious task in real-world projects involving several experts from different areas of expertise (e.g. the domain and the optimisation area). This paper presents a structured approach that allows the experts to systematically provide their knowledge using domain-specific languages. The presented approach defines a different language for the involved experts that enables them to add their knowledge and use the information provided by other experts. The languages are extensible, allowing the addition of new optimisation aspects without changing the actual language. These languages are the front-end to a versatile open-source optimisation tool, that we built, enabling the actual execution of the optimisation. It additionally provides features for surrogate models as well as data generation and different benchmarks for evaluation. Conducting a user study, we show that the language is suitable to express the domain knowledge and domain experts can use the language to describe their domain knowledge after a short introduction. This way, the approach reduces the effort for domain experts in providing their information. As a side effect, the complete configuration of the optimisation execution through these languages allows an easy and reliable reproduction.
    Publicationtype: Conference Paper
      37