Refine
Document type
- Conference Proceeding (57) (remove)
Has full text
- Yes (57) (remove)
Keywords
- Poster (3)
- Convolutional neural network (2)
- Sustainability (2)
- Artificial intelligence (1)
- Augmentation (1)
- Bin picking (1)
- Blockchain (1)
- CNN (1)
- COVID-19 pandemic (1)
- Data protection (1)
Health informatics plays a crucial role in modern healthcare provision. Training and continuous education are essential to bolster the healthcare workforce on health informatics. In this work, we present the training events within EU-funded DigNest project. The aim of the training events, the subjects offered, and the overall evaluation of the results are described in this paper.
In diesem Vortrag werde ich auf die Programmierumgebungen (ROS) und Schnittstellen (keras/Tensorflow) eingehen, die es ermöglichen Roboter mit Hilfe von maschinellem Lernen zu trainieren. Dabei werde ich insbesondere die Möglichkeiten vorstellen, wie man einen Roboter in der Simulation (gazebo) trainieren kann, um die trainierten Modelle auf echte Roboter zu übertragen. Anhand von praktischen Beispielen mit mobilen Robotern und Greifarmen werden die Konzepte des Reinforcement Learnings, Active Learnings, Transfer Learnings und der Objekterkennung demonstriert. Das Testszenario besteht aus einem Holz-Labyrinth und einem Turtlebot Roboter, der mit Laser Range Scanner und einer 2D-Kamera ausgestattet ist. Dabei soll der Roboter lernen, autonom den Weg zur angegebenen Zielposition zu planen ohne dabei gegen ein Hindernis zu fahren. Es wird hierbei untersucht in wie weit die trainierten Modelle in leicht abgeänderten Szenarien funktionsfähig bleiben.
The YOLO series of object detection algorithms, including YOLOv4 and YOLOv5, have shown superior performance in various medical diagnostic tasks, surpassing human ability in some cases. However, their black-box nature has limited their adoption in medical applications that require trust and explainability of model decisions. To address this issue, visual explanations for AI models, known as visual XAI, have been proposed in the form of heatmaps that highlight regions in the input that contributed most to a particular decision. Gradient-based approaches, such as Grad-CAM, and non-gradient-based approaches, such as Eigen-CAM, are applicable to YOLO models and do not require new layer implementation. This paper evaluates the performance of Grad-CAM and Eigen-CAM on the VinDrCXR Chest X-ray Abnormalities Detection dataset and discusses the limitations of these methods for explaining model decisions to data scientists.
Applications for the Internet of Things are becoming increasingly popular. Due to the large amount of available context data, such applications can be used effectively in many domains. By interlinking these data and analyzing them, it is possible to gather a lot of knowledge about a user. Therefore, these applications pose a threat to privacy. In this paper, we illustrate this threat by looking at a real-world application scenario. Current state of the art focuses on privacy mechanisms either for Smart Things or for big data processing systems. However, our studies show that for a comprehensive privacy protection a holistic view on these applications is required. Therefore, we describe how to combine two promising privacy approaches from both categories, namely AVARE and PATRON. Evaluation results confirm the thereby achieved synergy effects.
In this paper, we present a study on the utilization of smart medical wearables and the user manuals of such devices. A total of 342 individuals provided input for 18 questions that address user behavior in the investigated context and the connections between various assessments and preferences. The presented work clusters individuals based on their professional relation to user manuals and analyzes the obtained results separately for these groups.
The Sustainable Development Goals (SDGs) of the United Nations focus on key issues for the transformation of our world towards sustainability. We argue for stronger integration of the SDGs into requirements and software engineering and for the creation of methods and tools that support the analysis of potential effects of software systems on sustainability in general and on SDGs in particular. To demonstrate one way of undertaking this integration, we report on how the Sustainability Awareness Framework (SusAF -- a tool developed by the authors of this paper) can be mapped to the SDGs, allowing the identification of potential effects of software systems on sustainability and on the SDGs. This mapping exercise demonstrates that it is possible for requirements engineers working on a specific system to consider that system's impact with respect to SDGs.
Cylindrical grinding is an important process in the manufacturing industry. During this process, the problem of grinding burn may appear, which can cause the workpiece to be worthless. In this work, a machine learning neural network approach is used to predict grinding burn based on the process parameters to prevent damage. A small dataset of 21 samples was gathered at a specific machine, grinding always the same element type with different process parameters. Each workpiece got a label from 0 to 3 after the process, indicating the severity of grinding burn. To get a robust neural network model, the dataset has been scaled by augmentation controlled by grinding experts, to generate more samples for training a neural network model. As a result, the model is able to predict the severity of grinding burn in a multiclass classification and it turned out that even with little data, the model performed well.
For many practitioners, considering sustainability during a software development project is a challenge. The Sustainability Awareness Framework (SusAF) is a tool for thinking through short, medium-and long-term impacts of socio-technical systems on its surrounding environment. While SusAF has been used by several companies, is not widely adopted in industry yet. In this Vision Paper, we discuss the options for extending the reach of SusAF and what it would take to evolve SusAF into a (de-facto) standard
Specification of neck muscle dysfunction through digital image analysis using machine learning
(2022)
This poster presents a Montenegrin Digital Academic Innovation Hub aimed to support education, innovations, and academia-business cooperation in medical informatics (as one of four priority areas) at national level in Montenegro. The Hub topology and its organisation in the form of two main nodes, with services established within key pillars: Digital Education; Digital Business Support; Innovations and cooperation with industry; and Employment support.
Changes of human trunk circumferences during different breathing styles in different positions
(2023)
Digital transformation is now reaching into topics like End-of-life Care, Funeral Culture, and Coping with Grief. Those developments are inevitably accompanied by the growing challenge to design IT systems that are appropriate and helpful for the stakeholders involved. Our aim in this paper is to further introduce the rather new combined research field of Socioinformatics and Thanatology (the scientific study of death and dying) and to present it with the first results on which requirements to consider for the design of digital tools within ‘Thanatopractice’. By using Participatory Design and the Sustainability Awareness Framework (SusAF) in the context of three workshops on socio-technical systems (Online Pastoral Care, Virtual Graveyards, and AI Memory Avatars), we want to sensitize software practitioners to the multidimensional impacts of their products and services in a field, which the participants in the workshops often described as “highly sensitive”.
Context: The Software Engineering process can be seen as a socio-technical activity that involves fulfilling one's role as part of a team. Accordingly, software products and services are the result of a specific collaboration between employees (and other stakeholders). In recent years, sustainability, which Requirements Engineers often paraphrase as the ability of a system to endure, is becoming part of the process and thus the responsibility of Software Engineers (SE) as well. Objectives: This study shines the spotlight on the role of the SE: their self-attribution and their awareness for sustainability. We interviewed 13 SEs to figure out how they perceive their own role and to which extent they implement the topic of sustainability in their daily work. By visualizing these two sides, it is possible to debate changes and their possible paths to benefit the Software Engineering process including sustainability design. Results: A discrepancy between the current role and the ideal role of SEs becomes visible. It is characterized in particular by dwelling on their “classic” or time-honored tasks as an executive force, such as coding. At the same time, they point out the still missing necessity of an interdisciplinary, from communication coined working method. According to our interviewees SEs are inefficiently involved in the design process. They do not sufficiently assume their responsibility for the software and its sustainability impacts.
Year after year, software engineers celebrate new achievements in the field of AI. At the same time, the question about the impacts of AI on society remains insufficiently answered in terms of a comprehensive technology assessment. This article aims to provide software practitioners with a theoretically grounded and practically tested approach that enables an initial understanding of the potential multidimensional impacts. Subsequently, the results form the basis for discussions on AI software requirements. The approach is based on the Sustainability Awareness Framework (SusAF) and Participatory Design. We conducted three workshops on different AI topics: 1. Autonomous Driving, 2. Music Composition, and 3. Memory Avatars. Based on the results of the workshops we conclude that a two-level approach should be adopted: First, a broad one that includes a diverse selection of stakeholders and overall impact analysis. Then, in a second step, specific approaches narrowing down the stakeholders and focusing on one or few impact areas.
3D Computer Vision for the Industrial Metaverse - On the potentials of Neural Radiance Fields
(2023)
The industrial metaverse refers to the use of virtual reality (VR) and augmented reality (AR) technologies in the context of industry and manufacturing. It is envisioned as a shared, immersive digital space where people can interact with and manipulate virtual representations of physical objects and processes. The industrial metaverse has the potential to transform the way products are designed, manufactured, and maintained,
enabling new levels of collaboration, automation, and innovation.
It further includes virtual representations of humans, also known as avatars. These avatars can be used to enable remote collaboration and communication between people in the virtual space. In this way, the industrial metaverse can facilitate virtual meetings, trainings, and other interactive experiences that involve human participants.
Neural Radiance Fields (NeRFs) are a powerful tool for synthesizing photorealistic images of 3D objects, including virtual representations of humans known as avatars. In this talk, we will discuss the potential applications of NeRFs in generating high-fidelity objects and avatars for use in the industrial metaverse.
Führt die Omnipräsenz von Smartphone, Tablet & Co zu einer neuen Form des »Smart Social eLearning«?
(2016)
Ausgehend von dem Gedanken, dass das Medium Fernsehen in den letzten Jahren immer mehr durch das Internet als Leitmedium abgelöst wurde, wird in dem Beitrag eine Etablierung von SmartDevices im Unterricht diskutiert. Dabei wird aufgezeigt, dass die bisherige Entwicklung des Medieneinsatzes im Unterricht von multimedialen Lernprogrammen bis zu einem heutigen und zukünftigen „Smart Social eLearning“ reichen könnte, insbesondere durch den Einsatz der SmartDevices wie Tablets, Smartphones oder Smartwatches.
Darauf aufbauend werden die Ergebnisse einer empirischen Studie über den tatsächlichen Einsatz von und den Wunsch nach SmartDevices präsentiert. Dabei zeigte sich, dass der Großteil der Studierenden bereits SmartDevices zur Weiterbildung eingesetzt hat und auch bereits der Wunsch nach einem Einsatz dieser Geräte zur Weiterbildung besteht.
Evaluation of high compliant elastomer balloons for the identification of artery biomechanics
(2023)
Nachhaltigkeit ist für die Gesellschaften unseres Planeten von grundlegender Bedeutung, ebenso wie Software Systeme immer mehr Teil der heutigen Gesellschaften werden. Daher gewinnt Nachhaltigkeit auch immer mehr an Relevanz im Software Engineering und es wurden erste Ansätze entwickelt, um Nachhaltigkeit bei dem Software System Design zu berücksichtigen. Dennoch bleibt es schwer die erst später eintreffenden Auswirkungen von Entscheidungen, die beim System Design getroffen werden, zu erkennen und zu bewerten. Um diese schwierige Aufgabe zu unterstützen, wird in der Keynote die Metapher „Sustainability Debt“ vorgestellt. Die Metapher hilft bei der Identifikation, Dokumentation und Kommunikation von Nachhaltigkeitsfragen im Software Engineering. Sie baut auf der bestehenden Metapher des „Technical Debt“ auf und erweitert diese um vier weitere Dimensionen der Nachhaltigkeit (individuell, sozial, ökologisch, ökonomisch). Neben der Bedeutung der Metapher Sustainability Debt und ihrer Verwendung im Software Engineering wird im Rahmen der Keynote auch darauf eingegangen wie im Software Engineering Entscheidungen getroffen werden. Da Entscheidungen im Rahmen des Sustainability Debts immer bedeuten einen Kompromiss zu schließen zwischen zeitnahen und entfernten Ergebnissen. Bei solchen intertemporalen Entscheidungen werden entfernte Ergebnisse oft als weniger bedeutsam bewertet als zeitnahe, was berücksichtigt werden muss, um eine entsprechende Entscheidungsunterstützung zur Verringerung des Sustainability Debts zu liefern.
Creating Interactive Experiences together with People with Dementia – an Inclusive Design Story
(2017)
Separation of ventilation and cardiac activity on recorded voltages before EIT image reconstruction
(2023)
It is a fundamental right of every natural person to control which personal information is collected, stored and processed by whom, for what purposes and how long. In fact, many (cloud based) services can only be used if the user allows them broad data collection and analysis. Often, users can only decide to either give their data or not to participate in communities. The refusal to provide personal data results in significant drawbacks for social interaction. That is why we believe that there is a need for tools to control one's own data in an easy and effective way as protection against economic interest of global companies and their cloud computing systems (as data collector from apps, mobiles and services). Especially, as nowadays everybody is permanently online using different services and devices, users are often lacking the means to effectively control the access to their private data. Therefore, we present an approach to manage and distribute privacy settings: PRIVACY-AVARE is intended to enable users to centrally determine their data protection preferences and to apply them on different devices. Thus, users gain control over their data when using cloud based services. In this paper, we present the main idea of PRIVACY-AVARE.
Unter dem Motto „Technologie bewegt Pflege“ werden Beiträge aus Wissenschaft, Praxis und Industrie präsentiert. In einem abwechslungsreichen Programm werden aus verschiedenen Blickwinkeln die unterschiedlichen Schwerpunkte im Themenfeld Pflege und Technik diskutiert. Die Beiträge auf der 5. Clusterkonferenz, ausgerichtet vom Pflegepraxiszentrum Freiburg, sind im vorliegenden Abstractband ausgeführt.