Digital Library of Gesellschaft für Informatik e.V.
Not a member yet
40758 research outputs found
Sort by
A Complete Course Design for Teaching Machine Learning with Automated Testing for Learning Support
No full textThis paper describes the design of a complete course on machine learning for undergraduate and graduate students with little programming experience, which is made available as open educational resource. The practical learning sessions are supported by automated feedback, addressing both technical correctness and conceptual understanding. While most automated assessment systems are designed for grading, our focus is on formative feedback helping students to build confidence and competence in applied machine learning. A mixture of static and dynamic testing is used to address different challenges of student support.
To implement the course, three different setups and tools were tested and compared for the best learning experience: Moodle with VPL, Git with CI/CD pipelines, and PyCharm with JetBrains Academy
Mehr Pionierinnen für die Informatik – Ein Programm zur Inspiration und Orientierung zum Informatikstudium für Schülerinnen
No full textEin fortwährend relevantes Thema in der Informatik und ihrer Didaktik ist der Gender-Gap. Das Projekt PIONIERIN zielt darauf ab, Schülerinnen den Weg ins Informatikstudium zu bereiten. Im Fokus steht hierbei der Übergang von (außer-)schulischen Informatikaktivitäten zum Studium durch die Entwicklung von Lernumgebungen, die bekannte Forschungsergebnisse berücksichtigen und gezielt mit Informatikinhalten der ersten Semester verbinden. Die didaktisch rekonstruierten Lernangebote knüpfen dabei gezielt an den Perspektiven junger Frauen auf das Informatikstudium an. Forschungsseitig stehen die Wirksamkeit dieser Maßnahmen sowie Beweggründe für oder gegen ein Informatikstudium im Fokus, um langfristig den Gender-Gap in der Informatik zu reduzieren
Integrating Human Feedback in VR – A Human-in-the-Loop Approach to Real-Time Gesture Recognition
No full textStudies in virtual reality (VR) often suffer from missing participant feedback due to limited sensor data available on VR devices. However, some experiments require direct feedback to be evaluated in the VR scene immediately, which tends to be challenging. Our setup utilizes a coordinated setup of hardware and software components to provide a feedback loop from participants' gestures into the VR scene so entities can react to people's actions while simultaneously collecting data from all connected systems. This demo showcases a study setup including (a) a central data broker with low- and high-frequency data storage, (b) a gesture recognition and publishing system, (c) a VR system to collect entity movement data and voice transcriptions, and (d) a command-line interface for managing the system. This should facilitate study execution by limiting waiting times for participants and improving the overall data collection process
Wrist-Powered Touch: Evaluating Smartwatch-Based Touch Gesture Recognition for Interaction in Extended Reality
No full textThe lack of tactile feedback and occlusion from visual tracking systems hinders touch interaction in Extended Reality (XR) environments. In this work, we present a method that enables touch gesture interaction on any physical surface using smartwatch-based inertial sensing. By using accelerometer data from a smartwatch, our approach captures micro-wrist movements to detect seven distinct touch gestures with 91.67% accuracy via a Long Short-Term Memory neural network. Our approach allows users to interact with XR interfaces anchored to everyday surfaces, such as tables or walls, while benefiting from natural haptic feedback. We introduce a dataset collected from 20 participants to demonstrate the feasibility through a controlled study. Our findings show that smartwatch sensing offers a low-cost, mobile, and accurate solution for extending XR input capabilities beyond the camera's view on physical surfaces, paving the way for more natural and privacy-preserving interaction in future XR systems
BEHAVE AI@MuC: Towards the Human-Centered Design and Evaluation of Proactive AI Agents
No full textAdvancements in AI are a reason for an ongoing interest in studying human interactions with increasingly autonomous and proactive agents. Despite the growing research interest in proactive agents, design and evaluation methodologies continue to be largely informed by reactive system designs and arguably legacy principles. With our full-day multidisciplinary workshop, we aim to continue a new workshop series on closing the critical gap between reactive and proactive systems research. To this end, the series brings together researchers and practitioners from the interdisciplinary HCI community, both from academia and industry. We will address the challenges of designing and evaluating proactive agents by reflecting on issues with existing evaluation methods, identify opportunities in designing proactive systems, and discuss potential solutions, best practices, new theories, and human-centric guidelines. Ultimately, our goal is to map out key focus areas and research challenges, fostering strong interdisciplinary relationships within and across fields related to Artificial Intelligence (AI) and Human-Computer Interaction (HCI)
Licht an! Wie Grundschüler eine Lernumgebung smart gestalten: Entwicklung eines lernförderlichen Assistenzsystems mit dem Calliope mini
No full textIm Rahmen des Informatikunterrichts in einer vierten Grundschulklasse wurde ein innovatives Unterrichtsprojekt zur Förderung digitaler Kompetenzen, informatischer Denkweisen und nachhaltigen Handelns umgesetzt. Die Schülerinnen und Schüler entwickelten mit dem Mikrocontroller Calliope mini einen digitalen „Lernhelfer“, der den Lichtwert und die Lautstärke im Klassenzimmer misst und – abhängig vom Messergebnis – eine visuelle oder akustische Rückmeldung gibt. Ziel war es, eine lernförderliche Umgebung aktiv mitzugestalten und gleichzeitig zentrale Konzepte wie Eingabe–Verarbeitung–Ausgabe, Sensorik, bedingte Anweisungen und Algorithmik kindgerecht zu vermitteln. Das Projekt greift reale Erfahrungen der Kinder auf und überträgt sie in eine praktische, informatisch fundierte Problemlösung. Durch die eigene Programmierung eines nützlichen Geräts erkennen sie zudem die gesellschaftliche Bedeutung von Informatik im Alltag
Fallstudie zum Identitätsabgleich mittels digital-anthropometrischem Rig
No full textAnhand eines realen Falls wird ein digital-anthropometrischer Rigabgleich zwischen einer tatverdächtigen Person und einem Täter bei einem bewaffneten Raub evaluiert. Den Gutachtern bzw. Gutachterinnen lag Videomaterial von der Tat, sowie Vergleichsvideos vor. Von besonderem Interesse sind verschiedene Kameraperspektiven und der Prozess der Synchronisation. Somit konnte das personenspezifische Rig mit dem Tatvideo und dem Vergleichsvideo abgeglichen werden. Diese Ergebnisse wurden evaluiert und führten zu neuen Erkenntnissen für die numerische Bewertung von digital-anthropometrischen Rigs in der Strafverfolgung. Durch die Möglichkeit der Synchronisation verschiedener Kameras erfolgte eine neuartige Verortung des Täters im 3D-Modell des Ereignisortes. Es konnten sowohl handerstellte Rigs, als auch Algorithmus basierte Rigs zur Evaluierung genutzt werden
Research Data and Software Competencies Workshop 2025: Summary
No full textThe Research Data and Software Competencies (RDSC) Workshop 2025, organized in the context of INFORMATIK 2025, focuses on identifying essential competencies in research data and software and exploring effective strategies for their development. Building on the outcomes of a workshop that took place as part of the “Themenwoche Digitale Kompetenzen in der Wissenschaft” in 2024, the workshop brings together interdisciplinary contributions ranging from conceptual foundations to concrete approaches and tools for competency development
The use of digital technologies in mixed ability teams: opportunities and challenges for occupational participation of people with sensory disabilities
No full textNew technologies are on the rise and are increasingly being used in the workplace. Communication technologies in particular are shaping and changing teamwork. Successful Teamwork is a resource for individuals in the workplace particularly for people with disabilities in order to ensure a positive inclusion process. However, technology often presents a barrier for people with disabilities. Therefore, the presented project addresses the question of how the use of technology influences the processes and products of teamwork in mixed-ability teams. To answer this question, three different studies will be conducted using a mixed methods approach. First, a literature-based research and complementary problem-centred interviews will be used to investigate which factors influence the cooperation of (mixed-ability) teams and which variables are influenced by the quality of the fit between technology, task and individual. Next, a work analysis will provide further insights into how well the used technology fits and how this affects the previously determined dependent variables. Finally, the findings will be tested in laboratory studies and recommendations for action in the working world will be formulated
