Hochschule Bonn-Rhein-Sieg
Publikationsserver der Hochschule Bonn-Rhein-Sieg - pub H-BRSNot a member yet
7939 research outputs found
Sort by
Steuerungswirkung von Qualitätsindikatoren: Zusammenhänge zwischen der Routine-Qualitätssicherung und dem Rehabilitationsergebnis ein Jahr nach Reha
No full text
Measurement data availability within EnerSHelF
No full textIntention: Within the research project EnerSHelF (Energy-Self-Sufficiency for Health Facilities in Ghana), i. a. energy-meteorological and load-related measurement data are collected, for which an overview of the availability is to be presented on a poster.
Context: In Ghana, the total electricity consumed has almost doubled between 2008 and 2018 according to the Energy Commission of Ghana. This goes along with an unstable power grid, resulting in power outages whenever electricity consumption peaks. The blackouts called "dumsor" in Ghana, pose a severe burden to the healthcare sector. Innovative solutions are needed to reduce greenhouse gas emissions and improve energy and health access
DExT: Detector Explanation Toolkit for Explaining Multiple Detections Using Saliency Methods
No full textAs cameras are ubiquitous in autonomous systems, object detection is a crucial task. Object detectors are widely used in applications such as autonomous driving, healthcare, and robotics. Given an image, an object detector outputs both the bounding box coordinates as well as classification probabilities for each object detected. The state-of-the-art detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications in particular. It is therefore crucial to explain the reason behind each detector decision in order to gain user trust, enhance detector performance, and analyze their failure.
Previous work fails to explain as well as evaluate both bounding box and classification decisions individually for various detectors. Moreover, no tools explain each detector decision, evaluate the explanations, and also identify the reasons for detector failures. This restricts the flexibility to analyze detectors. The main contribution presented here is an open-source Detector Explanation Toolkit (DExT). It is used to explain the detector decisions, evaluate the explanations, and analyze detector errors. The detector decisions are explained visually by highlighting the image pixels that most influence a particular decision. The toolkit implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. To the author’s knowledge, this is the first work to conduct extensive qualitative and novel quantitative evaluations of different explanation methods across various detectors. The qualitative evaluation incorporates a visual analysis of the explanations carried out by the author as well as a human-centric evaluation. The human-centric evaluation includes a user study to understand user trust in the explanations generated across various explanation methods for different detectors. Four multi-object visualization methods are provided to merge the explanations of multiple objects detected in an image as well as the corresponding detector outputs in a single image. Finally, DExT implements the procedure to analyze detector failures using the formulated approach.
The visual analysis illustrates that the ability to explain a model is more dependent on the model itself than the actual ability of the explanation method. In addition, the explanations are affected by the object explained, the decision explained, detector architecture, training data labels, and model parameters. The results of the quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. In addition, a single explanation method cannot generate more faithful explanations than other methods for both the bounding box and the classification decision across different detectors. Both the quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. Finally, a convex polygon-based multi-object visualization method provides more human-understandable visualization than other methods.
The author expects that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions
Studieren und Menstruieren – geschlechtergerechterer (Hoch-)schulalltag durch kostenlose Menstruationshygieneartikel: Studie der Gleichstellungsstelle an der Hochschule Bonn-Rhein-Sieg 2021/2022
No full textFlüssigkeit, die in Werbespots symbolisch für Menstruationsblut steht, war jahrzehntelang blau, erst im September 2021 zeigte ein Hersteller erstmalig eine Flüssigkeit, welche realitätsnah in der Farbe Rot dargestellt wurde (1). Hygieneartikel, die Menstruierende zwingend benötigen, sind in Deutschland mit wenigen Ausnahmen auf öffentlichen Toiletten nicht verfügbar: Das Nicht-Sichtbarsein offenbarte auch im Jahr 2021 das Tabu um natürliche biologische Prozesse des weiblichen Körpers. Scham und Einschränkungen, die sich verhindern ließen, sind die Folge. Menstruierende werden in ihrem Wohlbefinden limitiert, und negative Erlebnisse führen dazu, dass Betroffene in der Ausübung von sozialen, schulischen und beruflichen Aktivitäten nicht nur durch die Menstruation selbst, sondern auch durch Normen und Erziehungsmuster beeinträchtigt sind, wie zahlreiche internationale Studien gezeigt haben (2). Für den deutschen Hochschulkontext fehlen solche Studien bislang
