TY - JOUR A1 - Bräuer-Burchardt, Christian A1 - Munkelt, Christoph A1 - Bleier, Michael A1 - Heinze, Matthias A1 - Gebhart, Ingo A1 - Kühmstedt, Peter A1 - Notni, Gunther T1 - Underwater 3D scanning system for cultural heritage documentation JF - Remote Sensing N2 - Three-dimensional capturing of underwater archeological sites or sunken shipwrecks can support important documentation purposes. In this study, a novel 3D scanning system based on structured illumination is introduced, which supports cultural heritage documentation and measurement tasks in underwater environments. The newly developed system consists of two monochrome measurement cameras, a projection unit that produces aperiodic sinusoidal fringe patterns, two flashlights, a color camera, an inertial measurement unit (IMU), and an electronic control box. The opportunities and limitations of the measurement principles of the 3D scanning system are discussed and compared to other 3D recording methods such as laser scanning, ultrasound, and photogrammetry, in the context of underwater applications. Some possible operational scenarios concerning cultural heritage documentation are introduced and discussed. A report on application activities in water basins and offshore environments including measurement examples and results of the accuracy measurements is given. The study shows that the new 3D scanning system can be used for both the topographic documentation of underwater sites and to generate detailed true-scale 3D models including the texture and color information of objects that must remain under water. KW - underwater 3D scanning KW - structured light illumination KW - object reconstruction KW - 3D model generation KW - site mapping Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-311116 SN - 2072-4292 VL - 15 IS - 7 ER - TY - JOUR A1 - Donnermann, Melissa A1 - Schaper, Philipp A1 - Lugrin, Birgit T1 - Social robots in applied settings: a long-term study on adaptive robotic tutors in higher education JF - Frontiers in Robotics and AI N2 - Learning in higher education scenarios requires self-directed learning and the challenging task of self-motivation while individual support is rare. The integration of social robots to support learners has already shown promise to benefit the learning process in this area. In this paper, we focus on the applicability of an adaptive robotic tutor in a university setting. To this end, we conducted a long-term field study implementing an adaptive robotic tutor to support students with exam preparation over three sessions during one semester. In a mixed design, we compared the effect of an adaptive tutor to a control condition across all learning sessions. With the aim to benefit not only motivation but also academic success and the learning experience in general, we draw from research in adaptive tutoring, social robots in education, as well as our own prior work in this field. Our results show that opting in for the robotic tutoring is beneficial for students. We found significant subjective knowledge gain and increases in intrinsic motivation regarding the content of the course in general. Finally, participation resulted in a significantly better exam grade compared to students not participating. However, the extended adaptivity of the robotic tutor in the experimental condition did not seem to enhance learning, as we found no significant differences compared to a non-adaptive version of the robot. KW - human-robot interaction KW - adaptive tutoring KW - higher education KW - robot-supported training KW - technology-supported education KW - robotic tutor Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-266012 SN - 2296-9144 VL - 9 ER - TY - JOUR A1 - Döllinger, Nina A1 - Wolf, Erik A1 - Mal, David A1 - Wenninger, Stephan A1 - Botsch, Mario A1 - Latoschik, Marc Erich A1 - Wienrich, Carolin T1 - Resize Me! Exploring the user experience of embodied realistic modulatable avatars for body image intervention in virtual reality JF - Frontiers in Virtual Reality N2 - Obesity is a serious disease that can affect both physical and psychological well-being. Due to weight stigmatization, many affected individuals suffer from body image disturbances whereby they perceive their body in a distorted way, evaluate it negatively, or neglect it. Beyond established interventions such as mirror exposure, recent advancements aim to complement body image treatments by the embodiment of visually altered virtual bodies in virtual reality (VR). We present a high-fidelity prototype of an advanced VR system that allows users to embody a rapidly generated personalized, photorealistic avatar and to realistically modulate its body weight in real-time within a carefully designed virtual environment. In a formative multi-method approach, a total of 12 participants rated the general user experience (UX) of our system during body scan and VR experience using semi-structured qualitative interviews and multiple quantitative UX measures. Using body weight modification tasks, we further compared three different interaction methods for real-time body weight modification and measured our system’s impact on the body image relevant measures body awareness and body weight perception. From the feedback received, demonstrating an already solid UX of our overall system and providing constructive input for further improvement, we derived a set of design guidelines to guide future development and evaluation processes of systems supporting body image interventions. KW - virtual reality KW - avatar embodiment KW - user experience KW - body awareness KW - body weight perception KW - body weight modification KW - body image disturbance KW - eating and body weight disorders Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-292940 SN - 2673-4192 VL - 3 ER - TY - JOUR A1 - Halbig , Andreas A1 - Babu , Sooraj K. A1 - Gatter , Shirin A1 - Latoschik , Marc Erich A1 - Brukamp, Kirsten A1 - von Mammen , Sebastian T1 - Opportunities and challenges of Virtual Reality in healthcare – a domain experts inquiry JF - Frontiers in Virtual Reality N2 - In recent years, the applications and accessibility of Virtual Reality (VR) for the healthcare sector have continued to grow. However, so far, most VR applications are only relevant in research settings. Information about what healthcare professionals would need to independently integrate VR applications into their daily working routines is missing. The actual needs and concerns of the people who work in the healthcare sector are often disregarded in the development of VR applications, even though they are the ones who are supposed to use them in practice. By means of this study, we systematically involve health professionals in the development process of VR applications. In particular, we conducted an online survey with 102 healthcare professionals based on a video prototype which demonstrates a software platform that allows them to create and utilise VR experiences on their own. For this study, we adapted and extended the Technology Acceptance Model (TAM). The survey focused on the perceived usefulness and the ease of use of such a platform, as well as the attitude and ethical concerns the users might have. The results show a generally positive attitude toward such a software platform. The users can imagine various use cases in different health domains. However, the perceived usefulness is tied to the actual ease of use of the platform and sufficient support for learning and working with the platform. In the discussion, we explain how these results can be generalized to facilitate the integration of VR in healthcare practice. KW - virtual reality KW - healthcare KW - therapy KW - rehabilitation KW - ethics KW - technology acceptance KW - authoring platform KW - healthcare professionals Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-284752 SN - 2673-4192 VL - 3 ER - TY - JOUR A1 - Hartelt, Alexander A1 - Puppe, Frank T1 - Optical Medieval Music Recognition using background knowledge JF - Algorithms N2 - This paper deals with the effect of exploiting background knowledge for improving an OMR (Optical Music Recognition) deep learning pipeline for transcribing medieval, monophonic, handwritten music from the 12th–14th century, whose usage has been neglected in the literature. Various types of background knowledge about overlapping notes and text, clefs, graphical connections (neumes) and their implications on the position in staff of the notes were used and evaluated. Moreover, the effect of different encoder/decoder architectures and of different datasets for training a mixed model and for document-specific fine-tuning based on an extended OMR pipeline with an additional post-processing step were evaluated. The use of background models improves all metrics and in particular the melody accuracy rate (mAR), which is based on the insert, delete and replace operations necessary to convert the generated melody into the correct melody. When using a mixed model and evaluating on a different dataset, our best model achieves without fine-tuning and without post-processing a mAR of 90.4%, which is raised by nearly 30% to 93.2% mAR using background knowledge. With additional fine-tuning, the contribution of post-processing is even greater: the basic mAR of 90.5% is raised by more than 50% to 95.8% mAR. KW - Optical Music Recognition KW - historical document analysis KW - medieval manuscripts KW - neume notation KW - fully convolutional neural networks KW - background knowledge Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-278756 SN - 1999-4893 VL - 15 IS - 7 ER - TY - CHAP A1 - Jannidis, Fotis A1 - Reger, Isabella A1 - Weimer, Lukas A1 - Krug, Markus A1 - Puppe, Frank T1 - Automatische Erkennung von Figuren in deutschsprachigen Romanen N2 - Eine wichtige Grundlage für die quantitative Analyse von Erzähltexten, etwa eine Netzwerkanalyse der Figurenkonstellation, ist die automatische Erkennung von Referenzen auf Figuren in Erzähltexten, ein Sonderfall des generischen NLP-Problems der Named Entity Recognition. Bestehende, auf Zeitungstexten trainierte Modelle sind für literarische Texte nur eingeschränkt brauchbar, da die Einbeziehung von Appellativen in die Named Entity-Definition und deren häufige Verwendung in Romantexten zu einem schlechten Ergebnis führt. Dieses Paper stellt eine anhand eines manuell annotierten Korpus auf deutschsprachige Romane des 19. Jahrhunderts angepasste NER-Komponente vor. KW - Digital Humanities KW - Figurenerkennung KW - Named-Entity-Recognition KW - Domänenadaption KW - Literatur Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-143332 UR - https://dhd2015.uni-graz.at/ ER - TY - CHAP A1 - Klemke, Roland A1 - Sanusi, Khaleel Asyraaf Mat A1 - Rose, Melina T1 - Immersive Game Technologies for Innovative Education - A Method for Experimental Interdisciplinary Technology Transfer T2 - Proceedings of the 1st Games Technology Summit N2 - Immersive, sensor-enabled technologies such as augmented and virtual reality expand the way human beings interact with computers significantly. While these technologies are widely explored in entertainment games, they also offer possibilities for educational use. However,their uptake in education is so far very limited. Within the ImTech4Ed project, we aim at systematically exploring the power of interdisciplinary, international hackathons as a novel method to create immersive educational game prototypes and as a means to transfer these innovative technical prototypes into educational use. To achieve this, we bring together game design and development, where immersive and interactive solutions are designed and developed; computer science, where the technological foundations for immersive technologies and for scalable architectures for these are created; and teacher education, where future teachers are educated. This article reports on the concept and design of these hackathons. KW - immersive technologies KW - educational games KW - hackathons Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-245843 ER - TY - THES A1 - Marquardt, André T1 - Machine-Learning-Based Identification of Tumor Entities, Tumor Subgroups, and Therapy Options T1 - Bestimmung von Tumorentitäten, Tumorsubgruppen und Therapieoptionen basierend auf maschinellem Lernen N2 - Molecular genetic analyses, such as mutation analyses, are becoming increasingly important in the tumor field, especially in the context of therapy stratification. The identification of the underlying tumor entity is crucial, but can sometimes be difficult, for example in the case of metastases or the so-called Cancer of Unknown Primary (CUP) syndrome. In recent years, methylome and transcriptome utilizing machine learning (ML) approaches have been developed to enable fast and reliable tumor and tumor subtype identification. However, so far only methylome analysis have become widely used in routine diagnostics. The present work addresses the utility of publicly available RNA-sequencing data to determine the underlying tumor entity, possible subgroups, and potential therapy options. Identification of these by ML - in particular random forest (RF) models - was the first task. The results with test accuracies of up to 99% provided new, previously unknown insights into the trained models and the corresponding entity prediction. Reducing the input data to the top 100 mRNA transcripts resulted in a minimal loss of prediction quality and could potentially enable application in clinical or real-world settings. By introducing the ratios of these top 100 genes to each other as a new database for RF models, a novel method was developed enabling the use of trained RF models on data from other sources. Further analysis of the transcriptomic differences of metastatic samples by visual clustering showed that there were no differences specific for the site of metastasis. Similarly, no distinct clusters were detectable when investigating primary tumors and metastases of cutaneous skin melanoma (SKCM). Subsequently, more than half of the validation datasets had a prediction accuracy of at least 80%, with many datasets even achieving a prediction accuracy of – or close to – 100%. To investigate the applicability of the used methods for subgroup identification, the TCGA-KIPAN dataset, consisting of the three major kidney cancer subgroups, was used. The results revealed a new, previously unknown subgroup consisting of all histopathological groups with clinically relevant characteristics, such as significantly different survival. Based on significant differences in gene expression, potential therapeutic options of the identified subgroup could be proposed. Concludingly, in exploring the potential applicability of RNA-sequencing data as a basis for therapy prediction, it was shown that this type of data is suitable to predict entities as well as subgroups with high accuracy. Clinical relevance was also demonstrated for a novel subgroup in renal cell carcinoma. The reduction of the number of genes required for entity prediction to 100 genes, enables panel sequencing and thus demonstrates potential applicability in a real-life setting. N2 - Molekulargenetische Analysen, wie z. B. Mutationsanalysen, gewinnen im Tumorbereich zunehmend an Bedeutung, insbesondere im Zusammenhang mit der Therapiestratifizierung. Die Identifizierung der zugrundeliegenden Tumorentität ist von entscheidender Bedeutung, kann sich aber manchmal als schwierig erweisen, beispielsweise im Falle von Metastasen oder dem sogenannten Cancer of Unknown Primary (CUP)-Syndrom. In den letzten Jahren wurden Methylom- und Transkriptom-Ansätze mit Hilfe des maschinellen Lernens (ML) entwickelt, die eine schnelle und zuverlässige Identifizierung von Tumoren und Tumorsubtypen ermöglichen. Bislang werden jedoch nur Methylomanalysen in der Routinediagnostik eingesetzt. Die vorliegende Arbeit befasst sich mit dem Nutzen öffentlich zugänglicher RNA-Sequenzierungsdaten zur Bestimmung der zugrunde liegenden Tumorentität, möglicher Untergruppen und potenzieller Therapieoptionen. Die Identifizierung dieser durch ML - insbesondere Random-Forest (RF)-Modelle - war die erste Aufgabe. Die Ergebnisse mit Testgenauigkeiten von bis zu 99 % lieferten neue, bisher unbekannte Erkenntnisse über die trainierten Modelle und die entsprechende Entitätsvorhersage. Die Reduktion der Eingabedaten auf die 100 wichtigsten mRNA-Transkripte führte zu einem minimalen Verlust an Vorhersagequalität und könnte eine Anwendung in klinischen oder realen Umgebungen ermöglichen. Durch die Einführung des Verhältnisses dieser Top 100 Gene zueinander als neue Datenbasis für RF-Modelle wurde eine neuartige Methode entwickelt, die die Verwendung trainierter RF-Modelle auf Daten aus anderen Quellen ermöglicht. Eine weitere Analyse der transkriptomischen Unterschiede von metastatischen Proben durch visuelles Clustering zeigte, dass es keine für den Ort der Metastasierung spezifischen Unterschiede gab. Auch bei der Untersuchung von Primärtumoren und Metastasen des kutanen Hautmelanoms (SKCM) konnten keine unterschiedlichen Cluster festgestellt werden. Mehr als die Hälfte der Validierungsdatensätze wiesen eine Vorhersagegenauigkeit von mindestens 80% auf, wobei viele Datensätze sogar eine Vorhersagegenauigkeit von 100% oder nahezu 100% erreichten. Um die Anwendbarkeit der verwendeten Methoden zur Identifizierung von Untergruppen zu untersuchen, wurde der TCGA-KIPAN-Datensatz verwendet, welcher die drei wichtigsten Nierenkrebs-Untergruppen umfasst. Die Ergebnisse enthüllten eine neue, bisher unbekannte Untergruppe, die aus allen histopathologischen Gruppen mit klinisch relevanten Merkmalen, wie z. B. einer signifikant unterschiedlichen Überlebenszeit, besteht. Auf der Grundlage signifikanter Unterschiede in der Genexpression konnten potenzielle therapeutische Optionen für die identifizierte Untergruppe vorgeschlagen werden. Zusammenfassend lässt sich sagen, dass bei der Untersuchung der potenziellen Anwendbarkeit von RNA-Sequenzierungsdaten als Grundlage für die Therapievorhersage gezeigt werden konnte, dass diese Art von Daten geeignet ist, sowohl Entitäten als auch Untergruppen mit hoher Genauigkeit vorherzusagen. Die klinische Relevanz wurde auch für eine neue Untergruppe beim Nierenzellkarzinom demonstriert. Die Verringerung der für die Entitätsvorhersage erforderlichen Anzahl von Genen auf 100 Gene ermöglicht die Sequenzierung von Panels und zeigt somit die potenzielle Anwendbarkeit in der Praxis. KW - Maschinelles Lernen KW - Krebs KW - Tumor KW - Sequenzdaten KW - Random Forest KW - Vorhersage KW - RNA-Sequenzierung KW - Prognose Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-329548 ER - TY - JOUR A1 - Oberdörfer, Sebastian A1 - Schraudt, David A1 - Latoschik, Marc Erich T1 - Embodied gambling — investigating the influence of level of embodiment, avatar appearance, and virtual environment design on an online VR slot machine JF - Frontiers in Virtual Reality N2 - Slot machines are one of the most played games by players suffering from gambling disorder. New technologies like immersive Virtual Reality (VR) offer more possibilities to exploit erroneous beliefs in the context of gambling. Recent research indicates a higher risk potential when playing a slot machine in VR than on desktop. To continue this investigation, we evaluate the effects of providing different degrees of embodiment, i.e., minimal and full embodiment. The avatars used for the full embodiment further differ in their appearance, i.e., they elicit a high or a low socio-economic status. The virtual environment (VE) design can cause a potential influence on the overall gambling behavior. Thus, we also embed the slot machine in two different VEs that differ in their emotional design: a colorful underwater playground environment and a virtual counterpart of our lab. These design considerations resulted in four different versions of the same VR slot machine: 1) full embodiment with high socio-economic status, 2) full embodiment with low socio-economic status, 3) minimal embodiment playground VE, and 4) minimal embodiment laboratory VE. Both full embodiment versions also used the playground VE. We determine the risk potential by logging gambling frequency as well as stake size, and measuring harm-inducing factors, i.e., dissociation, urge to gamble, dark flow, and illusion of control, using questionnaires. Following a between groups experimental design, 82 participants played for 20 game rounds one of the four versions. We recruited our sample from the students enrolled at the University of Würzburg. Our safety protocol ensured that only participants without any recent gambling activity took part in the experiment. In this comparative user study, we found no effect of the embodiment nor VE design on neither the gambling frequency, stake sizes, nor risk potential. However, our results provide further support for the hypothesis of the higher visual angle on gambling stimuli and hence the increased emotional response being the true cause for the higher risk potential. KW - virtual reality KW - virtual environments KW - immersion KW - gambling KW - risks KW - embodiment KW - avatars Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-284662 SN - 2673-4192 VL - 3 ER - TY - JOUR A1 - Puppe, Frank T1 - Gesellschaftliche Perspektiven einer fachspezifischen KI für automatisierte Entscheidungen JF - Informatik Spektrum N2 - Die künstliche Intelligenz (KI) entwickelt sich rasant und hat bereits eindrucksvolle Erfolge zu verzeichnen, darunter übermenschliche Kompetenz in den meisten Spielen und vielen Quizshows, intelligente Suchmaschinen, individualisierte Werbung, Spracherkennung, -ausgabe und -übersetzung auf sehr hohem Niveau und hervorragende Leistungen bei der Bildverarbeitung, u. a. in der Medizin, der optischen Zeichenerkennung, beim autonomen Fahren, aber auch beim Erkennen von Menschen auf Bildern und Videos oder bei Deep Fakes für Fotos und Videos. Es ist zu erwarten, dass die KI auch in der Entscheidungsfindung Menschen übertreffen wird; ein alter Traum der Expertensysteme, der durch Lernverfahren, Big Data und Zugang zu dem gesammelten Wissen im Web in greifbare Nähe rückt. Gegenstand dieses Beitrags sind aber weniger die technischen Entwicklungen, sondern mögliche gesellschaftliche Auswirkungen einer spezialisierten, kompetenten KI für verschiedene Bereiche der autonomen, d. h. nicht nur unterstützenden Entscheidungsfindung: als Fußballschiedsrichter, in der Medizin, für richterliche Entscheidungen und sehr spekulativ auch im politischen Bereich. Dabei werden Vor- und Nachteile dieser Szenarien aus gesellschaftlicher Sicht diskutiert. KW - Künstliche Intelligenz KW - Ethik KW - Entscheidungsfindung Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-324197 SN - 0170-6012 VL - 45 IS - 2 ER -